Advertisement base price adjusting method and related device

Abstract

The invention discloses an advertisement base price adjusting method and a related device, and relates to the technical field of data processing, and the method comprises the steps: obtaining advertisement flow information corresponding to a target advertisement position, demand side equipment identification information and transaction weighted price information of a current time step, generating initial base price information according to the advertisement flow information and the demand side equipment identification information, and sending the initial base price information to the target advertisement position; judging whether the initial bottom price information is adjusted or not according to the transaction weighted price information of the current time step, if not, determining the initial bottom price information as target bottom price information when the demand side purchases the target advertisement position at the current time step, and if yes, obtaining a negative feedback coefficient of the current time step, and adjusting the initial bottom price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step to obtain target bottom price information when the demand side purchases the target advertisement position at the current time step. According to the advertisement flow information, the demand side and the market bidding environment, the advertisement base price is flexibly adjusted, and the base price adjusting capability is higher.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an advertisement floor price adjustment method and related devices. Background Art

[0002] In the field of online advertising, the two common floor price models include the waterfall model and the no-floor price bidding model. However, these two floor price models have the problem of poor floor price adjustment capabilities, which needs to be solved urgently. Summary of the invention

[0003] In view of the above problems, the present application provides an advertisement floor price adjustment method and related devices to achieve the purpose of flexibly adjusting the advertisement floor price according to the advertisement flow information and the market bidding environment. The specific scheme is as follows:

[0004] The first aspect of the present application provides an advertisement reserve price adjustment method, comprising:

[0005] Acquire the advertisement flow information corresponding to the target advertisement position, the demander device identification information and the transaction weighted price information of the current time step, wherein the transaction weighted price information of the current time step is obtained according to the transaction price information of the historical time step and the transaction price information of the current time step, and the demander device identification information refers to the identification information of the device used by the demander who needs to purchase the target advertisement position;

[0006] Generate initial reserve price information according to the advertisement flow information and the demand side device identification information;

[0007] Determining whether to adjust the initial reserve price information according to the transaction weighted price information of the current time step;

[0008] If not, the initial reserve price information is determined as the target reserve price information when the demander purchases the target advertising space at the current time step;

[0009] If so, obtain the negative feedback coefficient of the current time step, adjust the initial reserve price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step, and obtain the target reserve price information when the demander purchases the target advertising space at the current time step.

[0010] In a possible implementation, the determining whether to adjust the initial reserve price information according to the transaction weighted price information of the current time step includes:

[0011] Determining whether the transaction weighted price information at the current time step is greater than a preset transaction price threshold;

[0012] If so, it is determined to adjust the initial reserve price information; otherwise, it is determined not to adjust the initial reserve price information.

[0013] In a possible implementation, the process of determining the transaction price information of the current time step includes:

[0014] Based on the transaction price information of the historical time step, obtain the target floor price information when the demander purchased the target ad space in the previous time step, where the previous time step refers to the time step adjacent to the current time step in the forward direction, and the historical time step includes the previous time step;

[0015] Obtain the bid information of the demander in the current time step;

[0016] Determine whether the bid information of the demander in the current time step is greater than the target floor price information when the demander purchased the target ad space in the previous time step;

[0017] If so, determine the transaction price information of the current time step according to the bid information of the demander in the current time step.

[0018] In a possible implementation, the process of obtaining the negative feedback coefficient of the current time step includes:

[0019] Obtain the actual bid rate in the current time step, the actual bid rate in the previous time step, the predicted bid rate in the previous time step, the negative feedback coefficient in the previous time step, and the Kalman gain in the current time step;

[0020] Based on the actual bid rate in the previous time step, the predicted bid rate in the previous time step, the negative feedback coefficient in the previous time step, and the Kalman gain in the current time step, use the Kalman filtering algorithm to obtain the target bid rate in the current time step;

[0021] Based on the target bid rate in the current time step, the actual bid rate in the current time step, and the negative feedback coefficient in the previous time step, obtain the negative feedback coefficient of the current time step.

[0022] In a possible implementation, the process of obtaining the Kalman gain of the current time step includes:

[0023] Obtain the variance of the predicted bid rate in the previous time step and the Kalman gain in the previous time step, where if the previous time step is the first time step, both the variance of the predicted bid rate in the previous time step and the Kalman gain in the previous time step are preset values;

[0024] Based on the variance of the predicted bid rate in the previous time step and the Kalman gain in the previous time step, determine the variance of the target bid rate in the previous time step;

[0025] Determining a predicted bid rate variance at a current time step according to the negative feedback coefficient at the previous time step and the target bid rate variance at the previous time step;

[0026] The Kalman gain of the current time step is determined according to the predicted bid rate variance of the current time step.

