Advertisement bidding automatic adjustment method and system

Abstract

The invention discloses an automatic adjustment method and system for advertisement bidding. The method comprises the steps of S1, data collection; S2, parameter setting: setting a target CPC, a target return value and auxiliary parameters set according to business requirements and market experience; s3, exposure rate calculation: extracting related feature information of media from historical data, and constructing a feature vector in combination with current market environment information; inputting the feature vector into a pre-trained exposure rate prediction model to obtain a potential maximum exposure rate prediction value of the media; meanwhile, the prediction value is dynamically adjusted by using real-time data, and the prediction result is updated; step S4, bid adjustment: bid calculation of bid media; calculating a transaction profit rate; and S5, executing and optimizing. According to the invention, the exposure rate of the media can be improved, the consumption and profit are increased, and the workload of operators can be greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent advertising bidding technology, and in particular to an automatic advertising bidding adjustment method and system. Background Art

[0002] In the entire chain of programmatic advertising, the media floor price, the bid made to the demand side, and the adjustment of profit margins are the most basic and core functions for the programmatic system, and their importance is self-evident.

[0003] In the industry, combined Figure 4-5 , the supply side platform (SSP) acts as an intermediary and adjusts the bids in the three links of "② sending to the demand side", "④ returning media ads" and "⑥ giving the demand side the transaction price". In this way, the transaction can be carried out smoothly and the SSP can also gain benefits from it. Currently, the bidding situation is usually as shown in the figure below. The backend can provide the function of manually configuring price increase, price decrease and profit margin.

[0004] It should be noted that the transaction link data of the same media in different time periods and facing different customers will show large differences. Therefore, operators need to observe the data frequently, adjust the "floating rate" to affect the fill rate of the demand side, adjust the "floating rate" to affect the media's winning rate and exposure rate, and adjust the profit margin to optimize the click rate of the demand side.

[0005] However, how to maximize the overall benefits on the one hand, and reduce the time spent by operators on manual data observation and tuning on the other hand, is a technical problem that needs to be solved urgently in this field.

[0006] In view of this, the present invention is proposed. Summary of the invention

[0007] The purpose of the present invention is to overcome the above-mentioned technical deficiencies and provide a method and system for automatically adjusting advertising bids to solve the technical problem in the related art of how to maximize the overall revenue on the one hand and reduce the time spent by operators on manual observation of data and optimization on the other hand.

[0008] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:

[0009] An automatic adjustment method for an advertisement bid, comprising:

[0010] Step S1, data collection:

[0011] Collect client bid and media performance data;

[0012] Classify and organize the collected data and store it according to time series, media type, and customer category;

[0013] Step S2, parameter setting:

[0014] Set target CPC and target rebate values ​​and auxiliary parameters based on business needs and market experience;

[0015] Step S3, exposure rate calculation:

[0016] Extract relevant feature information of media from historical data, combine it with current market environment information, and construct feature vectors;

[0017] Input the feature vector into the pre-trained exposure rate prediction model to obtain the predicted value of the media's potential maximum exposure rate; at the same time, use real-time data to dynamically adjust the predicted value and update the prediction result;

[0018] Step S4, bid adjustment:

[0019] Bid media bid calculation: Based on the target CPC and the currently calculated exposure rate, combined with the cost-benefit analysis model, calculate the media bid that can maximize the exposure opportunities for the ad while meeting the target CPC;

[0020] Calculation of transaction profit rate: Based on the target rebate set by the operation staff and the advertising cost structure, taking into account the revenue sharing ratio of different media and tax factors, a transaction profit rate calculation model is established. By solving the model, it is ensured that the calculated transaction profit rate can meet the target set by the operation staff, while ensuring the preset price advantage in the market competition;

[0021] Step S5, execution and optimization:

[0022] Apply the adjusted bidding strategy to the advertising delivery system in real time. During the delivery process, continuously collect feedback data and use reinforcement learning algorithms to optimize the bidding strategy in real time.

[0023] Furthermore, the collecting of customer bids and media performance data specifically includes:

[0024] Using web crawler technology, data interface calls and log file analysis, we collect customer bidding and media performance data from the advertising exchange platform's database, the media's advertising management system, and the client's behavior tracking logs.

[0025] Furthermore, the auxiliary parameters set according to business needs and market experience include: a maximum limit on bid adjustment and a tolerance range for profit margin fluctuations.

