Advertisement putting method and device based on data driving, equipment and storage medium

Abstract

The invention discloses an advertisement putting method based on data driving, and the method comprises the steps: generating initial advertisement putting data in response to an advertisement exposure putting instruction; putting the initial advertisement creative material to an advertisement channel platform corresponding to the advertisement exposure putting instruction; after the initial advertisement creative material is put, obtaining advertisement cost data, advertisement revenue data and user behavior data of the corresponding advertisement channel platform; performing multi-dimensional index analysis based on the advertisement cost data, the advertisement revenue data and the user behavior data to obtain an advertisement index report corresponding to the initial advertisement putting data; optimizing the initial advertisement putting data according to the advertisement index report to obtain target advertisement putting data; and performing advertisement putting again based on the target advertisement putting data. Through the feedback data after the putting behavior, the index data of the putting behavior is obtained, correction of the subsequent putting behavior is driven based on the index data, and the problem of how to improve the accuracy of advertisement putting materials in advertisement putting is solved.

Description

Technical Field

[0001] The present application relates to the technical field of advertisement delivery, and in particular to a data-driven advertisement delivery method, device, equipment and storage medium. Background Art

[0002] With the development of Internet technology, online advertising, as a new type of media, occupies an important position in media propaganda. Online advertising with the Internet as the communication medium has developed rapidly, and as a bridge between producers and consumers, consumers rely more on advertising in their product choices.

[0003] In the prior art, when managing the delivery of advertising materials, the delivery of advertising materials is often determined by manual experience. After the advertising materials are exposed, due to the lag in revenue analysis, the delivery strategy cannot be adjusted in real time, resulting in the advertiser's advertising revenue rate not being able to achieve scientific growth. Therefore, a data-driven advertising delivery method is urgently needed to achieve real-time adjustment of advertising delivery materials to solve the above problems. Summary of the invention

[0004] The present application provides a data-driven advertising delivery method, apparatus, device and storage medium, which obtains indicator data of the delivery behavior through feedback data after the delivery behavior, and drives the correction of subsequent delivery behavior based on the indicator data, thereby improving the positive driving force of the advertising delivery behavior during the advertising delivery process and solving the problem of how to improve the accuracy of advertising delivery materials during advertising delivery.

[0005] According to one aspect of the present application, a data-driven advertising delivery method is proposed, the method comprising:

[0006] In response to the advertisement exposure delivery instruction, initial advertisement delivery data is generated; the initial advertisement delivery data includes initial advertisement creative material, and the initial advertisement creative material is at least one of a plurality of preset creative materials in a creative material library;

[0007] Placing the initial advertising creative material on the advertising channel platform corresponding to the advertising exposure delivery instruction;

[0008] After the initial advertising creative material is released, obtaining advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform;

[0009] Perform multi-dimensional indicator analysis based on the advertising cost data, the advertising revenue data, and the user behavior data to obtain an advertising indicator report corresponding to the initial advertising delivery data;

[0010] Optimizing the initial advertising delivery data according to the advertising indicator report to obtain target advertising delivery data;

[0011] Re-deliver the advertisement based on the target advertisement delivery data.

[0012] In a possible implementation, the advertisement exposure delivery instruction includes delivery platform information, the delivery platform information represents an advertisement channel platform corresponding to the advertisement exposure delivery instruction, and the advertisement channel platform is at least one of a plurality of preset advertisement platforms.

[0013] The generating of initial advertisement delivery data in response to the advertisement exposure delivery instruction includes:

[0014] According to the advertisement exposure delivery instruction, obtaining preset creative materials corresponding to the advertisement exposure delivery instruction from the creative material library;

[0015] Based on the delivery platform information and the preset creative material, generating advertisement delivery data corresponding to the advertisement channel platform;

[0016] The advertisement delivery data corresponding to the advertisement channel platform is determined as the initial advertisement delivery data.

[0017] In a possible implementation, the method for constructing the creative material library includes:

[0018] Upload multiple pre-made creative files to the material management platform;

[0019] Labeling each creative file based on the attribute information of each creative file to obtain a creative label for each creative file; the attribute information includes a preset advertising platform for each creative file;

[0020] Recording the creative tag of each creative file based on the material management platform, and storing each creative file based on the material management platform to obtain preset creative materials corresponding to the creative tag of each creative file;

[0021] The creative material library is constructed based on the preset creative materials corresponding to the creative tags of each creative file.

[0022] In a possible implementation, after the initial advertising creative material is delivered, the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are obtained, including:

[0023] At a preset delivery time after the initial advertising creative material is delivered, obtaining cost data of the delivery behavior on the advertising channel platform as the advertising cost data;

[0024] and obtaining the revenue data of the delivery behavior on the advertising channel platform as the advertising revenue data;

[0025] Based on the tracking technology, the user tracking data of the preset delivery time is obtained from the advertising channel platform as the user behavior data.

[0026] In a possible implementation, the advertising indicator report includes multiple preset dimensions.

[0027] The multi-dimensional indicator analysis is performed based on the advertising cost data, the advertising revenue data and the user behavior data to obtain an advertising indicator report corresponding to the initial advertising delivery data, including:

[0028] Mapping the advertising cost data, the advertising revenue data, and the user behavior data to a plurality of preset dimensions respectively, and obtaining indicator calculation data corresponding to each preset dimension;

[0029] Performing indicator calculation on the indicator calculation data corresponding to each preset dimension to obtain the indicator calculation result of each preset dimension;

[0030] Based on the indicator calculation results of each preset dimension, an advertising indicator report corresponding to the initial advertising delivery data is obtained.