[0027] In a possible implementation, obtaining the negative feedback coefficient of the current time step according to the target bid rate of the current time step, the actual bid rate of the current time step, and the negative feedback coefficient of the previous time step includes:

[0028] Calculating the difference between the target bid rate at the current time step and the actual bid rate at the current time step;

[0029] If the difference is a positive value and the absolute value of the difference is greater than a preset difference threshold, the negative feedback coefficient of the previous time step is lowered according to the preset first step length to obtain the negative feedback coefficient of the current time step;

[0030] If the difference is a negative value and the absolute value of the difference is greater than the difference threshold, the negative feedback coefficient of the previous time step is increased according to a preset second step size to obtain the negative feedback coefficient of the current time step.

[0031] In a possible implementation, the initial reserve price information is adjusted according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step to obtain the target reserve price information when the demander purchases the target advertising space at the current time step, including:

[0032] Determining the reserve price adjustment amount information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step;

[0033] The reserve price adjustment amount information and the initial reserve price information are added together, and the sum is used as the target reserve price information when the demander purchases the target advertising space at the current time step.

[0034] A second aspect of the present application provides an advertising floor price adjustment device, comprising:

[0035] A data acquisition module is used to acquire the advertisement flow information corresponding to the target advertisement position, the demander device identification information and the transaction weighted price information of the current time step, wherein the transaction weighted price information of the current time step is obtained according to the transaction price information of the historical time step and the transaction price information of the current time step, and the demander device identification information refers to the identification information of the device used by the demander who needs to purchase the target advertisement position;

[0036] An initial reserve price generating module, used to generate initial reserve price information according to the advertisement flow information and the demand side device identification information;

[0037] An adjustment judgment module, used to judge whether to adjust the initial reserve price information according to the transaction weighted price information of the current time step;

[0038] A first target reserve price generating module, configured to determine the initial reserve price information as the target reserve price information when the demander purchases the target advertising space at the current time step when the adjustment judgment module determines that the initial reserve price information is not to be adjusted;

[0039] The second target reserve price generating module is used for obtaining the negative feedback coefficient of the current time step when the adjustment judgment module determines to adjust the initial reserve price information, and adjusting the initial reserve price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step to obtain the target reserve price information when the demander purchases the target advertising space at the current time step.

[0040] A third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the advertising floor price adjustment method of the first aspect or any implementation of the first aspect.

[0041] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0042] The memory is used to store computer programs;

[0043] The processor is used to execute the computer program so that the electronic device can implement the advertising floor price adjustment method of the first aspect or any implementation manner of the first aspect.

[0044] In a fifth aspect, the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the advertising floor price adjustment method of the first aspect or any implementation method of the first aspect.

[0045] With the above technical solution, for the advertising floor price adjustment method provided by this application, considering that both advertising traffic and demand parties can affect the advertising floor price, this application obtains the advertising traffic information and demand party device identification information corresponding to the target advertising space, and generates the initial floor price information based on the advertising traffic information and demand party device identification information. Further, the current market bidding environment may also affect the advertising floor price. For example, the more intense the bidding, the higher the transaction price, and the higher the advertising floor price. Based on this, this application also obtains the weighted transaction price information of the target advertising space at the current time step, and determines whether to adjust the initial floor price information according to the weighted transaction price information at the current time step. If not, the initial floor price information is determined as the target floor price information when the demand party purchases the target advertising space at the current time step. If so, the negative feedback coefficient at the current time step is obtained, and the initial floor price information is adjusted according to the negative feedback coefficient at the current time step and the weighted transaction price information at the current time step to obtain the target floor price information when the demand party purchases the target advertising space at the current time step. It can be seen that this application can flexibly adjust the advertising floor price according to the advertising traffic information, demand parties, and market bidding environment, with stronger floor price adjustment ability and more reasonable floor price. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the original components and elements are not necessarily drawn to scale.

[0047] Figure 1 It is a schematic diagram of a system architecture provided by this application;

[0048] Figure 2 It is a schematic flowchart of an advertising floor price adjustment method provided by this application;

[0049] Figure 3 It is a schematic flowchart of a method for determining the transaction price information at the current time step provided by this application;

[0050] Figure 4 It is a schematic flowchart of a method for determining the negative feedback coefficient at the current time step provided by this application;

[0051] Figure 5 It is a schematic diagram of the structure of an advertising floor price adjustment device provided by this application;

[0052] Figure 6 It is a schematic diagram of the structure of an electronic device provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application. The terms used in the embodiments of the present application are only used to explain the specific embodiments of the present application, rather than to limit the present application.

[0054] The embodiments of the present application will be described below in conjunction with the accompanying drawings. Those of ordinary skill in the art will know that with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0055] The terms "first", "second", etc. in the specification, claims and above-mentioned drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, which is only a way of distinguishing when describing objects with the same attributes in the embodiments of the present application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product or device including a series of units does not have to be limited to those units, but may include other units that are not clearly listed or are inherent to these processes, methods, products or devices.

[0056] See Figure 1 , Figure 1 which shows a schematic diagram of a system architecture. The system may include a supply-side platform 100, an ad exchange platform 200, and a demand-side platform 300.

[0057] Among them, the supply-side platform (Supply Side Platform, SSP) 100 is an online advertising technology platform designed specifically for media / publishers to optimize and manage ad inventory programmatically. Its main functions include:

[0058] 1. Ad inventory management: Helps publishers centrally manage their ad inventory, including the planning, pricing, display, etc. of ad slots, and ensures the effective utilization of ad resources.

