Advertisement bidding strategy configuration method and device, electronic equipment and storage medium

By configuring policy groups and sub-strategy groups for each business scenario in the advertising bid strategy platform and clarifying priority, the frequent and complexity of bid strategy iteration is solved, the system maintenance and stability is improved, and efficient advertising is achieved Delivery.

CN119090567APending Publication Date: 2024-12-06BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411212379.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

During the advertising performance process, frequent iteration of bidding strategies leads to unclear policy priorities, too many complex policy branches, making it difficult for the system to maintain.

Method used

The policy group is configured for each business scenario in the bid strategy platform. The sub-strategy groups are sorted according to the number of traffic hits on the ad publishing point, and the policies are prioritized according to the bid method. They adopt the design of single-step, multi-step and global policy groups to clarify Priority and policy paths avoid duplicate wheels and reduce system complexity.

Benefits of technology

It improves the maintainability and stability of the system, avoids the situation of repeated wheel creation, and reduces the system complexity through clear priorities and clear strategy paths, and improves the configuration efficiency and effectiveness of advertising bidding strategies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090567A_ABST
    Figure CN119090567A_ABST
Patent Text Reader

Abstract

The invention provides an advertisement bidding strategy configuration method and device, electronic equipment and a storage medium, and the method comprises the steps: configuring a strategy group in a bidding strategy platform for each business scene, sorting a plurality of sub-strategy groups in the strategy group according to the priority of the strategy, the strategy priority is used for indicating the number of the advertisement publishing points hit by the flow; sub-policy groups are configured, and a plurality of policies in each sub-policy group are sorted according to the priority of the bidding mode; strategies are configured, and a strategy operator of each strategy is composed of a specified condition, an ECPM factor and an ECPM formula. According to the invention, the system complexity is reduced, and the maintainability and stability of a bidding strategy platform are provided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of platform configuration, and in particular to an advertisement bidding strategy configuration method, device, electronic device and storage medium. Background Art

[0002] In the process of performance advertising, the ECPM (effective cost per mille, advertising revenue obtained for every thousand impressions) calculation strategy will directly affect the advertising results. In different delivery scenarios, personalized strategies need to be designed based on advertising attributes and target groups. In the early stages of system development, in order to quickly trial and error, bidding strategies were frequently iterated, and the wheel was reinvented. Over time, the priorities between bidding strategies were unclear, and there were too many complex strategy branches, making the system difficult to maintain. Summary of the invention

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides an advertising bidding strategy configuration method, device, electronic device and storage medium.

[0004] In a first aspect, the present application provides an advertisement bidding strategy configuration method, the method comprising:

[0005] A strategy group is configured in the bidding strategy platform for each business scenario, wherein multiple sub-strategy groups in the strategy group are sorted according to strategy priorities, and the strategy priorities are used to indicate the number of traffic hits on the advertising publishing point;

[0006] Configure sub-strategy groups, where multiple strategies in each sub-strategy group are sorted according to bidding method priority;

[0007] Configure the strategy, where the strategy operator of each strategy consists of the specified condition, ECPM factor and ECPM formula.

[0008] Optionally, configure a strategy group in the bidding strategy platform for each business scenario including:

[0009] If the policy group is determined to be a single-step policy group according to the business scenario, the plurality of sub-policy groups are sorted in descending order of policy priority;

[0010] The strategies are sorted in descending order of priority, and the bid calculation is terminated after any sub-strategy group is successfully executed.

[0011] Optionally, configure the sub-policy group to include:

[0012] If the sub-strategy group is in a single-step strategy group, then the sub-strategy group is a single-step sub-strategy group;

[0013] Sorting the multiple strategies in the single-step sub-strategy group in descending order of bidding method priority;

[0014] The bidding methods are sorted in descending order of priority, and the bidding calculation is terminated after any bidding method is successfully executed.

[0015] Optionally, configuring multiple strategy groups in the bidding strategy platform includes:

[0016] If the policy group is determined to be a multi-step policy group according to the business scenario, the multiple sub-policy groups are sorted in order from low to high policy priority;

[0017] The strategy priorities are sorted from low to high, and the bid calculation is terminated after all sub-strategy groups are executed.

[0018] Optionally, configure the sub-policy group to include:

[0019] If the sub-strategy group is in a multi-step strategy group, then the sub-strategy group is a multi-step sub-strategy group;

[0020] Sorting the multiple strategies in the multi-step sub-strategy group in order of bidding method priority from low to high;

[0021] According to the order of priority of the bidding methods from low to high, the bidding calculation of the multi-step sub-strategy group is ended after all strategies are executed.

[0022] Optionally, the configuration policy includes:

[0023] Determine whether the traffic attribute satisfies the bidding method according to a Boolean expression, wherein each Boolean expression is used to represent a bidding method;

[0024] If the bidding method is met, the bidding result is calculated according to the ECPM factor and the ECPM formula.