[0031] In a possible implementation, the optimizing the initial advertisement delivery data according to the advertisement indicator report to obtain target advertisement delivery data includes:

[0032] Performing an indicator analysis on the advertising indicator report to obtain an indicator analysis result;

[0033] When the indicator analysis result indicates that the initial advertisement delivery data contains preset creative materials that trigger warning conditions, the preset creative materials that trigger warning conditions are removed from the initial advertisement delivery data to obtain the target advertisement delivery data.

[0034] In a possible implementation, after obtaining the advertisement indicator report corresponding to the initial advertisement delivery data, the method further includes:

[0035] Perform an indicator analysis on the indicator calculation result of each preset dimension of the advertising indicator report to obtain the indicator analysis result:

[0036] When the indicator analysis result indicates that the indicator calculation result meets the preset warning condition, a warning message is sent to the advertising delivery specialist.

[0037] In a possible implementation, after re-delivering advertisements based on the target advertisement delivery data, the method further includes:

[0038] The target advertising delivery data is used again as the initial advertising delivery data, and the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are repeatedly obtained until the step of re-delivering advertising based on the target advertising delivery data is completed, so as to update the advertising delivery strategy in real time.

[0039] In another aspect, a data-driven advertising delivery device is provided, the device comprising:

[0040] An advertisement delivery data generation module, configured to generate initial advertisement delivery data in response to an advertisement exposure delivery instruction; the initial advertisement delivery data includes initial advertisement creative materials, and the initial advertisement creative materials are at least one of a plurality of preset creative materials in a creative material library;

[0041] An advertisement delivery module, used for delivering the initial advertisement creative material to the advertisement channel platform corresponding to the advertisement exposure delivery instruction;

[0042] An indicator data acquisition module, used to acquire advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform after the initial advertising creative material is released;

[0043] An indicator report generation module, used to perform multi-dimensional indicator analysis based on the advertising cost data, the advertising revenue data and the user behavior data to obtain an advertising indicator report corresponding to the initial advertising delivery data;

[0044] A target advertising delivery data determination module is used to optimize the initial advertising delivery data according to the advertising indicator report to obtain target advertising delivery data;

[0045] The advertisement delivery strategy updating module is used to re-deliver advertisements based on the target advertisement delivery data.

[0046] In a possible implementation, the advertisement exposure delivery instruction includes delivery platform information, the delivery platform information represents an advertisement channel platform corresponding to the advertisement exposure delivery instruction, and the advertisement channel platform is at least one of a plurality of preset advertisement platforms.

[0047] The advertisement delivery data generating module is used to:

[0048] According to the advertisement exposure delivery instruction, obtaining preset creative materials corresponding to the advertisement exposure delivery instruction from the creative material library;

[0049] Based on the delivery platform information and the preset creative material, generating advertisement delivery data corresponding to the advertisement channel platform;

[0050] The advertisement delivery data corresponding to the advertisement channel platform is determined as the initial advertisement delivery data.

[0051] In a possible implementation, the device further includes a material library construction module, and the material library construction module is used to:

[0052] Upload multiple pre-made creative files to the material management platform;

[0053] Labeling each creative file based on the attribute information of each creative file to obtain a creative label for each creative file; the attribute information includes a preset advertising platform for each creative file;

[0054] Recording the creative tag of each creative file based on the material management platform, and storing each creative file based on the material management platform to obtain preset creative materials corresponding to the creative tag of each creative file;

[0055] The creative material library is constructed based on the preset creative materials corresponding to the creative tags of each creative file.

[0056] In a possible implementation, the indicator data acquisition module is used to:

[0057] At a preset delivery time after the initial advertising creative material is delivered, obtaining cost data of the delivery behavior on the advertising channel platform as the advertising cost data;

[0058] and obtaining the revenue data of the delivery behavior on the advertising channel platform as the advertising revenue data;

[0059] Based on the tracking technology, the user tracking data of the preset delivery time is obtained from the advertising channel platform as the user behavior data.

[0060] In a possible implementation, the advertising indicator report includes multiple preset dimensions.

[0061] The indicator report generation module is used to:

[0062] Mapping the advertising cost data, the advertising revenue data, and the user behavior data to a plurality of preset dimensions respectively, and obtaining indicator calculation data corresponding to each preset dimension;

[0063] Performing indicator calculation on the indicator calculation data corresponding to each preset dimension to obtain the indicator calculation result of each preset dimension;

[0064] Based on the indicator calculation results of each preset dimension, an advertising indicator report corresponding to the initial advertising delivery data is obtained.

[0065] In a possible implementation, the target advertisement delivery data determination module is used to:

[0066] Performing an indicator analysis on the advertising indicator report to obtain an indicator analysis result;

[0067] When the indicator analysis result indicates that the initial advertisement delivery data contains preset creative materials that trigger warning conditions, the preset creative materials that trigger warning conditions are removed from the initial advertisement delivery data to obtain the target advertisement delivery data.

[0068] In a possible implementation, the device further includes a warning module, and after obtaining the advertisement indicator report corresponding to the initial advertisement delivery data, the warning module is used to:

[0069] Perform an indicator analysis on the indicator calculation result of each preset dimension of the advertising indicator report to obtain the indicator analysis result:

[0070] When the indicator analysis result indicates that the indicator calculation result meets the preset warning condition, a warning message is sent to the advertising delivery specialist.