[0059] 2. Real-time bidding: Connects to the ad exchange platform and the demand-side platform, and determines the final display price of ads through a real-time bidding mechanism to ensure that ad inventory is sold at the highest effective cost per thousand impressions (eCPM).

[0060] 3. Data analysis and optimization: Provides rich data analysis functions to help publishers understand key metrics such as the utilization of ad inventory and ad revenue, optimize ad strategies, and improve ad effects.

[0061] 4. Automated trading: Realizes the automation of ad trading, reduces manual intervention, and improves trading efficiency and accuracy.

[0062] The Ad Exchange (ADX) 200 is an online platform for digital advertising transactions that connects advertisers and media, facilitating their transactions and cooperation in the digital advertising market. Its main functions include:

[0063] 1. Ad placement: Allows advertisers to place ads and select target audiences. Advertisers can choose suitable ad spaces for placement according to their own needs and target audiences.

[0064] 2. Ad trading: This is the transaction process between advertisers and media. During the transaction, advertisers can select ad spaces and purchase ads, while media provides ad spaces to maximize ad revenue.

[0065] 3. Data analysis and optimization: Provides data analysis tools to help advertisers and media better understand ad effects and audience feedback, and make corresponding optimizations. Advertisers can use these tools to monitor and optimize ads in real time to ensure maximum ad placement effects.

[0066] 4. Technical support and innovation: With the rapid development of artificial intelligence and big data technologies, the ad trading platform can better utilize user data (it should be noted that here the user data is data that has been properly informed to users and obtained user authorization in accordance with relevant laws and regulations) to optimize ad targeting and placement strategies.

[0067] The Demand-Side Platform (DSP) 300 is a technology platform in the digital advertising ecosystem that helps advertisers or agencies purchase ad traffic programmatically across channels. Its main functions include:

[0068] 1. Cross-platform traffic integration: The DSP can integrate traffic resources from multiple ad trading platforms, break media silos, and connect to tens of thousands of media resources (including web pages, apps, videos, etc.) with one click.

[0069] 2. Precise targeting ability: The DSP combines multi-dimensional tags such as user behavior data, geographical location, and device type to achieve a population targeting accuracy of over 90%.

[0070] 3. Real-time bidding efficiency: The DSP uses real-time bidding technology, and the bidding decision time for a single ad display is less than 100 ms, which is 1000 times the efficiency of traditional manual negotiation.

[0071] 4. Cost control advantages: The DSP supports multiple billing models and dynamically optimizes the bidding strategy through algorithms to help advertisers effectively control costs.

[0072] In a possible scenario, the supply-side platform 100 may receive an advertisement request from a supplier (the advertisement request is used to request the sale of an advertisement space), and then send the advertisement request to the advertisement exchange platform 200 .

[0073] The advertising trading platform 200 generates a price inquiry request based on the advertising floor price information in the advertising request, and then sends the price inquiry request to each demand-side platform 300 .

[0074] The demand-side platform 300 may respond to the price inquiry request and return the demand-side bidding information, or may not respond to the price inquiry request.

[0075] The advertising trading platform 200 performs bidding processing according to the bid information received from each demand party, and obtains the transaction price information of the advertising space to be sold according to the bidding result.

[0076] Of course, the above scenarios are only examples, and there may be other scenarios besides these, which are not specifically limited in this application.

[0077] The present application provides an advertisement floor price adjustment method, which can be applied to the advertisement trading platform 200 in the above system. In order to make those skilled in the art better understand the present application, the advertisement floor price adjustment method of the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0078] Reference Figure 2 , Figure 2 A flowchart of a method for adjusting an advertisement floor price provided in an embodiment of the present application, the method may include:

[0079] Step S201: Obtain the advertisement flow information corresponding to the target advertisement position, the demander device identification information and the transaction weighted price information of the current time step.

[0080] Here, the demander's device identification information refers to the identification information of the device used by the demander who needs to purchase the target advertising space, such as the device number, device name, and other identification information.

[0081] Considering the differences in advertising traffic, demand parties and market bidding environments, different reserve prices may result. For example, the greater the advertising traffic, the more intense the market bidding environment, which means the better the advertising position, the higher the reserve price may be. On the contrary, the smaller the advertising traffic, the quieter the market bidding environment, which means the worse the advertising position may be, the lower the reserve price may be. The more active the demand party, the higher the reserve price may be. The less active the demand party (for example, the demand party has not logged into the media application for a long time, indicating that the demand party is a lost user), the lower the reserve price may be. For example, demand party A is a highly active user of the media application, and demand party B is a lost user of the media application (for example, demand party B has not logged into the media application for a long time). Compared with demand party B, demand party A may have a higher reserve price. Based on this, in order to enable the advertising reserve price to be dynamically adjusted with the advertising traffic, demand party and market bidding environment, this embodiment can obtain the advertising traffic information corresponding to the target advertising position, the demand party device identification information and the transaction weighted price information of the current time step.