[0025] Optionally, the method further comprises:

[0026] Configure a global policy group, wherein the global policy is used to execute a preset bidding method when the traffic attribute fails to match all Boolean expressions, and set the policy to be sorted in descending order of bidding method priority and the sub-policy groups to be sorted in descending order of policy priority.

[0027] In a second aspect, the present application provides an advertisement bidding strategy configuration device, the device comprising:

[0028] A first configuration module is used to configure a strategy group in the bidding strategy platform for each business scenario, wherein multiple sub-strategy groups in the strategy group are sorted according to a strategy priority, and the strategy priority is used to indicate the number of advertisement publishing points hit by traffic;

[0029] A second configuration module is used to configure a sub-strategy group, wherein multiple strategies in each sub-strategy group are sorted according to the bidding method priority;

[0030] The third configuration module is used to configure the strategy, wherein the strategy operator of each strategy is composed of a specified condition, an ECPM factor and an ECPM formula.

[0031] In a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0032] Memory, used to store computer programs;

[0033] The processor is used to implement any of the steps of the advertising bidding strategy configuration method when executing the program stored in the memory.

[0034] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any of the steps of the advertising bidding strategy configuration method is implemented.

[0035] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0036] The method provided in the embodiment of the present application configures a policy group for each business scenario in the bidding strategy platform, so that the configured policy group can meet multiple business scenarios, and multiple sub-policy groups in the policy group are sorted according to the number of traffic hits on the advertising publishing point, and multiple policies in the sub-policy group are sorted according to the bidding method. The present application configures multiple policy groups in advance to avoid reinventing the wheel, and by setting clear priorities and clear and definite policy paths, adopts a high cohesion and low coupling approach, reduces system complexity, and provides maintainability and stability of the bidding strategy platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0039] Figure 1 A schematic diagram of the hardware environment of an advertisement bidding strategy configuration method provided in an embodiment of the present application;

[0040] Figure 2 A flowchart of an advertising bidding strategy configuration method provided in an embodiment of the present application;

[0041] Figure 3 A configuration flow chart of an advertising bidding strategy provided in an embodiment of the present application;

[0042] Figure 4 A schematic diagram of the system architecture of an advertisement bidding strategy provided in an embodiment of the present application;

[0043] Figure 5 A schematic diagram of the structure of an advertisement bidding strategy configuration device provided in an embodiment of the present application;

[0044] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are 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.

[0046] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application and have no specific meaning. Therefore, "module" and "component" can be used interchangeably.

[0047] In order to solve the problems mentioned in the background technology, according to one aspect of an embodiment of the present application, an embodiment of an advertisement bidding strategy configuration method is provided.

[0048] Optionally, in the embodiment of the present application, the above-mentioned advertising bidding strategy configuration method can be applied to: Figure 1 In the hardware environment composed of the terminal 101 and the server 103 shown in FIG. Figure 1As shown, the server 103 is connected to the terminal 101 via a network, and can be used to provide services for the terminal or a client installed on the terminal. A database 105 can be set on the server or independently of the server to provide data storage services for the server 103. The above-mentioned network includes but is not limited to: a wide area network, a metropolitan area network or a local area network, and the terminal 101 includes but is not limited to a PC, a mobile phone, a tablet computer, etc.

[0049] An advertisement bidding strategy configuration method in an embodiment of the present application may be executed by the server 103 .

[0050] An embodiment of the present application provides an advertisement bidding strategy configuration method, which can be applied to a server to configure multiple advertisement bidding strategies in a bidding strategy platform to improve system stability.

[0051] The following will describe in detail an advertising bidding strategy configuration method provided by the embodiment of the present application in combination with a specific implementation method. Figure 2 As shown, the specific steps are as follows:

[0052] Step 201: A strategy group is configured in the bidding strategy platform for each business scenario, wherein multiple sub-strategy groups in the strategy group are sorted according to strategy priority, and the strategy priority indicates the number of advertisement publishing points hit by traffic.

[0053] Step 202: configuring sub-strategy groups, wherein multiple strategies in each sub-strategy group are sorted according to bidding method priority.

[0054] Step 203: Configure the strategy, wherein the strategy operator of each strategy is composed of a specified condition, an ECPM factor and an ECPM formula.

[0055] In this application, the system configures a strategy group for each business scenario in the bidding strategy platform. Each strategy group corresponds to a routing key. After receiving the bidding request sent by the user, the system executes different strategy groups according to the traffic data, obtains the ECPM corresponding to each strategy group, and selects the strategy group with the highest ECPM in the subsequent bidding stage.