[0071] In a possible implementation, the device further includes an updating module, and after re-delivering advertisements based on the target advertisement delivery data, the updating module is configured to:

[0072] The target advertising delivery data is used again as the initial advertising delivery data, and the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are repeatedly obtained until the step of re-delivering advertising based on the target advertising delivery data is completed, so as to update the advertising delivery strategy in real time.

[0073] On the other hand, an electronic device is provided, including a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement any of the above-mentioned data-driven advertising delivery methods.

[0074] On the other hand, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement a data-driven advertising delivery method as described in any of the above aspects.

[0075] On the other hand, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes any of the above data-driven advertising delivery methods.

[0076] The embodiment of the present application generates initial advertising delivery data by responding to an advertising exposure delivery instruction; the initial advertising delivery data includes initial advertising creative materials, and the initial advertising creative materials are at least one of multiple preset creative materials in a creative material library; the initial advertising creative materials are delivered to the advertising channel platform corresponding to the advertising exposure delivery instruction; after the initial advertising creative materials are delivered, the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are obtained; based on the advertising cost data, the advertising revenue data and the user behavior data, a multi-dimensional indicator analysis is performed to obtain an advertising indicator report corresponding to the initial advertising delivery data; the initial advertising delivery data is optimized according to the advertising indicator report to obtain target advertising delivery data; and advertising is re-delivered based on the target advertising delivery data. The indicator data of the delivery behavior is obtained through the feedback data after the delivery behavior, and the correction of the subsequent delivery behavior is driven based on the indicator data, thereby improving the positive driving force of the advertising delivery behavior during the advertising delivery process, solving the problem of how to improve the accuracy of the advertising delivery materials in the advertising delivery, and also improving the yield of the advertising delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0078] Figure 1 This is a flow chart of a data-driven advertising delivery method provided in an embodiment of the present application:

[0079] Figure 2 It is a flowchart of a data-driven advertising delivery method provided in an embodiment of the present application;

[0080] Figure 3 It is a flow chart of a method for generating initial advertisement delivery data based on a data-driven advertisement delivery method provided in an embodiment of the present application;

[0081] Figure 4It is a flowchart of a method for constructing a creative material library based on a data-driven advertising delivery method provided in an embodiment of the present application;

[0082] Figure 5 It is a flowchart of a method for determining an advertising indicator report based on a data-driven advertising delivery method provided in an embodiment of the present application;

[0083] Figure 6 It is a structural block diagram of a data-driven advertising delivery device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0084] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0085] In the current advertising market, the battle for the effectiveness of information flow advertising is fierce. On the one hand, the growth trend of Internet information flow advertising and the increasingly complex marketing environment have brought about a surge in learning costs, decision-making difficulties, and performance pressure; on the other hand, a large number of homogeneous materials and plans are piled up, and the effectiveness of advertising volume even depends on the advertiser's "good luck" and "involution". A healthier and more sustainable performance marketing growth has become a common demand of many advertisers.

[0086] At present, for the automated management of creatives, such as uploading videos or background images, delivery specialists usually need to log in to the advertising platform to upload them individually and in a scattered manner. They are also unable to manage creatives in a targeted and homogeneous manner. Single operations are time-consuming and there is no summary page to view. Although the indicators after the creatives are exposed are intuitive, it is impossible to manage the materials in a knowledge base-like manner. Through this solution, delivery specialists can place materials in batches on a designated network disk every day. The location and naming of the materials are in accordance with the agreed specifications. The materials are scanned and uploaded to the OSS (Operation Support Systems) at a regular and quantitative manner. At the same time, the uploaded materials are tagged, combined with creative indicators, and scored using a recommendation algorithm to select high-quality and high-volume materials to drive existing delivery actions and recommend high-quality materials for subsequent delivery.

[0087] The embodiment of the present application provides a data-driven advertising delivery method to improve the problems in the existing conventional advertising delivery process, such as slow and unstable data collection, inability of the collected data to positively drive advertising delivery, and slow efficiency of creative creation by delivery personnel. Figure 1 The data-driven advertising delivery method includes steps S101 to S1011.

[0088] In step S101, in response to an advertisement exposure delivery instruction, initial advertisement delivery data is generated; the initial advertisement delivery data includes initial advertisement creative material, and the initial advertisement creative material is at least one of a plurality of preset creative materials in a creative material library.

[0089] In a possible implementation, the advertisement exposure delivery instruction represents an advertisement delivery behavior issued by a party demanding advertisement delivery. The party demanding advertisement delivery may be an advertisement delivery specialist.

[0090] In a possible implementation, an advertising specialist issues the advertising exposure and delivery instructions through a self-developed delivery platform according to an advertising delivery plan.

[0091] In one possible implementation, Figure 2 As shown, advertising specialists monitor the market and build plans through the self-developed advertising platform, that is, they specify advertising delivery plans through the self-developed advertising platform.

[0092] In a possible implementation, the advertisement exposure delivery instruction includes delivery platform information, the delivery platform information represents an advertisement channel platform corresponding to the advertisement exposure delivery instruction, and the advertisement channel platform is at least one of a plurality of preset advertisement platforms.