[0082] The transaction weighted price information of the current time step is obtained based on the transaction price information of the historical time step and the transaction price information of the current time step, and the historical time step includes one or more time steps before the current time step.

[0083] Optionally, this embodiment can obtain the transaction price information of the target advertising position at each time step starting from the first time step, and then calculate the transaction weighted price information of each time step according to the following formula (1) to obtain the transaction weighted price information of the current time step.

[0084] Formula (1);

[0085] in, represents the transaction weighted price information at the kth time step, represents the transaction weighted price information of the k-1th time step, represents the transaction price information at the kth time step, and Represents the preset weight value. The kth time step refers to the backward adjacent time step of the k-1th time step, that is, the next time step of the k-1th time step is the kth time step. If the k-1th time step is the first time step, then is 0.

[0086] Step S202: Generate initial reserve price information based on the advertisement flow information and the demander's device identification information.

[0087] Here, the initial reserve price information corresponds to the demander and the target advertisement slot. If the demander is different or the target advertisement slot is different, the initial reserve price information generated in this embodiment will be different.

[0088] Optionally, in this embodiment, first floor price information positively correlated with the advertisement traffic information may be generated, that is, the greater the advertisement traffic information, the greater the first floor price information. Then, second floor price information corresponding to the demand-side device identification information is generated. Finally, the first floor price information and the second floor price information are weighted and summed to obtain the initial floor price information.

[0089] In a possible implementation, the process of "generating first floor price information positively correlated with the advertisement traffic information" may include: presetting traffic quality levels according to the advertisement traffic, where different traffic quality levels correspond to different weights. For example, when the advertisement traffic information is in the range [0, a], it belongs to the low traffic quality level with a weight of 0.1; when the advertisement traffic information is in the range (a, b], it belongs to the medium traffic quality level with a weight of 0.2; when the advertisement traffic information is in the range (b, c], it belongs to the high traffic quality level with a weight of 0.3; when the advertisement traffic information is in the range (c, +∞), it belongs to the special traffic quality level with a weight of 0.4. Here, a, b, and c are all values preset according to the actual scenario and satisfy 0 < a < b < c < +∞.

[0090] Then, this embodiment can determine the traffic quality level to which the advertisement traffic information belongs, and then obtain the weight corresponding to the advertisement traffic information. Then, the first floor price information is generated based on the weight corresponding to the advertisement traffic information and the advertisement traffic information. For example, the advertisement traffic information is multiplied by the corresponding weight, and then the product value is scaled according to a preset scaling ratio function to obtain a scaled value that meets the advertisement floor price range, which is used as the first floor price information.

[0091] In another possible implementation, the process of "generating first floor price information positively correlated with the advertisement traffic information" may include: establishing a linear function between the advertisement traffic and the advertisement floor price based on the historical advertisement traffic and the corresponding advertisement floor price, and then substituting the advertisement traffic information into the linear function to obtain the first floor price information.

[0092] Optionally, the process of "generating second floor price information corresponding to the demand-side device identification information" may include: determining the account activity of each demand side in the media application according to a preset activity calculation function, and establishing a corresponding function between the demand side and the account activity. Then, according to the demand-side device identification information, the demand side that needs to purchase the target advertisement space in this embodiment is determined. Furthermore, through the corresponding function between the demand side and the account activity, the account activity corresponding to the demand side that needs to purchase the target advertisement space in this embodiment is queried. Finally, second floor price information positively correlated with the queried account activity is generated.

[0093] Optionally, the preset activity calculation function can be obtained based on the number of times and frequency of the demand side logging in to the media account.

[0094] Of course, the above implementation manners are only examples and do not limit this application.

[0095] Step S203: Determine whether to adjust the initial floor price information based on the volume-weighted price information of the current time step.

[0096] As introduced above, the volume-weighted price information of the current time step is a value obtained based on the transaction price information of the current time step and historical time steps. The transaction price information can reflect the intensity of market competition for the target ad space to a certain extent. Therefore, in this embodiment, it can be determined whether to adjust the initial floor price information based on the volume-weighted price information of the current time step, so as to appropriately increase the initial floor price information when the market competition is intense to maximize the value of the target ad space, and appropriately decrease the initial floor price information when the market competition is weak to increase the ad fill rate of the target ad space.

[0097] It should be noted that in Figure 1 the system, even for the same supplier (corresponding to the supplier platform 100 above, and the same hereinafter) and the same ad space, when the demand side (corresponding to the demand side platform above, and the same hereinafter) is different, the volume-weighted price information of the current time step obtained in the previous step may be different, and thus the judgment conclusion of this embodiment may be different, that is, the judgment conclusion of this embodiment is related to the specific application scenario. For ease of understanding, the embodiments of this application are introduced by taking a target ad space provided by a supplier and a demand side as an example, and the same applies hereinafter.

[0098] In a possible implementation, this embodiment can preset a transaction price threshold. Among them, for different demand sides, the preset transaction price thresholds can be the same or different, which are specifically determined according to the actual scenario. Then, this embodiment can determine whether the volume-weighted price information of the current time step is greater than the preset transaction price threshold. If so, it is determined to adjust the initial floor price information; otherwise, it is determined not to adjust the initial floor price information.