[0056] Among them, ECPM refers to the advertising revenue that can be obtained for every thousand impressions. It is an indicator for advertising publishers to evaluate the profitability of CPM-format advertising, which indicates the actual or estimated advertising revenue that can be obtained for one thousand advertising impressions. The calculation formula of ECPM is as follows: ECPM = (total revenue / total number of advertising impressions) * 1000. For example, if an advertising campaign earns 500 yuan in revenue from 100,000 advertising impressions, then the ECPM of the campaign is: ECPM = (500 / 100,000) * 1000 = 5 yuan, which means that the campaign can bring in an average of 5 yuan in revenue for every thousand impressions. Advertisers and publishers usually use ECPM as a key performance indicator to evaluate the profitability of advertising campaigns, compare different advertising networks or advertising positions, and optimize strategies to increase revenue.

[0057] The rules for configuring policy groups are as follows: the policy configuration platform configures a policy group for each business scenario, so multiple policy groups need to be configured for multiple business scenarios. Each policy group includes multiple sub-policy groups sorted according to certain rules, and each sub-policy group also includes multiple policies sorted according to certain requirements. The specific content of the policy is reflected in the policy operator, which consists of specified conditions, ECPM factors, and ECPM formulas.

[0058] The order of multiple sub-strategy groups is set according to the strategy priority, where the strategy priority indicates the number of advertising publishing points hit by traffic. Advertising publishing points refer to specific locations or media where advertisements are displayed on specific locations or media. These locations include but are not limited to websites, applications, social media platforms, outdoor billboards, etc. The more traffic data hits the advertising publishing points, the higher the strategy priority.

[0059] The order of multiple strategies is set according to the bidding method priority, where the bidding method priority includes many situations, such as the depth of the ad conversion type, the complexity of the bidding form, whether the bidding method has special marks, etc. In general, the deeper the ad conversion type, the higher the priority; the more complex the bidding form, the higher the priority; and the special marks depend on the specific scenario. In some scenarios, the bidding method with special marks has a high priority, while in some scenarios, the bidding method with special marks has a low priority.

[0060] For example, an advertiser places orders for two types of advertising conversions: payment and activation. Payment is a deeper conversion type, so this type of order has a higher priority. On the contrary, activation is a shallower conversion type, so this type of order has a lower priority.

[0061] During the policy execution process, a policy is composed of specified conditions, ECPM factors and ECPM formulas, so all three are made into operators and placed in the policy. When the operator is executed, the condition, factor and formula are all an operator node. The condition operator returns a bool result to determine whether to interrupt the task flow. Therefore, the condition operator is placed at the front and the factor operator is placed in the middle to calculate the factors required by the formula. ECPM is an infix expression and is converted into a postfix expression during execution.

[0062] In this application, by configuring a strategy group for each business scenario in the bidding strategy platform, the configured strategy group can meet multiple business scenarios. By setting multiple sub-strategy groups in the strategy group to be sorted according to the number of traffic hits on the advertising publishing point, and setting multiple strategies in the sub-strategy group to be sorted according to the bidding method, this application considers the popularity of the advertising publishing point and the feasibility of the bidding method in the configuration process of the advertising bidding strategy, and improves the comprehensiveness of the advertising bidding strategy in the configuration dimension. This application configures multiple strategy groups in advance to avoid reinventing the wheel, and by setting clear priorities and clear and definite strategy paths, it adopts a high cohesion and low coupling approach to reduce system complexity and provide maintainability and stability of the bidding strategy platform.

[0063] The following is a detailed explanation of policy groups, sub-policy groups, and policies.

[0064] For a policy group, it can be a single-step policy group, a multi-step policy group, or a global policy group. The specific division method is determined according to the business scenario.

[0065] 1. If the strategy group is a single-step strategy group, then the multiple sub-strategy groups in the single-step strategy group are sorted in descending order of strategy priority. In the process of executing the sub-strategy groups, the sub-strategy group with the highest priority is executed first. If a sub-strategy group fails to execute, the next sub-strategy group will continue to execute until a sub-strategy group is successfully executed, and then the bid calculation is terminated. The core of the single-step strategy group lies in its "one-step" execution logic, that is, to achieve the goal as much as possible in one attempt.

[0066] Specifically, when a single-step policy group is executed, if one of the sub-policy groups is executed successfully, it means that the single-step policy group is executed successfully. For example, a single-step policy group has three sub-policy groups A, B, and C, which are ranked from high to low in policy priority. If A fails to execute, B will be executed. If B succeeds, the entire policy is executed successfully. Otherwise, C will continue to execute.

[0067] Assume that a bidding strategy platform sets a single-step strategy group for setting bids for online ads. This strategy group includes the following sub-strategy groups, which are sorted from high to low in terms of strategy priority: 1. Advertising on social media platforms, popular websites, and offline billboards; 2. Advertising on social media platforms and offline billboards; 3. Advertising on social media platforms. During the execution process, the system will first try the first seed strategy group. If the strategy succeeds (for example, the bid is successfully placed and the ad space is obtained), the entire bid calculation ends; if it fails (for example, the bid is too high or the ad content does not comply with the platform policy), the second seed strategy group will be tried, and so on, until a sub-strategy group is successfully executed.