[0093] The generating of initial advertisement delivery data in response to the advertisement exposure delivery instruction includes:

[0094] According to the advertisement exposure delivery instruction, obtaining preset creative materials corresponding to the advertisement exposure delivery instruction from the creative material library;

[0095] Based on the delivery platform information and the preset creative material, generating advertisement delivery data corresponding to the advertisement channel platform;

[0096] The advertisement delivery data corresponding to the advertisement channel platform is determined as the initial advertisement delivery data.

[0097] In one possible implementation, Figure 3 As shown, the method for generating initial advertisement delivery data includes steps S301 to S305.

[0098] In step S301, according to the advertisement exposure delivery instruction, a preset creative material corresponding to the advertisement exposure delivery instruction is obtained from the creative material library.

[0099] In a possible implementation, the preset creative material includes an advertising creative, and the preset creative material may be at least one of a picture, a video, music, and a text.

[0100] In a possible implementation, the creative material library is a pre-built material library, and the delivery specialist can perform management operations such as adding and deleting the creative material library.

[0101] In step S303, based on the delivery platform information and the preset creative material, the advertisement delivery data corresponding to the advertisement channel platform is generated.

[0102] In a possible implementation, the advertising delivery data includes delivery accounts, advertisements, projects, and creatives that can be directly used on multiple preset advertising channel platforms. The capabilities of the multiple advertising channel platforms include ByteDance, Qutoutiao, Tencent Advertising, Huawei Alliance, etc.

[0103] In a possible implementation, the self-developed delivery platform has been connected to multiple advertising channel platforms, and the initial advertising delivery data can be directly sent to the corresponding advertising channel platform.

[0104] In step S305, the advertisement delivery data corresponding to the advertisement channel platform is determined as the initial advertisement delivery data.

[0105] In a possible implementation, the advertisement delivery data of each advertisement channel platform is generated according to the platform rules of each advertisement channel platform and the preset creative material.

[0106] In this implementation, based on the delivery platform information and the preset creative material, the advertisement delivery data corresponding to the advertisement channel platform is generated, thereby improving the convenience and efficiency of advertisement delivery.

[0107] In a possible implementation, the method for constructing the creative material library includes:

[0108] Upload multiple pre-made creative files to the material management platform;

[0109] Labeling each creative file based on the attribute information of each creative file to obtain a creative label for each creative file; the attribute information includes a preset advertising platform for each creative file;

[0110] Recording the creative tag of each creative file based on the material management platform, and storing each creative file based on the material management platform to obtain preset creative materials corresponding to the creative tag of each creative file;

[0111] The creative material library is constructed based on the preset creative materials corresponding to the creative tags of each creative file.

[0112] In one possible implementation, Figure 4 As shown, the method for constructing the creative material library includes steps S401 to S407.

[0113] In step S401, a plurality of pre-made creative files are uploaded to a material management platform.

[0114] In step S403, label processing is performed on each creative file based on the attribute information of each creative file to obtain a creative label of each creative file; the attribute information includes a preset advertising platform of each creative file.

[0115] In step S405, the creative tag of each creative file is recorded based on the material management platform, and each creative file is stored based on the material management platform to obtain preset creative materials corresponding to the creative tag of each creative file.

[0116] In step S407, the creative material library is constructed based on the preset creative materials corresponding to the creative tags of each creative file.

[0117] In one possible implementation, the advertising specialist can place the prepared creative files in a designated directory on the local computer, where the designated directory is a directory shared by all advertising specialists. The folder name must be consistent with the directory in the material management library in the self-developed advertising platform, and the file name must follow the preset naming format, such as the format of "distribution channel-date splicing-chemist name", to facilitate subsequent platform statistics.

[0118] In a possible implementation, the creative file may be in the form of pictures, videos, music, text, etc.

[0119] In this implementation, by building a creative material library to manage and share materials, projects, creativity, and advertisements for various advertising platforms can be created in batches, thereby improving the efficiency of advertising specialists and saving labor costs.

[0120] In step S103, the initial advertising creative material is delivered to the advertising channel platform corresponding to the advertising exposure delivery instruction.

[0121] In a possible implementation, the advertisement exposure delivery instruction includes platform information of the advertisement channel platform specified for this delivery.

[0122] In one possible implementation, Figure 2 As shown, the initial advertising creative materials are uploaded regularly and quantitatively through the self-developed delivery platform, and the initial advertising creative materials are batch-synchronized and assigned to the advertising channel platform corresponding to the advertising exposure delivery instruction. Specifically, the platform information of the initial advertising creative materials matches the platform information of the advertising channel platform.

[0123] In a possible implementation, the review status and usage association count of the material on each advertising channel platform are automatically synchronized.

[0124] In one possible implementation, Figure 2 As shown, materials can be managed through the self-developed delivery platform, including material tag management, batch management of materials, etc.

[0125] In step S105, after the initial advertising creative material is delivered, the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are obtained.

[0126] In a possible implementation, after the initial advertising creative material is delivered, the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are obtained, including:

[0127] At a preset delivery time after the initial advertising creative material is delivered, obtaining cost data of the delivery behavior on the advertising channel platform as the advertising cost data;

[0128] And obtain the revenue data of the delivery behavior on the advertising channel platform as the advertising revenue data:

[0129] Based on the tracking technology, the user tracking data of the preset delivery time is obtained from the advertising channel platform as the user behavior data.