[0099] Step S204a: If not, determine the initial floor price information as the target floor price information when the demand side purchases the target ad space at the current time step.

[0100] Specifically, if it is determined not to adjust the initial floor price information based on the volume-weighted price information of the current time step, it means that the initial floor price information is the floor price information that meets the market demand. Then, the initial floor price information can be determined as the target floor price information when the demand side purchases the target ad space at the current time step.

[0101] Step S204b: If so, obtain the negative feedback coefficient of the current time step, and adjust the initial floor price information according to the negative feedback coefficient of the current time step and the volume-weighted price information of the current time step to obtain the target floor price information when the demand side purchases the target ad space at the current time step.

[0102] In this embodiment, if the initial reserve price information is determined to be adjusted based on the transaction weighted price information at the current time step, it means that either the market bidding is fierce or the market bidding is cold. At this time, the initial reserve price information needs to be adjusted to meet market demand and increase the advertising fill rate of the target advertising space.

[0103] Based on this, this embodiment can obtain the negative feedback coefficient of the current time step, and adjust the initial reserve price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step, so as to obtain the target reserve price information when the demand side purchases the target advertising space at the current time step. Here, the negative feedback coefficient of the current time step is the value obtained by adjusting the initial negative feedback coefficient according to the bid rate of the demand side in each historical time step and the current time step on the basis of the initial negative feedback coefficient (optional, the initial negative feedback coefficient can be 1 by default).

[0104] Optionally, the process of "adjusting the initial reserve price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step to obtain the target reserve price information when the demander purchases the target advertising space at the current time step" may include: determining the reserve price adjustment amount information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step; adding the reserve price adjustment amount information and the initial reserve price information, and using the sum as the target reserve price information when the demander purchases the target advertising space at the current time step.

[0105] For example, the negative feedback coefficient of the current time step is multiplied by the transaction weighted price information of the current time step, and the product value is used as the reserve price adjustment amount information. The reserve price adjustment amount information and the initial reserve price information are then added together, and the sum is used as the target reserve price information when the demander purchases the target advertising space at the current time step.

[0106] For example, the calculation process of the target reserve price information of the target advertising position at the second time step is as shown in the following formula (2).

[0107] Formula (2);

[0108] in, It indicates the target floor price information when the demand side purchases the target advertising space at the kth time step. represents the negative feedback coefficient of the kth time step, Indicates the initial reserve price information. Indicates the transaction price threshold.

[0109] The advertising floor price adjustment method provided in this application takes into account that both advertising traffic and demand parties can affect the advertising floor price. This application obtains the advertising traffic information and the device identification information of the demand party corresponding to the target advertising space, and generates the initial floor price information based on the advertising traffic information and the device identification information of the demand party. Further, the current market bidding environment may also affect the advertising floor price. For example, the more intense the bidding, the higher the transaction price, and the higher the advertising floor price. Based on this, this application also obtains the weighted transaction price information of the target advertising space at the current time step, and determines whether to adjust the initial floor price information according to the weighted transaction price information at the current time step. If not, the initial floor price information is determined as the target floor price information when the demand party purchases the target advertising space at the current time step. If so, the negative feedback coefficient at the current time step is obtained, and the initial floor price information is adjusted according to the negative feedback coefficient at the current time step and the weighted transaction price information at the current time step, so as to obtain the target floor price information when the demand party purchases the target advertising space at the current time step. It can be seen that this application can flexibly adjust the advertising floor price according to the advertising traffic information, the demand party, and the market bidding environment, with stronger floor price adjustment ability and more reasonable floor price.

[0110] In a possible implementation, the determination process of the transaction price information at the current time step in the previous step S201 is introduced.

[0111] Optionally, the determination process of the transaction price information at the current time step may include: obtaining the target floor price information when the demand party purchased the target advertising space at the previous time step according to the transaction price information at the historical time step, where the previous time step refers to the time step adjacent to the current time step in the forward direction, and the historical time step includes the previous time step; obtaining the bid information of the demand party at the current time step; determining whether the bid information of the demand party at the current time step is greater than the target floor price information when the demand party purchased the target advertising space at the previous time step; if so, determining the transaction price information at the current time step according to the bid information of the demand party at the current time step.

[0112] Here, the process of "obtaining the target floor price information when the demand party purchased the target advertising space at the previous time step according to the transaction price information at the historical time step" can refer to the determination process of the target floor price information when the demand party purchases the target advertising space at the current time step as described above, and will not be elaborated here.

[0113] As described above Figure 1According to the system introduction, the demand-side platform can respond to the inquiry request and return the demand-side bidding information, or it can not respond to the inquiry request. Therefore, if the demand-side bidding information of the current time step is obtained in this embodiment, it can be determined whether the demand-side bidding information of the current time step is greater than the target reserve price information when the demand-side purchased the target advertising space in the previous time step. If so, it means that the demand-side bidding information of the current time step is valid, and then the transaction price information of the current time step can be determined based on the demand-side bidding information of the current time step.