[0068] 2. If the strategy group is a multi-step strategy group, then the multiple sub-strategy groups in the multi-step strategy group are sorted in order from low to high according to the strategy priority. In the process of executing the sub-strategy groups, start from the sub-strategy group with the lowest priority and execute in sequence. After all sub-strategy groups are executed, the bid calculation ends. The multi-step strategy group emphasizes the process of gradual optimization and adjustment.

[0069] A multi-step policy group is considered to be completed only after all its sub-policy groups are executed. For example, a single-step policy group includes three sub-policy groups D, E, and F, which are sorted from low to high in terms of policy priority. When D is executed successfully, E will continue to be executed. When E is executed successfully, F will continue to be executed.

[0070] 3. The global policy group is a fallback solution. If the traffic data does not hit any route, the policy in the global policy group is executed. One or more sub-policy groups can also be set in the global policy group. When a sub-policy group is successfully executed, the bid calculation is stopped and the subsequent sub-policy groups are no longer executed. In the fallback solution, the strategies are sorted in order of bidding method priority from high to low, and the sub-policy groups are sorted in order of strategy priority from high to low. The design of the global policy group allows the system to flexibly select the most appropriate advertising delivery strategy when faced with traffic that cannot be matched by routing rules. Sorting by priority ensures that resources can be allocated to strategies that are more likely to produce positive advertising effects, thereby improving overall advertising efficiency and return on investment.

[0071] For the sub-strategy group, the sub-strategy group can be a single-step sub-strategy group, a multi-step sub-strategy group, or a global sub-strategy group, which will be explained below.

[0072] 1. The single-step sub-strategy group is located in the single-step strategy group. The multiple strategies in the single-step sub-strategy group are sorted in descending order according to the bidding method priority. The system first tries to execute the strategy with the highest bidding method priority. If the strategy is successfully executed, the bid calculation ends; if the strategy fails to be executed, the system continues to execute the next strategy with a lower priority until a strategy is successfully executed.

[0073] Each strategy is composed of specified conditions, ECPM factors, and cepm formulas. The bidding method is specifically reflected in the specified conditions. If the specified conditions are met, the subsequent ECPM formula can be directly executed, indicating that the strategy is successfully executed. If the specified conditions are not met, there is no need to calculate the subsequent ECPM formula, indicating that the strategy has failed to execute.

[0074] For example, the system sorts the strategies in the following order: 1. The user has entered the payment stage after placing an order, and the user has a high conversion rate tag; 2. The user is currently in the member activation stage; 3. The user is currently in the browsing stage, and the user has a high conversion rate tag. When the first strategy is successfully executed, the ECPM can be directly calculated, so there is no need to execute the subsequent strategies. If the previous strategies are not successfully executed, the next strategy needs to be executed.

[0075] 2. The multi-step sub-strategy group is located in the multi-step strategy group. The multiple strategies in the multi-step sub-strategy group are sorted in order from low to high according to the bidding method priority. The system starts to execute from the strategy with the lowest priority and gradually adjusts to the strategy with higher priority until all strategies are executed. At this time, the bid calculation is completed.

[0076] 3. The global sub-strategy group is located in the global strategy group. The global sub-strategy group includes a specific fallback plan. In the global sub-strategy group, the prerequisite for the strategy to take effect is that ALL_REGION takes effect, and then the corresponding bidding method is executed. As a prerequisite, ALL_REGION takes effect, which stipulates that the strategy can only be applied when all the conditions involved are activated or ready.

[0077] Exemplarily, the bidding method in the bottom-line solution is: bid = advertiser bid * estimated value. This bidding method combines the advertiser's bid and a coefficient estimated by the system. Usually, this coefficient is calculated based on past data and prediction models, and aims to optimize the ratio of advertising effect to cost. In this model, the advertiser's bid is the maximum amount the advertiser is willing to pay for a certain ad display, and the estimated value may include the expected click-through rate, conversion rate or other indicators related to advertising performance. By multiplying these two factors, the system can dynamically adjust the bid to ensure that the bidding strategy not only meets the advertiser's budget constraints, but also strives for display opportunities in a highly competitive advertising environment.

[0078] The priority and execution logic of each strategy clearly reflect the priority of the bidding method. Through this priority sorting and condition checking, the system can allocate advertising budget more effectively and improve the ECPM of advertising delivery.

[0079] The composition of the strategy includes specified conditions, ECPM factors and ECPM calculation formulas. The specified conditions are composed of a set of bool expressions. Bool is the definer of Boolean variables (logical variables). Each expression judges the specified advertisement or traffic attributes and returns true or false, such as deep or shallow bidding judgment, or whether there are certain specific tags. If true is returned, the subsequent formula calculation is executed. If false is returned, it means that the conditions are not met and there is no need to execute the subsequent formula calculation.