[0130] In one possible implementation, Figure 2 As shown in the figure, after the advertisement is exposed and the user pulls up to enter the application, all user behavior meta-events are reported at this time. In a near real-time manner, the data reporting interface is called every time the user in the application (client) triggers it. The interface is configured with multiple domain names to load distribute traffic. After the request enters nginx, it is written into the access log. Specifically, nginx is a lightweight web server / reverse proxy server and email (IMAP / POP3) proxy server, and access is a database management system that combines the graphical user interface of the database engine with software development tools.

[0131] In one possible implementation, Figure 2 As shown in the figure, all user behavior meta-events are the user behavior data, that is, the user's behavior in the application. Specifically, who did what, when, where, in what way, and the user behavior abstract meta-events to create an event analysis model for analyzing user behavior on the application. Metadata includes startup, activity page visit, gold coin unlocking, triggering recharge retention, payment order, etc., which are persisted to the storage layer in a structured form.

[0132] In one possible implementation, Figure 2 As shown, the material events of each application are configured through the self-developed delivery platform, including the number of material purchase exposures, purchase clicks, material quantity, consumption amount, etc., and stored in the storage layer in a structured form.

[0133] In one possible implementation, Figure 2 As shown in the figure, FileBeat collects nginx log data in near real time and writes it to Kafka. To prevent a single application behavior log from being too large, physical isolation is achieved by dividing the topic.

[0134] In one possible implementation, FileBeat is a lightweight data collector with low resource consumption and efficient performance, suitable for deployment and operation in various environments; nginx has the function of output log configuration and viewing; Kafka is an open source stream processing platform developed by the Apache Software Foundation, written in Scala and Java, and is a high-throughput distributed publish-subscribe messaging system that can process all action stream data of consumers on the website.

[0135] In one possible implementation, in Kafka, topic is a logical classification of messages, and each topic represents a type of message stream. The producer publishes messages to a specified topic, and consumers can subscribe to one or more topics to receive messages. Topic is used to identify and distinguish different types of messages12. Partition is the physical division of topic, and each topic can be divided into one or more partitions. Each partition is an ordered message queue, and messages are stored in the order they are written, and modification or deletion is not allowed. The partition mechanism enables Kafka to process large amounts of data and support horizontal expansion. By dividing the topic into multiple partitions, parallel processing of messages can be achieved, improving the throughput and scalability of the system.

[0136] In one possible implementation, Figure 2 As shown, combined with Kafka materialized views and multi-partition consumption, the data is written to ClickHouse / SelectDB, the storage layer on the data warehouse side.

[0137] In one possible implementation, Kafka materialized views are a mechanism that can transform and store data in Kafka into another system, such as another Kafka topic or a database. This mechanism can be used for real-time or batch data processing and can simplify the data processing process.

[0138] In one possible implementation, ClickHouse and SelectDB are both high-performance data warehouse systems designed to handle fast query and analysis of large-scale data sets. ClickHouse is well-known for its efficient columnar storage and distributed computing architecture, while SelectDB further develops on this basis, integrating the features of cloud native, providing higher performance and better user experience.

[0139] In one possible implementation, Figure 2 As shown in the figure, the self-developed third-party platform regularly pulls data from each advertising platform, including the cost and revenue data corresponding to the account, and combines the reported behavioral original events to split the cost and revenue into the finest granularity (plan, channel, link, manufacturer, application, etc.), and then writes the data into the data warehouse side storage layer ClickHouse / SelectDB.

[0140] In a possible implementation, the cost data corresponding to the account is the advertising cost data, and the revenue data corresponding to the account is the advertising revenue data.

[0141] In this implementation, after the initial advertising creative material is released, the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are obtained, so as to facilitate the subsequent generation of indicator reports based on the above data, thereby improving the calculation efficiency.

[0142] In step S107, a multi-dimensional indicator analysis is performed based on the advertising cost data, the advertising revenue data and the user behavior data to obtain an advertising indicator report corresponding to the initial advertising delivery data.

[0143] In a possible implementation, the advertising indicator report includes multiple preset dimensions.

[0144] The multi-dimensional indicator analysis is performed based on the advertising cost data, the advertising revenue data and the user behavior data to obtain an advertising indicator report corresponding to the initial advertising delivery data, including:

[0145] Mapping the advertising cost data, the advertising revenue data, and the user behavior data to a plurality of preset dimensions respectively, and obtaining indicator calculation data corresponding to each preset dimension;

[0146] Performing indicator calculation on the indicator calculation data corresponding to each preset dimension to obtain the indicator calculation result of each preset dimension;

[0147] Based on the indicator calculation results of each preset dimension, an advertising indicator report corresponding to the initial advertising delivery data is obtained.

[0148] In one possible implementation, Figure 5As shown, the method for determining the advertising indicator report includes steps S501 to S505.

[0149] In step S501, the advertising cost data, the advertising revenue data and the user behavior data are respectively mapped to a plurality of preset dimensions to obtain indicator calculation data corresponding to each preset dimension.

[0150] In step S503, the indicator calculation is performed on the indicator calculation data corresponding to each preset dimension to obtain the indicator calculation result of each preset dimension.

[0151] In step S505, based on the indicator calculation results of each preset dimension, an advertising indicator report corresponding to the initial advertising delivery data is obtained.

[0152] In one possible implementation, the multiple preset dimensions include ad space, controller, channel, material, manufacturer, application, and other dimensions.

[0153] In a possible implementation, the advertising cost data, the advertising revenue data, and the user behavior data are split into various dimensions and filled with data including dimensions such as ad space, controller, channel, material, manufacturer, and application.