[0114] Optionally, the process of "determining the transaction price information of the current time step based on the demand side bidding information of the current time step" may include: using the demand side bidding information of the current time step as the transaction price information of the current time step, or, in a scenario where two prices are used for advertising, using the bidding information of another demand side that is second only to the demand side bidding information of the current time step as the transaction price information of the current time step.

[0115] See also Figure 3 As shown in FIG. 1 , it is a schematic diagram of a process for determining the transaction price information of the current time step provided by the present application. Figure 3 In step S301-step S302, after obtaining the advertisement request, the target reserve price information of the target advertisement position in the previous time step can be obtained according to the transaction price information of the historical time step.

[0116] Further, if Figure 3 Steps S303-S304, after obtaining the bid information of the demand side at the current time step, it can be determined whether the bid information of the demand side at the current time step is greater than the target reserve price information when the demand side purchased the target advertising space at the previous time step. If so, Figure 3 Step S305a determines the transaction price information of the current time step according to the demand side bidding information of the current time step. If not, Figure 3 Step S305b filters out the demand side bidding information at the current time step (the demand side bidding information at this time is considered invalid because it is lower than the target reserve price information of the target advertising position at the previous time step).

[0117] See also Figure 3 In step S306, the target floor price information of the demander when purchasing the target advertising space at the current time step can be obtained based on the transaction price information at the current time step and the transaction weighted price information at the previous time step. This process can refer to the introduction of steps S201 to S204a and step S204b above and will not be repeated here.

[0118] Still see Figure 3In step S306, as the time step moves forward, the target reserve price information when the demand side purchases the target ad space at the current time step will be used as the target reserve price information when the demand side purchases the target ad space at the previous time step, and then return to step S303 to continue obtaining the transaction price information for the next time step.

[0119] In summary, the embodiment of the present application provides a process for determining the transaction price information at the current time step, which can effectively filter out the transaction price information lower than the ad reserve price, provide a basis for the subsequent reserve price calculation process, and improve the efficiency of reserve price calculation.

[0120] In some other embodiments of the present application, the process of obtaining the negative feedback coefficient at the current time step in the previous step S204b is introduced.

[0121] In this embodiment, the Kalman Filter iterative algorithm can be used to iteratively calculate the preset initial negative feedback coefficient step by step in time to obtain the negative feedback coefficient at the current time step. Here, the Kalman Filter iterative algorithm is an algorithm that uses the linear system state equation to optimally estimate the system state through the system input and output observation data. Since the observation data includes the influence of noise and interference in the system, the optimal estimate can also be regarded as a filtering process. Essentially, the Kalman filter is a process of estimating the true value based on the data of both the observed value and the estimated value.

[0122] See Figure 4 shown in the flowchart of determining the negative feedback coefficient at the current time step provided by the present application.

[0123] As Figure 4 in step S401, in this embodiment, the actual bid rate at the current time step, the actual bid rate at the previous time step, the predicted bid rate at the previous time step, the negative feedback coefficient at the previous time step, and the Kalman gain at the current time step can be obtained.

[0124] Optionally, the process of obtaining the Kalman gain at the current time step may include: obtaining the predicted bid rate variance at the previous time step and the Kalman gain at the previous time step, where if the previous time step is the first time step, both the predicted bid rate variance at the previous time step and the Kalman gain at the previous time step are preset values; determining the target bid rate variance at the previous time step according to the predicted bid rate variance at the previous time step and the Kalman gain at the previous time step; determining the predicted bid rate variance at the current time step according to the negative feedback coefficient at the previous time step and the target bid rate variance at the previous time step; and determining the Kalman gain at the current time step according to the predicted bid rate variance at the current time step.

[0125] Here, the target bid rate refers to the posterior estimate in the Kalman filter iteration algorithm, and the predicted bid rate refers to the prior estimate in the Kalman filter iteration algorithm.

[0126] Taking the current time step as the k-th time step as an example, in this embodiment, the variance of the predicted bid rate at the previous time step (i.e., the k-1-th time step) can be obtained. and the Kalman gain at the previous time step .

[0127] Optionally, the process of "determining the variance of the target bid rate at the previous time step according to the variance of the predicted bid rate at the previous time step and the Kalman gain at the previous time step" can be implemented by the following formula (3).

[0128] Formula (3);

[0129] where, represents the variance of the target bid rate at the k-1-th time step.

[0130] Optionally, the process of "determining the variance of the predicted bid rate at the current time step according to the negative feedback coefficient at the previous time step and the variance of the target bid rate at the previous time step" can be implemented by the following formula (4).

[0131] Formula (4);

[0132] where, represents the variance of the predicted bid rate at the k-th time step, represents the noise variance of the system process, which is a preset system setting value, and usually it is assumed that does not change with the system state.

[0133] Optionally, the process of "determining the Kalman gain at the current time step according to the variance of the predicted bid rate at the current time step" can be implemented by the following formula (5).