[0080] ECPM factors are involved in calculating ECPM parameters, which are pushed by the algorithm side or obtained by calculation on the engine side according to policy rules.

[0081] The ECPM formula is an infix expression. When the specified conditions are met, the ECPM result is calculated based on the infix expression and factors. The ECPM formula supports basic addition, subtraction, multiplication, division and other algorithms, basic trigonometric functions, logarithmic functions and exponential functions.

[0082] The policy can also include an identifier, which can be used to supplement the policy-specific attributes after the traffic hits the policy and returned to the next stage for recording in the log for data analysis.

[0083] The bidding strategy platform can also perform the following functions:

[0084] Supports query, addition, copy, modification, deletion and logging of policy groups; supports query, addition, copy, modification, deletion and logging of sub-policy groups; supports query, addition, copy, modification, deletion and logging of policies; supports query, addition, modification, deletion and logging of routes; Approval mechanism: When the operator submits an online operation, it will trigger the approval of the corresponding superior and record the approval document in the OA system; Conflict monitoring: When the operator configures the task, it will monitor conflicts based on the primary key, index and other mechanisms to prevent duplicate and redundant configuration.

[0085] This application provides a configuration flow chart of an advertising bidding strategy. Figure 3 In the policy platform, technical personnel can flexibly configure routing rules, policy group rules, sub-policy group rules and specific policies according to different business needs and market scenarios.

[0086] The system configures multiple policy groups according to specific business scenarios. Each routing key can only hit one policy group. This design ensures the specificity and accuracy of policy execution. The policy group contains multiple sub-policy groups, which are sorted according to policy priorities. For single-step policy groups, sub-policy groups are sorted from high to low according to policy priorities. This means that during the execution process, the system will try to execute the sub-policy group with the highest priority first. If the sub-policy group is executed successfully (that is, the preset conditions are met and the subsequent ECPM formula can be continued), the bid calculation is terminated; if the execution fails (that is, the preset conditions are not met and the ECPM formula does not need to be calculated), the system will try the next sub-policy group with a lower priority in order until a sub-policy group is successfully executed.

[0087] The single-step sub-strategy group also includes multiple specific strategies. These strategies are also sorted from high to low according to the priority of the bidding method. This allows the system to flexibly select the most appropriate bidding strategy in different situations, thereby optimizing the effectiveness of advertising delivery.

[0088] In a multi-step strategy group, sub-strategy groups are sorted from low to high according to strategy priority. The system starts from lower strategy priorities and gradually tries until higher strategy requirements are met. Similarly, multiple strategies in a multi-step sub-strategy group are also sorted from low to high according to the priority of the bidding method. This helps the system select the most appropriate strategy at different execution stages and gradually improve the bidding effect of the advertisement.

[0089] In addition, the system is also configured with a global policy group as a fallback solution. When the traffic does not hit any set routing key, that is, there is no routing rule that meets specific conditions, the system can execute this global policy group, which ensures that even in some abnormal or special circumstances, the system can maintain basic operations and maintain the basic effect of advertising.

[0090] The configuration interface in this application supports extension, abstracting the entire architecture from four aspects: computing logic, business scenarios, advertising attributes, and traffic attributes, and then abstracting four interfaces: routing, policy group, sub-policy group, and policy, making the entire architecture look neat and cohesive. Users can add and modify policies through the platform page to generate a policy configuration file and distribute it online. After the online service is loaded, it will execute the corresponding ECPM calculation logic according to the configuration.

[0091] In the advertising bidding strategy platform, the configuration and execution of strategies are the key links to achieve efficient advertising delivery. These strategies are organized and executed through a multi-level structure to ensure that the bid for each ad display can match the advertiser's goals and budget constraints to the greatest extent. The framework of strategy configuration consists of four parts: overall fan routing rules, strategy groups, sub-strategy groups, and strategies.

[0092] 1. Routing rules

[0093] Routing rules are a set of predefined rules based on traffic attributes, which are used to direct traffic data to a specific policy group. In an advertising system, traffic attributes may include the user's geographic location, device type, access time, etc. Each routing rule has a unique routing key, which is used to identify a specific type of traffic. A routing key can only be associated with one policy group, ensuring that traffic data can be clearly and uniquely directed to a policy group. For example, if an advertising campaign is mainly targeted at mobile device users, a routing rule can be set to count all traffic from mobile devices into a specific policy group so that targeted strategies under that policy group can be applied.

[0094] 2. Strategy Group

[0095] A policy group is a collection of sub-policy groups. Each policy group contains multiple sub-policy groups, which are executed in a certain priority order. Policy groups are divided into single-step policy groups and multi-step policy groups:

[0096] Single-step strategy group: In a single-step strategy group, sub-strategy groups are executed in order of priority from high to low. If a high-priority strategy is successfully executed (i.e., it meets certain conditions and successfully calculates the ECPM value), the bid calculation ends and subsequent lower-priority strategies are no longer executed.