[0026] Furthermore, the relevant characteristic information of the media includes: the audience coverage of the media, the audience activity, and the distribution of advertising positions; the current market environment information includes: competitor situation and hot topics in the industry.

[0027] Furthermore, the use of real-time data to dynamically adjust the predicted value and update the predicted result specifically includes: updating the predicted result by a weighted average method according to the exposure rate change trend in a recent period of time.

[0028] Furthermore, the calculation of the media bid that can maximize the exposure opportunity of the advertisement under the premise of meeting the target CPC specifically includes: using a linear regression model to analyze the relationship between historical bids and exposure rates and costs, and calculating the current bid based on this.

[0029] Furthermore, the real-time optimization of the bidding strategy specifically includes: when it is found that the click-through rate of a certain advertisement on a specific media is continuously lower than expected, the bid reduction rate or transaction profit rate is automatically adjusted to try to improve the attractiveness and competitiveness of the advertisement.

[0030] The present invention also provides an automatic adjustment system for advertisement bidding, comprising:

[0031] A data collection unit is used to collect customer bids and media performance data; the collected data is classified and sorted, and stored according to time series, media type, and customer category;

[0032] Parameter setting unit, used to set target CPC and target rebate value and auxiliary parameters according to business needs and market experience;

[0033] The exposure rate calculation unit is used to extract relevant feature information of the media from historical data, and construct a feature vector in combination with the current market environment information; the feature vector is input into the pre-trained exposure rate prediction model to obtain the predicted value of the potential maximum exposure rate of the media; at the same time, the predicted value is dynamically adjusted using real-time data to update the prediction result;

[0034] The bid adjustment unit is used for media bid calculation: based on the target CPC and the currently calculated exposure rate, combined with the cost-benefit analysis model, the media bid that can maximize the exposure opportunities of the advertisement while meeting the target CPC is calculated; transaction profit rate calculation: based on the target rebate set by the operator and the advertising cost structure, taking into account the share ratio of different media and tax factors, a transaction profit rate calculation model is established. By solving the model, it is ensured that the calculated transaction profit rate can meet the target set by the operator, while ensuring that it has a preset price advantage in market competition;

[0035] The execution and optimization unit is used to apply the adjusted bidding strategy to the advertising delivery system in real time. During the delivery process, it continuously collects feedback data and uses reinforcement learning algorithms to optimize the bidding strategy in real time.

[0036] According to another aspect of the present invention, there is also provided an electronic device, comprising: a processor and a memory;

[0037] The memory stores a computer-readable program executable by the processor;

[0038] When the processor executes the computer-readable program, the steps in the above method are implemented.

[0039] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the steps in the above method.

[0040] The present invention provides an automatic adjustment method and system for advertising bids, which creatively introduces a new bidding link to automatically adjust the base price and profit margin. This method uses big data and algorithms, takes the maximum exposure rate of the media as the cornerstone, and automatically calculates the bid reduction rate and transaction profit margin, so as to achieve the target cost per click (CPC) and target profit margin after rebate set by the operator. This new strategy can not only increase media exposure, thereby increasing consumption and profits, but also greatly reduce the workload of operators. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic flow chart of an automatic adjustment method for an advertisement bid is provided for an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of the structure of an automatic adjustment system for advertisement bidding is provided for an embodiment of the present invention;

[0043] Figure 3 It is a structural block diagram of a terminal capable of implementing the automatic adjustment method of the advertisement bid according to the embodiment of the present invention;

[0044] Figure 4 This is a flowchart of the programmatic core transaction link;

[0045] Figure 5 This is a flowchart about bidding in the programmatic core transaction link;

[0046] Figure 6 A bidding link diagram of the automatic adjustment method for advertisement bidding provided by an embodiment of the present invention;

[0047] Figure 7This is a diagram showing the effect of the automatic adjustment method for advertisement bids provided by an embodiment of the present invention in an application scenario. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the solution of the present application, 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 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 creative work should fall within the scope of protection of the present application.