[0134] Formula (5);

[0135] where, represents the Kalman gain at the k-th time step, represents the noise variance of the actual bid rate, which is a preset system setting value, and usually it is assumed that does not change with the system state.

[0136] It should be noted that the above formulas (3)-(5) are only examples and do not limit this application.

[0137] Furthermore, as Figure 4In step S402, in this embodiment, the target bid rate at the current time step can be obtained by using the Kalman filter algorithm based on the actual bid rate at the previous time step, the predicted bid rate at the previous time step, the negative feedback coefficient at the previous time step, and the Kalman gain at the current time step.

[0138] Here, the predicted bid rate at the first time step is the initial value, and the predicted bid rate at a non-first time step is equal to the target bid rate at that non-first time step, that is , where represents the predicted bid rate at the k-th time step, represents the target bid rate at the k-th time step.

[0139] Optionally, the process of "obtaining the target bid rate at the current time step by using the Kalman filter algorithm based on the actual bid rate at the previous time step, the predicted bid rate at the previous time step, the negative feedback coefficient at the previous time step, and the Kalman gain at the current time step" can be implemented by the following formula (6).

[0140] Formula (6);

[0141] Wherein, represents the negative feedback coefficient at the (k - 1)-th time step, represents the predicted bid rate at the (k - 1)-th time step, represents the actual bid rate at the (k - 1)-th time step.

[0142] Finally, as Figure 4 in step S403, in this embodiment, the negative feedback coefficient at the current time step can be obtained based on the target bid rate at the current time step, the actual bid rate at the current time step, and the negative feedback coefficient at the previous time step.

[0143] Here, the process of "obtaining the negative feedback coefficient at the current time step based on the target bid rate at the current time step, the actual bid rate at the current time step, and the negative feedback coefficient at the previous time step" can have multiple implementation manners, and the following implementation manners are provided but not limited to.

[0144] The first implementation manner: In this embodiment, it can be determined whether the target bid rate at the current time step is greater than the actual bid rate at the current time step; if so, the negative feedback coefficient at the previous time step is decreased by a preset first step length to obtain the negative feedback coefficient at the current time step; if not, the negative feedback coefficient at the previous time step is increased by a preset second step length to obtain the negative feedback coefficient at the current time step.

[0145] In the second implementation manner, in this embodiment, the difference between the target bid rate at the current time step and the actual bid rate at the current time step can be calculated; if the difference is positive and the absolute value of the difference is greater than a preset difference threshold, the negative feedback coefficient at the previous time step is decreased by a preset first step length to obtain the negative feedback coefficient at the current time step; if the difference is negative and the absolute value of the difference is greater than the difference threshold, the negative feedback coefficient at the previous time step is increased by a preset second step length to obtain the negative feedback coefficient at the current time step.

[0146] In this embodiment, the difference between the target bid rate at the current time step and the actual bid rate at the current time step can be calculated, and then it is determined whether the absolute value of the difference is greater than a preset difference threshold. If so, it is determined whether the difference is positive. If it is positive, the negative feedback coefficient at the previous time step is decreased by a preset first step length to obtain the negative feedback coefficient at the current time step. If it is negative, the negative feedback coefficient at the previous time step is increased by a preset second step length to obtain the negative feedback coefficient at the current time step.

[0147] That is, when the target bid rate at the current time step is greater than the actual bid rate at the current time step and exceeds the preset difference threshold, it indicates that the current floor price exceeds the affordability of the demand side. Then, the negative feedback coefficient at the previous time step can be decreased by a preset first step length to reduce the floor price and avoid a decrease in the ad fill rate due to too high a floor price. On the contrary, when the target bid rate at the current time step is less than or equal to the actual bid rate at the current time step and is lower than the preset difference threshold, it indicates that the current floor price is still within the affordability of the demand side and there is a certain margin. Then, the negative feedback coefficient at the previous time step can be increased by a preset second step length to increase the floor price and realize the maximum value of the target ad space.

[0148] In summary, the embodiment of the present application provides an ad floor price adjustment method based on the Kalman filter iteration algorithm. By introducing the Kalman filter iteration algorithm into the dynamic floor price of the ad media, an ad dynamic floor price adjustment method with a negative feedback mechanism is established, and the target floor price information that can maximize the filling of ads in the target ad space and maximize the value of the target ad space can be obtained quickly.

[0149] The above introduced an ad floor price adjustment method provided by the embodiment of the present application. Next, the device for executing the above ad floor price adjustment method will be introduced.