[0097] Multi-step policy group: In a multi-step policy group, sub-policy groups are executed in order from low to high priority, and the system will try to execute policies one by one in order until all policies are executed.

[0098] In addition, there is a special "fallback strategy group". When the traffic data does not match any routing rules, the system will execute the strategies in this fallback strategy group. This ensures that even if there is no explicit match, the system can continue to calculate ECPM according to the fallback strategy.

[0099] 3. Sub-strategy group

[0100] A sub-strategy group is a more fine-grained form of strategy organization, which usually contains a group of functionally related bidding methods. The strategies within the sub-strategy group can schedule bidding strategies according to the needs of business scenarios. Each strategy has conditional judgments, and the associated bidding methods are executed only when the conditions are met.

[0101] Single-step strategy: In a single-step strategy, bidding methods are executed in order of priority from high to low. Once a bidding method is successfully executed, the calculation ends.

[0102] Multi-step strategy: In a multi-step strategy, bidding methods are executed in order of priority from low to high, and the system will gradually try each bidding method until all are executed.

[0103] 4. Strategy

[0104] A strategy is the basic unit that constitutes a sub-strategy group. Each strategy consists of specified conditions, ECPM factors, and ECPM calculation formulas:

[0105] Specified conditions: consist of a set of Boolean expressions, each of which judges the specified advertisement or traffic attribute and returns a true or false result. For example, the specified conditions are the conversion type of the advertisement, the ad slot of the traffic, or AB experiment, etc.

[0106] ECPM factors: Parameters involved in ECPM calculation, which can be pushed by the algorithm side or obtained by the engine side according to policy rules. For example, ECPM factors include advertiser bids, model estimates, etc.

[0107] ECPM formula: It is an infix expression. When the conditions are met, the ECPM result is calculated according to this formula and factors. It supports basic mathematical operations and advanced mathematical functions.

[0108] Through such structural design, the advertising bidding strategy platform can flexibly adapt to different market demands and advertising strategies, optimize advertising effects, and improve advertising efficiency and return on investment.

[0109] The calculation logic of ECPM involves multiple levels, including the processing of traffic data, the matching of routes, the selection and execution of policy groups, and the final determination of bids. The following is a detailed description of the calculation logic of ECPM.

[0110] When users interact with ads and generate traffic data, the system first analyzes the data to determine whether they hit a preset route. The route is a set of predefined rules used to guide traffic data to match the corresponding policy group.

[0111] If the traffic data hits a certain route, the system executes the policy group associated with the route. The policy group contains one or more sub-policy groups, and each sub-policy group contains a series of specific policies. During the execution process, the system first checks whether each policy meets specific conditions based on a Boolean variable (bool variable). For policies that meet the conditions, the system further executes the related ECPM formula, which usually combines multiple factors, such as expected click-through rate, ad quality score, competitive environment, etc., to estimate the potential revenue of each ad display. The accuracy of this formula is directly related to the revenue of advertising.

[0112] The priority of the bidding method also plays a decisive role between strategies. The system will determine the execution order based on the bidding method priority preset by different strategies. For example, a bidding method that is more complex or more likely to bring conversions may be given a higher priority. The system will calculate bids based on the strategy priority between sub-strategy groups. This means that within a strategy group, different sub-strategy groups may target different advertising scenarios or user groups. The system will select the sub-strategy group with the highest priority to start the bid calculation.

[0113] Finally, after evaluating all strategies and sub-strategy groups, the system will select the strategy with the highest ECPM as the final bidding strategy. This strategy will determine the final bid for the ad, that is, the highest price the system is willing to pay for this ad display.

[0114] If the traffic data does not hit any preset routes, the system uses a fallback solution, which is usually a default strategy used to deliver ads in the absence of a clear match. The fallback solution may be based on general data or a more conservative bidding strategy to ensure that basic ad delivery activities can be maintained even in non-ideal situations.

[0115] Through this series of sophisticated calculations and strategy selections, the system can accurately determine the optimal bid for each ad display in real time, thereby maximizing advertising effectiveness and return on investment.

[0116] The effects that can be achieved by this application include: 1. Architectural decoupling: high cohesion and low coupling, which reduces system complexity and provides maintainability and stability; 2. Improved production and research efficiency: strategic cohesion, clear structure, improved iteration efficiency, and optimized labor efficiency; 3. Revenue gain: strategies are easy to optimize, helping to increase revenue.