[0154] In a possible implementation, the indicators are calculated based on the data split into various dimensions to obtain an advertising indicator report corresponding to the initial advertising data. Specifically, the indicators of the advertising indicator report include calculating ROI (return on investment), billing token ROI, time-sharing billing ROI, estimated ecpm (effective cost per mille), estimated quality score, purchase click-through rate, average conversion cost, etc. Specifically, ecpm refers to the advertising revenue that can be obtained for every thousand impressions, and the display unit can be a web page, an advertising unit, or even a single advertisement.

[0155] In a possible implementation, the advertising indicator report represents information such as channel analysis, plan analysis, data trends, and user behavior.

[0156] In a possible implementation, the advertising index report includes a cost & revenue index BI report and a material index report, each representing an index analysis of different dimensions.

[0157] In this implementation, the cost, revenue data and user behavior data of each advertising platform are pulled, and the above data are split into various dimensions to form a multi-dimensional indicator report, so as to drive corrective decisions on advertising delivery, improve the accuracy of advertising delivery, and thus increase advertising revenue.

[0158] In a possible implementation, after obtaining the advertisement indicator report corresponding to the initial advertisement delivery data, the method further includes:

[0159] Perform an indicator analysis on the indicator calculation result of each preset dimension of the advertising indicator report to obtain the indicator analysis result:

[0160] When the indicator analysis result indicates that the indicator calculation result meets the preset warning condition, a warning message is sent to the advertising delivery specialist.

[0161] In one possible implementation, Figure 2 As shown, an indicator report and an indicator warning task of the creative material dimension are constructed. The constructed creative material is the initial advertising creative material included in the initial advertising delivery data. The indicator report of the creative material dimension includes the number of displays, clicks, activations, effective conversions, average clicks, etc. corresponding to each material.

[0162] In one possible implementation, Figure 2 As shown in the figure, the indicator warning task is to determine whether the preset warning conditions are met based on the indicator analysis results. If the preset warning conditions are met, a warning message is sent to the advertising specialist.

[0163] In a possible implementation, the advertising specialist checks the creative material indicator page to eliminate or reduce the use of unqualified creative materials.

[0164] In a possible implementation, homogeneity analysis is performed based on the advertising indicator report, and high-quality creatives are recommended according to the creative indicator ranking to drive and correct the delivery action. Specifically, the delivery resources of creative materials with a return on income exceeding a preset first revenue threshold are increased, and the delivery resources of creative materials with a return on income below a preset second revenue threshold are reduced, wherein the preset first revenue threshold is greater than the preset second revenue threshold.

[0165] In this implementation, the light indicator report is analyzed based on preset thresholds or trigger conditions, and advertising delivery data with good delivery feedback effects are screened out based on the analysis results to increase delivery probability and delivery opportunities of advertising delivery data with good delivery feedback effects, thereby improving the effectiveness of advertising.

[0166] In step S109, the initial advertisement delivery data is optimized according to the advertisement index report to obtain target advertisement delivery data.

[0167] In a possible implementation, the optimizing the initial advertisement delivery data according to the advertisement indicator report to obtain target advertisement delivery data includes:

[0168] Performing an indicator analysis on the advertising indicator report to obtain an indicator analysis result;

[0169] When the indicator analysis result indicates that the initial advertisement delivery data contains preset creative materials that trigger warning conditions, the preset creative materials that trigger warning conditions are removed from the initial advertisement delivery data to obtain the target advertisement delivery data.

[0170] In a possible implementation, each indicator parameter of the advertising indicator report is set with a preset indicator threshold, each indicator parameter is compared with the preset indicator threshold, and whether the current indicator parameter meets the triggering warning condition is determined based on the comparison result.

[0171] In a possible implementation, when there are preset creative materials that trigger warning conditions in the initial advertising delivery data, an advertising delivery specialist is warned so that the advertising delivery specialist removes the preset creative materials that trigger the warning conditions from the initial advertising delivery data.

[0172] In one possible implementation, the data center provides the ability to build early warning tasks based on various indicators, and to send phone and DingTalk message alert notifications when there are abnormal indicators or abnormal trends. Advertising specialists can intuitively view indicator reports and receive timely notifications when there are abnormal situations. Advertising actions can be driven / corrected through report indicator data.

[0173] In this implementation, the initial advertising delivery data is optimized according to the advertising indicator report to obtain target advertising delivery data, which is determined according to the advertising indicator report, and can also respond in a timely manner to the advertising delivery specialist's adjustment of the delivery behavior.

[0174] In step S1011, advertisement delivery is performed again based on the target advertisement delivery data.

[0175] In a possible implementation, after re-delivering advertisements based on the target advertisement delivery data, the method further includes:

[0176] The target advertising delivery data is used again as the initial advertising delivery data, and the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are repeatedly obtained until the step of re-delivering advertising based on the target advertising delivery data is completed, so as to update the advertising delivery strategy in real time.

[0177] In a possible implementation, the advertising cost data, the advertising revenue data, and the user behavior data of each advertising channel platform are periodically pulled, split into various dimensions, and an indicator report is formed to drive real-time delivery correction decisions.

[0178] In this implementation, based on the timed pulling of the advertising cost data, the advertising revenue data and the user behavior data on each advertising channel platform, the advertising delivery strategy is modified to improve the accuracy of advertising delivery, thereby improving the long-term return on advertising delivery.