[0049] Programmatic transaction link for advertising bidding Figure 4-5 As shown. First, the media end ( Figure 4 , 5 The APP end in the process (such as direct media, third-party SSP, ADX, etc.) sends an advertising request to the supply-side platform SSP, and then the supply-side platform sends the advertising request to the demand-side DSP, and then the DSP returns the advertisement to the SSP, and then returns it to the media end, and finally the media end displays it successfully. Regarding the bidding link, the media end first gives the media floor price and sends it to the SSP. The demand-side floor price sent by the SSP to the DSP = media submission * (1 + floating rate), the DSP returns the demand-side bid, and the SSP returns the media bid = demand-side bid * (1 + floating rate), and then completes the media transaction price and sends it to the SSP. The SSP sends the demand-side transaction price to the DSP = media transaction price * (1 + floating rate).

[0050] Embodiment 1

[0051] According to an embodiment of the present invention, a method for automatically adjusting an advertisement bid is provided. Figure 1 ,include:

[0052] Step S1, data collection:

[0053] By using a variety of methods such as web crawler technology, data interface calls and log file analysis, we collect rich customer bidding and media performance data from multiple channels such as the advertising trading platform database, the media's advertising management system, and the client's behavior tracking logs.

[0054] The collected data is classified and organized, and stored according to dimensions such as time series, media type, and customer category to facilitate subsequent analysis and processing.

[0055] In step S1, data is collected from different channels through various means such as web crawlers, API calls, and log analysis, which can ensure that the data sources are extensive and diverse, and improve the comprehensiveness and accuracy of the data. This helps to gain a deeper understanding of market dynamics and provide solid data support for advertising strategies.

[0056] Classification, organization and storage: Data is classified, organized and stored according to dimensions such as time series, media type, and customer category, making subsequent data processing more efficient and orderly, facilitating rapid retrieval and analysis, and improving the convenience and efficiency of data use.

[0057] Step S2, parameter setting:

[0058] Operation personnel input the target CPC and target rebate value through a specially designed user interface. At the same time, other auxiliary parameters can be set according to business needs and market experience, such as the maximum limit of bid adjustment and the tolerance range of profit margin fluctuations.

[0059] Perform legality checks and range verification on input parameters to ensure that parameter values ​​are within a reasonable range and avoid algorithm anomalies caused by unreasonable parameters.

[0060] In step S2, operators can flexibly adjust the target CPC (cost per click) and rebate value and other auxiliary parameters through a specially designed interface, which enhances the flexibility and adaptability of the system and enables rapid response to market changes. Legality check: Verify the input parameters to ensure the stability and reliability of the system operation and prevent algorithm failure or abnormal situations caused by incorrect settings.

[0061] Step S3, exposure rate calculation:

[0062] Extract relevant characteristic information of the media from historical data, such as the media's audience coverage, audience activity, advertising space distribution, etc., and combine it with current market environment information (such as competitor situation, industry hot topics, etc.) to construct a feature vector.

[0063] The feature vector is input into the pre-trained exposure prediction model to obtain the predicted value of the media's potential maximum exposure rate. At the same time, the predicted value is dynamically adjusted using real-time data, such as updating the prediction result through weighted average and other methods based on the exposure rate change trend in the recent period.

[0064] In step S3, the prediction results are updated using real-time data to make the prediction closer to the actual situation, enhance the support for decision-making, and ensure that the advertising strategy can respond to market changes in a timely manner.

[0065] Step S4, bid adjustment:

[0066] Bid media bid calculation: Based on the target CPC and the currently calculated exposure rate, combined with the cost-benefit analysis model, calculate the media bid that can maximize the exposure opportunities for the ad while meeting the target CPC. This model takes into account multiple factors such as advertising costs, expected returns, and market competition, and solves the optimal bid by establishing a mathematical relationship. For example, a linear regression model is used to analyze the relationship between historical bids and exposure rates and costs, and the current bid is calculated based on this.

[0067] Transaction profit rate calculation: Based on the target rebate set by the operator and the advertising cost structure, and taking into account the share ratio of different media, taxation and other factors, a transaction profit rate calculation model is established. By solving this model, it is ensured that the calculated transaction profit rate can meet the target set by the operator, while ensuring a certain price advantage in market competition.

[0068] In step S4, under the premise of meeting the target CPC, the optimal bid is solved by comprehensively considering multiple factors, which not only reduces the cost of advertising, but also increases the exposure opportunities of advertising, achieving the dual effects of cost control and effect improvement. In addition, a calculation model is established by considering factors such as the share ratio and taxation to ensure that the final profit margin meets expectations, maintains good profitability, and maintains price competitiveness.