[0117] This application provides a schematic diagram of the system architecture of an advertising bidding strategy, such as Figure 4 As shown in the figure, the system architecture adds a bidding calculation engine framework. In the bidding stage of the advertising delivery link, the bidding calculation engine interface is called to obtain the ECPM of the advertisement. By decomposing and abstracting the bidding strategy, multiple bidding strategies are edited into DAG (Directed Acyclic Graph) according to the execution method. When the advertisement is delivered, the ECPM of the advertisement is calculated according to the graph element. Under the premise of ensuring the growth of business indicators, the bidding strategy is configured and managed through the platform to improve the efficiency of human-computer interaction.

[0118] Based on the same technical concept, the embodiment of the present application also provides an advertising bidding strategy configuration device, such as Figure 5 As shown, the device comprises:

[0119] The first configuration module 501 is used to configure a strategy group in the bidding strategy platform for each business scenario, wherein multiple sub-strategy groups in the strategy group are sorted according to the strategy priority, and the strategy priority is used to indicate the number of advertisement publishing points hit by traffic;

[0120] The second configuration module 502 is used to configure the sub-strategy group, wherein the multiple strategies in each sub-strategy group are sorted according to the bidding method priority;

[0121] The third configuration module 503 is used to configure policies, wherein the policy operator of each policy is composed of a specified condition, an ECPM factor and an ECPM formula.

[0122] Optionally, the first configuration module 501 is used to:

[0123] If the policy group is determined to be a single-step policy group based on the business scenario, multiple sub-policy groups are sorted in descending order of policy priority;

[0124] The strategies are sorted from high to low in priority, and the bid calculation ends after any sub-strategy group is successfully executed.

[0125] Optionally, the second configuration module 502 is used to:

[0126] If a sub-strategy group is in a single-step strategy group, then the sub-strategy group is a single-step sub-strategy group;

[0127] Sort multiple strategies in the single-step sub-strategy group in descending order of bidding method priority;

[0128] The bidding methods are sorted in descending order of priority, and the bidding calculation ends after any bidding method is successfully executed.

[0129] Optionally, the first configuration module 501 is used to:

[0130] If the policy group is determined to be a multi-step policy group based on the business scenario, multiple sub-policy groups are sorted in order from low to high policy priority;

[0131] The strategies are sorted from low to high in priority, and the bid calculation ends after all sub-strategy groups are executed.

[0132] Optionally, the second configuration module 502 is used to:

[0133] If a sub-strategy group is in a multi-step strategy group, then the sub-strategy group is a multi-step sub-strategy group;

[0134] Sort multiple strategies in the multi-step sub-strategy group in order of bidding method priority from low to high;

[0135] The bidding methods are sorted from low to high priority, and the bidding calculation of the multi-step sub-strategy group is completed after all strategies are executed.

[0136] Optionally, the third configuration module 503 is used to:

[0137] Determine whether the traffic attribute satisfies the bidding method according to a Boolean expression, wherein each Boolean expression is used to represent a bidding method;

[0138] If the bidding method is met, the bidding result is calculated based on the ECPM factor and ECPM formula.

[0139] Optionally, the device is also used for:

[0140] Configure a global policy group. The global policy is used to execute the preset bidding method when the traffic attribute fails to match all Boolean expressions. Set the policies to be sorted in descending order of bidding method priority and the sub-policy groups to be sorted in descending order of policy priority.

[0141] Based on the same technical concept, an embodiment of the present invention further provides an electronic device, such as Figure 6 As shown, it includes a processor 601, a communication interface 602, a memory 603 and a communication bus 604, wherein the processor 601, the communication interface 602, and the memory 603 communicate with each other through the communication bus 604.

[0142] Memory 603, used for storing computer programs;

[0143] The processor 601 is used to implement the above steps when executing the program stored in the memory 603.

[0144] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0145] The communication interface is used for communication between the above electronic device and other devices.

[0146] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0147] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0148] In another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above methods are implemented, including the following contents.

[0149] A strategy group is configured in the bidding strategy platform for each business scenario, wherein multiple sub-strategy groups in the strategy group are sorted according to the strategy priority, and the strategy priority is used to indicate the number of traffic hits on the advertising publishing point;

[0150] Configure sub-strategy groups, where multiple strategies in each sub-strategy group are sorted according to bidding method priority;

[0151] Configure the strategy, where the strategy operator of each strategy consists of the specified condition, ECPM factor and ECPM formula.

[0152] Optionally, configure a strategy group in the bidding strategy platform for each business scenario including:

[0153] If the policy group is determined to be a single-step policy group based on the business scenario, multiple sub-policy groups are sorted in descending order of policy priority;

[0154] The strategies are sorted from high to low in priority, and the bid calculation ends after any sub-strategy group is successfully executed.

[0155] Optionally, configure the sub-policy group to include:

[0156] If a sub-strategy group is in a single-step strategy group, then the sub-strategy group is a single-step sub-strategy group;

[0157] Sort multiple strategies in the single-step sub-strategy group in descending order of bidding method priority;

[0158] The bidding methods are sorted in descending order of priority, and the bidding calculation ends after any bidding method is successfully executed.