[0179] Figure 5 The structure diagram of a data-driven advertising delivery device 500 provided in an embodiment of the present application is shown. The device has the function of implementing the data-driven advertising delivery method in the above method embodiment. The function can be implemented by hardware or by hardware executing corresponding software. Figure 5 As shown, the device may include:

[0180] The advertisement delivery data generating module 501 is used to generate initial advertisement delivery data in response to the advertisement exposure delivery instruction; the initial advertisement delivery data includes initial advertisement creative material, and the initial advertisement creative material is at least one of a plurality of preset creative materials in the creative material library;

[0181] Advertisement delivery module 502, used to deliver the initial advertisement creative material to the advertisement channel platform corresponding to the advertisement exposure delivery instruction;

[0182] The indicator data acquisition module 503 is used to obtain the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform after the initial advertising creative material is released;

[0183] An indicator report generation module 504 is used to perform multi-dimensional indicator analysis based on the advertising cost data, the advertising revenue data and the user behavior data to obtain an advertising indicator report corresponding to the initial advertising delivery data;

[0184] The target advertisement delivery data determination module 505 is used to optimize the initial advertisement delivery data according to the advertisement index report to obtain the target advertisement delivery data;

[0185] The advertisement delivery strategy updating module 506 is used to re-deliver advertisements based on the target advertisement delivery data.

[0186] In a possible implementation, the advertisement exposure delivery instruction includes delivery platform information, the delivery platform information represents an advertisement channel platform corresponding to the advertisement exposure delivery instruction, and the advertisement channel platform is at least one of a plurality of preset advertisement platforms.

[0187] The advertisement delivery data generating module 501 is used to:

[0188] According to the advertisement exposure delivery instruction, obtaining preset creative materials corresponding to the advertisement exposure delivery instruction from the creative material library;

[0189] Based on the delivery platform information and the preset creative material, generating advertisement delivery data corresponding to the advertisement channel platform;

[0190] The advertisement delivery data corresponding to the advertisement channel platform is determined as the initial advertisement delivery data.

[0191] In a possible implementation, the device further includes a material library construction module 507, and the material library construction module 507 is used to:

[0192] Upload multiple pre-made creative files to the material management platform;

[0193] Labeling each creative file based on the attribute information of each creative file to obtain a creative label for each creative file; the attribute information includes a preset advertising platform for each creative file;

[0194] Recording the creative tag of each creative file based on the material management platform, and storing each creative file based on the material management platform to obtain preset creative materials corresponding to the creative tag of each creative file;

[0195] The creative material library is constructed based on the preset creative materials corresponding to the creative tags of each creative file.

[0196] In a possible implementation, the indicator data acquisition module 503 is used to:

[0197] At a preset delivery time after the initial advertising creative material is delivered, obtaining cost data of the delivery behavior on the advertising channel platform as the advertising cost data;

[0198] and obtaining the revenue data of the delivery behavior on the advertising channel platform as the advertising revenue data;

[0199] Based on the tracking technology, the user tracking data of the preset delivery time is obtained from the advertising channel platform as the user behavior data.

[0200] In a possible implementation, the advertising indicator report includes multiple preset dimensions.

[0201] The indicator report generation module 504 is used to:

[0202] Mapping the advertising cost data, the advertising revenue data, and the user behavior data to a plurality of preset dimensions respectively, and obtaining indicator calculation data corresponding to each preset dimension;

[0203] Performing indicator calculation on the indicator calculation data corresponding to each preset dimension to obtain the indicator calculation result of each preset dimension;

[0204] Based on the indicator calculation results of each preset dimension, an advertising indicator report corresponding to the initial advertising delivery data is obtained.

[0205] In a possible implementation, the target advertisement delivery data determination module 505 is used to:

[0206] Performing an indicator analysis on the advertising indicator report to obtain an indicator analysis result;

[0207] When the indicator analysis result indicates that the initial advertisement delivery data contains preset creative materials that trigger warning conditions, the preset creative materials that trigger warning conditions are removed from the initial advertisement delivery data to obtain the target advertisement delivery data.

[0208] In a possible implementation, the device further includes a warning module 508. After obtaining the advertisement indicator report corresponding to the initial advertisement delivery data, the warning module 508 is configured to:

[0209] Perform an indicator analysis on the indicator calculation result of each preset dimension of the advertising indicator report to obtain the indicator analysis result:

[0210] When the indicator analysis result indicates that the indicator calculation result meets the preset warning condition, a warning message is sent to the advertising delivery specialist.

[0211] In a possible implementation, the device further includes an updating module 509. After re-delivering advertisements based on the target advertisement delivery data, the updating module 509 is configured to:

[0212] The target advertising delivery data is used again as the initial advertising delivery data, and the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are repeatedly obtained until the step of re-delivering advertising based on the target advertising delivery data is completed, so as to update the advertising delivery strategy in real time.

[0213] It should be noted that the device provided in the above embodiment, when implementing its functions, is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0214] An embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement any data-driven advertising delivery method provided in the above method embodiments.

[0215] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory can also include a memory controller to provide the processor with access to the memory.

[0216] An embodiment of the present application also provides a computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a data-driven advertising delivery method. The at least one instruction or the at least one program is loaded and executed by the processor to implement any one of the data-driven advertising delivery methods provided in the above method embodiments.