[0069] Step S5, execution and optimization:

[0070] The adjusted bidding strategy is applied to the advertising delivery system in real time through the execution unit. During the delivery process, feedback data is continuously collected and the bidding strategy is optimized in real time using the reinforcement learning algorithm. For example, when it is found that the click-through rate of an advertisement on a specific media is continuously lower than expected, the bid reduction rate or transaction profit rate is automatically adjusted to try to improve the attractiveness and competitiveness of the advertisement.

[0071] In step S5, a reinforcement learning algorithm is used to continuously optimize the bidding strategy and adjust parameters based on actual feedback, such as automatically adjusting bids or profit margins when the click-through rate is lower than expected, thereby enhancing the effectiveness and competitiveness of the advertising campaign and promoting long-term performance growth.

[0072] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0073] As an example, Figure 6 The bidding link of the embodiment of the present invention is shown. Figure 5 The difference is that the media bid returned by the supply-side platform WM = (demand-side bid - target profit after rebate) × (1-() current CPC - target CPC) × bid corresponding winning rate, and the demand-side transaction price = demand-side bid × (95%-99% random value).

[0074] Embodiment 2

[0075] According to an embodiment of the present invention, a system for automatically adjusting an advertisement bid is provided. Figure 2 ,include:

[0076] A data collection unit is used to collect customer bids and media performance data; the collected data is classified and sorted, and stored according to time series, media type, and customer category;

[0077] Parameter setting unit, used to set target CPC and target rebate value and auxiliary parameters according to business needs and market experience;

[0078] The exposure rate calculation unit is used to extract relevant feature information of the media from historical data, and construct a feature vector in combination with the current market environment information; the feature vector is input into the pre-trained exposure rate prediction model to obtain the predicted value of the potential maximum exposure rate of the media; at the same time, the predicted value is dynamically adjusted using real-time data to update the prediction result;

[0079] The bid adjustment unit is used for media bid calculation: based on the target CPC and the currently calculated exposure rate, combined with the cost-benefit analysis model, the media bid that can maximize the exposure opportunities of the advertisement while meeting the target CPC is calculated; transaction profit rate calculation: based on the target rebate set by the operator and the advertising cost structure, taking into account the share ratio of different media and tax factors, a transaction profit rate calculation model is established. By solving the model, it is ensured that the calculated transaction profit rate can meet the target set by the operator, while ensuring that it has a preset price advantage in market competition;

[0080] The execution and optimization unit is used to apply the adjusted bidding strategy to the advertising delivery system in real time. During the delivery process, it continuously collects feedback data and uses reinforcement learning algorithms to optimize the bidding strategy in real time.

[0081] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0082] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can be run in a corresponding hardware environment, can be implemented by software, and can also be implemented by hardware, wherein the hardware environment includes a network environment.

[0083] Application Example 1

[0084] Based on a small-scale pilot on an advertising platform, data was collected to verify the effectiveness of the algorithm and record changes in exposure and profits.

[0085] Application Example 2

[0086] Conduct data comparison experiments on multiple media platforms to track overall advertising effectiveness and ensure that each indicator achieves the expected results.

[0087] Economic Benefits

[0088] The implementation of this invention can significantly improve the economic benefits of advertising, increase consumption, and reduce operating costs through intelligent management. This technical patent will provide relevant companies with a competitive advantage in the field of advertising. Figure 7 .

[0089] Figure 3 is a structural block diagram of a terminal according to an embodiment of the present application, such as Figure 3 As shown, the terminal may include: one or more (only one is shown) processors 101, a memory 103, and a transmission device 105, such as Figure 3 As shown, the terminal may also include an input and output device 107 .

[0090] Among them, the memory 103 can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 103, that is, implementing the above-mentioned method. The memory 103 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 103 may further include a memory remotely arranged relative to the processor 101, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0091] The transmission device 105 is used to receive or send data via a network, and can also be used for data transmission between a processor and a memory. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 105 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 105 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0092] Specifically, the memory 103 is used to store application programs.

[0093] The processor 101 may call the application program stored in the memory 103 through the transmission device 105 to execute the steps in the above method.

[0094] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0095] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to execute the program code of the above method.

[0096] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0097] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0098] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0099] In several embodiments provided in this application, the device embodiments described are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of units or modules, which may be electrical or other forms.