[0159] Optionally, configuring multiple strategy groups in the bidding strategy platform includes:

[0160] If the policy group is determined to be a multi-step policy group based on the business scenario, multiple sub-policy groups are sorted in order from low to high policy priority;

[0161] The strategies are sorted from low to high in priority, and the bid calculation ends after all sub-strategy groups are executed.

[0162] Optionally, configure the sub-policy group to include:

[0163] If a sub-strategy group is in a multi-step strategy group, then the sub-strategy group is a multi-step sub-strategy group;

[0164] Sort multiple strategies in the multi-step sub-strategy group in order of bidding method priority from low to high;

[0165] The bidding methods are sorted from low to high priority, and the bidding calculation of the multi-step sub-strategy group is completed after all strategies are executed.

[0166] Optionally, the configuration policy includes:

[0167] Determine whether the traffic attribute satisfies the bidding method according to a Boolean expression, wherein each Boolean expression is used to represent a bidding method;

[0168] If the bidding method is met, the bidding result is calculated based on the ECPM factor and ECPM formula.

[0169] Optionally, the method further comprises:

[0170] Configure a global policy group. The global policy is used to execute the preset bidding method when the traffic attribute fails to match all Boolean expressions. Set the policies to be sorted in descending order of bidding method priority and the sub-policy groups to be sorted in descending order of policy priority.

[0171] In another embodiment of the present invention, a computer program product including instructions is provided, which enables the computer to execute any one of the methods in the above embodiments when the computer program product is executed on the computer.

[0172] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0173] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0174] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for configuring an advertising bidding strategy, characterized in that: The method comprises: A strategy group is configured in the bidding strategy platform for each business scenario, wherein multiple sub-strategy groups in the strategy group are sorted according to strategy priorities, and the strategy priorities are used to indicate the number of advertisement publishing points hit by traffic; Configure sub-strategy groups, where multiple strategies in each sub-strategy group are sorted according to bidding method priority; Configure the strategy, where the strategy operator of each strategy consists of the specified condition, ECPM factor and ECPM formula.

2. The method according to claim 1, characterized in that Configuring a strategy group in the bidding strategy platform for each business scenario includes: If the policy group is determined to be a single-step policy group according to the business scenario, the plurality of sub-policy groups are sorted in descending order of policy priority; The strategies are sorted in descending order of priority, and the bid calculation is terminated after any sub-strategy group is successfully executed.

3. The method according to claim 2, characterized in that The configuration sub-policy groups include: If the sub-strategy group is in a single-step strategy group, then the sub-strategy group is a single-step sub-strategy group; Sorting the multiple strategies in the single-step sub-strategy group in descending order of bidding method priority; The bidding methods are sorted in descending order of priority, and the bidding calculation is terminated after any bidding method is successfully executed.

4. The method according to claim 1, characterized in that: Configuring multiple strategy groups in the bidding strategy platform includes: If the policy group is determined to be a multi-step policy group according to the business scenario, the multiple sub-policy groups are sorted in order from low to high policy priority; The strategy priorities are sorted from low to high, and the bid calculation is terminated after all sub-strategy groups are executed.

5. The method according to claim 4, characterized in that The configuration sub-policy groups include: If the sub-strategy group is in a multi-step strategy group, then the sub-strategy group is a multi-step sub-strategy group; Sorting the multiple strategies in the multi-step sub-strategy group in order of bidding method priority from low to high; According to the order of priority of the bidding methods from low to high, the bidding calculation of the multi-step sub-strategy group is ended after all strategies are executed.

6. The method according to claim 1, characterized in that Configuration strategies include: Determine whether the traffic attribute satisfies the bidding method according to a Boolean expression, wherein each Boolean expression is used to represent a bidding method; If the bidding method is met, the bidding result is calculated according to the ECPM factor and the ECPM formula.

7. The method according to claim 1, characterized in that The method further comprises: Configure a global policy group, wherein the global policy is used to execute a preset bidding method when the traffic attribute fails to match all Boolean expressions, and set the policy to be sorted in descending order of bidding method priority and the sub-policy groups to be sorted in descending order of policy priority.

8. An advertising bidding strategy configuration device, characterized in that: The device comprises: A first configuration module is used to configure a strategy group in the bidding strategy platform for each business scenario, wherein multiple sub-strategy groups in the strategy group are sorted according to a strategy priority, and the strategy priority is used to indicate the number of advertisement publishing points hit by traffic; A second configuration module is used to configure a sub-strategy group, wherein multiple strategies in each sub-strategy group are sorted according to the bidding method priority; The third configuration module is used to configure the strategy, wherein the strategy operator of each strategy is composed of a specified condition, an ECPM factor and an ECPM formula.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.