[0217] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0218] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0219] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0220] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0221] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A data-driven advertising method, characterized in that: The method comprises: In response to the advertisement exposure delivery instruction, initial advertisement delivery data is generated; the initial advertisement delivery data includes initial advertisement creative material, and the initial advertisement creative material is at least one of a plurality of preset creative materials in a creative material library; Placing the initial advertising creative material on the advertising channel platform corresponding to the advertising exposure delivery instruction; After the initial advertising creative material is released, obtaining advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform; Perform multi-dimensional indicator analysis based on the advertising cost data, the advertising revenue data, and the user behavior data to obtain an advertising indicator report corresponding to the initial advertising delivery data; Optimizing the initial advertising delivery data according to the advertising indicator report to obtain target advertising delivery data; Re-deliver the advertisement based on the target advertisement delivery data.

2. The data-driven advertising method according to claim 1, characterized in that: The advertisement exposure delivery instruction includes delivery platform information, wherein the delivery platform information represents an advertisement channel platform corresponding to the advertisement exposure delivery instruction, and the advertisement channel platform is at least one of a plurality of preset advertisement platforms. The generating of initial advertisement delivery data in response to the advertisement exposure delivery instruction includes: According to the advertisement exposure delivery instruction, obtaining preset creative materials corresponding to the advertisement exposure delivery instruction from the creative material library; Based on the delivery platform information and the preset creative material, generating advertisement delivery data corresponding to the advertisement channel platform; The advertisement delivery data corresponding to the advertisement channel platform is determined as the initial advertisement delivery data.

3. The data-driven advertising method according to claim 2, characterized in that: The method for constructing the creative material library includes: Upload multiple pre-made creative files to the material management platform; Labeling each creative file based on the attribute information of each creative file to obtain a creative label for each creative file; the attribute information includes a preset advertising platform for each creative file; Recording the creative tag of each creative file based on the material management platform, and storing each creative file based on the material management platform to obtain preset creative materials corresponding to the creative tag of each creative file; The creative material library is constructed based on the preset creative materials corresponding to the creative tags of each creative file.

4. The data-driven advertising method according to claim 1, characterized in that: After the initial advertising creative material is released, the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are obtained, including: At a preset delivery time after the initial advertising creative material is delivered, obtaining cost data of the delivery behavior on the advertising channel platform as the advertising cost data; and obtaining the revenue data of the delivery behavior on the advertising channel platform as the advertising revenue data; Based on the tracking technology, the user tracking data of the preset delivery time is obtained from the advertising channel platform as the user behavior data.

5. The data-driven advertising method according to claim 1, characterized in that: The advertising indicator report includes multiple preset dimensions. The multi-dimensional indicator analysis is performed based on the advertising cost data, the advertising revenue data and the user behavior data to obtain an advertising indicator report corresponding to the initial advertising delivery data, including: Mapping the advertising cost data, the advertising revenue data, and the user behavior data to a plurality of preset dimensions respectively, and obtaining indicator calculation data corresponding to each preset dimension; Performing indicator calculation on the indicator calculation data corresponding to each preset dimension to obtain the indicator calculation result of each preset dimension; Based on the indicator calculation results of each preset dimension, an advertising indicator report corresponding to the initial advertising delivery data is obtained.

6. The data-driven advertising method according to claim 1, characterized in that: The step of optimizing the initial advertisement delivery data according to the advertisement indicator report to obtain target advertisement delivery data includes: Performing an indicator analysis on the advertising indicator report to obtain an indicator analysis result; When the indicator analysis result indicates that the initial advertisement delivery data contains preset creative materials that trigger warning conditions, the preset creative materials that trigger warning conditions are removed from the initial advertisement delivery data to obtain the target advertisement delivery data.

7. The data-driven advertising method according to claim 5, characterized in that: After obtaining the advertisement indicator report corresponding to the initial advertisement delivery data, the method further includes: Perform an indicator analysis on the indicator calculation result of each preset dimension of the advertising indicator report to obtain the indicator analysis result: When the indicator analysis result indicates that the indicator calculation result meets the preset warning condition, a warning message is sent to the advertising delivery specialist.

8. The data-driven advertising method according to claim 1, characterized in that: After re-delivering advertisements based on the target advertisement delivery data, the method further includes: The target advertising delivery data is used again as the initial advertising delivery data, and the advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform are repeatedly obtained until the step of re-delivering advertising based on the target advertising delivery data is completed, so as to update the advertising delivery strategy in real time.

9. A data-driven advertising device, characterized in that: The device comprises: An advertisement delivery data generation module, configured to generate initial advertisement delivery data in response to an advertisement exposure delivery instruction; the initial advertisement delivery data includes initial advertisement creative materials, and the initial advertisement creative materials are at least one of a plurality of preset creative materials in a creative material library; An advertisement delivery module, used for delivering the initial advertisement creative material to the advertisement channel platform corresponding to the advertisement exposure delivery instruction; An indicator data acquisition module, used to acquire advertising cost data, advertising revenue data and user behavior data corresponding to the advertising channel platform after the initial advertising creative material is released; An indicator report generation module, used to perform multi-dimensional indicator analysis based on the advertising cost data, the advertising revenue data and the user behavior data to obtain an advertising indicator report corresponding to the initial advertising delivery data; A target advertising delivery data determination module is used to optimize the initial advertising delivery data according to the advertising indicator report to obtain target advertising delivery data; The advertisement delivery strategy updating module is used to re-deliver advertisements based on the target advertisement delivery data.

10. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the data-driven advertising delivery method as described in any one of claims 1 to 8.

Images