[0100] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0101] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0102] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for automatically adjusting an advertisement bid, characterized in that: include: Step S1, data collection: Collect client bid and media performance data; Classify and organize the collected data and store it according to time series, media type, and customer category; Step S2, parameter setting: Set target CPC and target rebate value and auxiliary parameters based on business needs and market experience; Step S3, exposure rate calculation: Extract relevant feature information of media from historical data, combine it with current market environment information, and construct feature vectors; Input the feature vector into the pre-trained exposure rate prediction model to obtain the predicted value of the media's potential maximum exposure rate; at the same time, use real-time data to dynamically adjust the predicted value and update the prediction result; Step S4, bid adjustment: Bid media bid calculation: Based on the target CPC and the currently calculated exposure rate, combined with the cost-benefit analysis model, calculate the media bid that can maximize the exposure opportunities for the ad while meeting the target CPC; Calculation of transaction profit rate: Based on the target rebate set by the operation staff and the advertising cost structure, taking into account the revenue sharing ratio of different media and tax factors, a transaction profit rate calculation model is established. By solving the model, it is ensured that the calculated transaction profit rate can meet the target set by the operation staff, while ensuring the preset price advantage in the market competition; Step S5, execution and optimization: Apply the adjusted bidding strategy to the advertising delivery system in real time. During the delivery process, continuously collect feedback data and use reinforcement learning algorithms to optimize the bidding strategy in real time.

2. The method for automatically adjusting an advertisement bid according to claim 1, characterized in that: The collection of customer bidding and media performance data specifically includes: Using web crawler technology, data interface calls and log file analysis, we collect customer bidding and media performance data from the advertising exchange platform's database, the media's advertising management system, and the client's behavior tracking logs.

3. The method for automatically adjusting an advertisement bid according to claim 1, characterized in that: The auxiliary parameters set according to business needs and market experience include: a maximum limit on bid adjustment and a tolerance range for profit margin fluctuations.

4. The method for automatically adjusting an advertisement bid according to claim 1, characterized in that: The relevant characteristic information of the media includes: the audience coverage, audience activity, and advertising space distribution of the media; the current market environment information includes: competitor situation and industry hot topics.

5. The method for automatically adjusting an advertisement bid according to claim 1, characterized in that: The method of dynamically adjusting the predicted value using real-time data and updating the predicted result specifically includes: updating the predicted result by a weighted average method according to the exposure rate change trend in the recent period of time.

6. The method for automatically adjusting an advertisement bid according to claim 1, characterized in that: The calculation of the media bid that can maximize the exposure opportunity of the advertisement under the premise of meeting the target CPC specifically includes: using a linear regression model to analyze the relationship between historical bids, exposure rates and costs, and calculating the current bid based on this.

7. The method for automatically adjusting an advertisement bid according to claim 1, characterized in that: The real-time optimization of the bidding strategy specifically includes: when it is found that the click-through rate of a certain advertisement on a specific media is continuously lower than expected, the bid reduction rate or transaction profit rate is automatically adjusted to try to improve the attractiveness and competitiveness of the advertisement.

8. An automatic adjustment system for advertising bids, characterized in that: include A data collection unit is used to collect customer bids and media performance data; the collected data is classified and sorted, and stored according to time series, media type, and customer category; Parameter setting unit, used to set target CPC and target rebate value and auxiliary parameters according to business needs and market experience; An exposure rate calculation unit is used to extract relevant feature information of the media from historical data and construct a feature vector in combination with current market environment information; Input the feature vector into the pre-trained exposure rate prediction model to obtain the predicted value of the media's potential maximum exposure rate; at the same time, use real-time data to dynamically adjust the predicted value and update the prediction result; The bid adjustment unit is used for media bid calculation: based on the target CPC and the currently calculated exposure rate, combined with the cost-benefit analysis model, the media bid that can maximize the exposure opportunities of the advertisement while meeting the target CPC is calculated; transaction profit rate calculation: based on the target rebate set by the operator and the advertising cost structure, taking into account the share ratio of different media and tax factors, a transaction profit rate calculation model is established. By solving the model, it is ensured that the calculated transaction profit rate can meet the target set by the operator, while ensuring that it has a preset price advantage in market competition; The execution and optimization unit is used to apply the adjusted bidding strategy to the advertising delivery system in real time. During the delivery process, it continuously collects feedback data and uses reinforcement learning algorithms to optimize the bidding strategy in real time.

9. An electronic device, characterized in that: include: Processor and memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps in the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the method according to any one of claims 1 to 7.

Images