[0150] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of an ad floor price adjustment device provided by the embodiment of the present application. As Figure 5 shown, the device may include:

[0151] A data acquisition module 501, configured to acquire advertising traffic information, demander device identification information, and transaction weighted price information of the current time step corresponding to a target ad slot, where the transaction weighted price information of the current time step is obtained based on the transaction price information of historical time steps and the transaction price information of the current time step, and the demander device identification information refers to the identification information of the device used by the demander who needs to purchase the target ad slot;

[0152] An initial reserve price generation module 502, configured to generate initial reserve price information according to the advertising traffic information and the demander device identification information;

[0153] An adjustment judgment module 503, configured to judge whether to adjust the initial reserve price information according to the transaction weighted price information of the current time step;

[0154] A first target reserve price generation module 504, configured to, when the adjustment judgment module determines not to adjust the initial reserve price information, determine the initial reserve price information as the target reserve price information for the demander to purchase the target ad slot at the current time step;

[0155] A second target reserve price generation module 505, configured to, when the adjustment judgment module determines to adjust the initial reserve price information, obtain the negative feedback coefficient of the current time step, and adjust the initial reserve price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step, so as to obtain the target reserve price information for the demander to purchase the target ad slot at the current time step.

[0156] In a possible implementation, the process of the adjustment judgment module judging whether to adjust the initial reserve price information according to the transaction weighted price information of the current time step may include:

[0157] Judge whether the transaction weighted price information of the current time step is greater than a preset transaction price threshold;

[0158] If so, determine to adjust the initial reserve price information, otherwise, determine not to adjust the initial reserve price information.

[0159] In a possible implementation, the determination process of the transaction price information of the current time step in the data acquisition module may include:

[0160] According to the transaction price information of historical time steps, obtain the target reserve price information for the demander to purchase the target ad slot at the previous time step, where the previous time step refers to the time step adjacent to the current time step in the forward direction, and the historical time steps include the previous time step;

[0161] Obtain the demander bid information of the current time step;

[0162] Judge whether the demander bid information of the current time step is greater than the target reserve price information for the demander to purchase the target ad slot at the previous time step;

[0163] If so, determine the transaction price information for the current time step according to the bid information of the demand side at the current time step.

[0164] In a possible implementation, the process by which the above-mentioned second target floor price generation module obtains the negative feedback coefficient for the current time step may include:

[0165] Obtain the actual bid rate for the current time step, the actual bid rate for the previous time step, the predicted bid rate for the previous time step, the negative feedback coefficient for the previous time step, and the Kalman gain for the current time step;

[0166] According to the actual bid rate for the previous time step, the predicted bid rate for the previous time step, the negative feedback coefficient for the previous time step, and the Kalman gain for the current time step, use the Kalman filter algorithm to obtain the target bid rate for the current time step;

[0167] According to the target bid rate for the current time step, the actual bid rate for the current time step, and the negative feedback coefficient for the previous time step, obtain the negative feedback coefficient for the current time step.

[0168] In a possible implementation, the process of obtaining the Kalman gain for the current time step in the above-mentioned second target floor price generation module includes:

[0169] Obtain the predicted bid rate variance for the previous time step and the Kalman gain for the previous time step, where if the previous time step is the first time step, both the predicted bid rate variance and the Kalman gain for the previous time step are preset values;

[0170] Determine the target bid rate variance for the previous time step according to the predicted bid rate variance for the previous time step and the Kalman gain for the previous time step;

[0171] Determine the predicted bid rate variance for the current time step according to the negative feedback coefficient for the previous time step and the target bid rate variance for the previous time step;

[0172] Determine the Kalman gain for the current time step according to the predicted bid rate variance for the current time step.

[0173] In a possible implementation, the process by which the above-mentioned second target floor price generation module obtains the negative feedback coefficient for the current time step according to the target bid rate for the current time step, the actual bid rate for the current time step, and the negative feedback coefficient for the previous time step may include:

[0174] Calculate the difference between the target bid rate for the current time step and the actual bid rate for the current time step;

[0175] If the difference is positive and the absolute value of the difference is greater than the preset difference threshold, the negative feedback coefficient of the previous time step is adjusted down according to the preset first step length to obtain the negative feedback coefficient of the current time step;

[0176] If the difference is negative and the absolute value of the difference is greater than the difference threshold, the negative feedback coefficient of the previous time step is increased according to the preset second step length to obtain the negative feedback coefficient of the current time step.

[0177] In a possible implementation, the second target reserve price generating module adjusts the initial reserve price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step, and the process of obtaining the target reserve price information when the demander purchases the target advertising space at the current time step may include:

[0178] Determine the reserve price adjustment amount information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step;

[0179] The reserve price adjustment amount information and the initial reserve price information are added together, and the sum is used as the target reserve price information when the demander purchases the target advertising space at the current time step.

[0180] The advertising floor price adjustment device provided in the embodiment of the present application corresponds to the advertising floor price adjustment method provided in the previous text. For details, please refer to the previous text introduction and will not be repeated here.

[0181] The present application also provides an electronic device in an embodiment. Figure 6 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0182] like Figure 6 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0183] Generally, the following devices can be connected to the I / O interface 605: input devices 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 can allow the electronic device to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 6 an electronic device with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices can be implemented or had.

[0184] An embodiment of the present application also provides a computer program product, including computer-readable instructions, which, when running on an electronic device, enable the electronic device to implement any one of the advertising floor price adjustment methods provided by the embodiments of the present application.

[0185] An embodiment of the present application also provides a computer-readable storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, they can enable the electronic device to implement any one of the advertising floor price adjustment methods provided by the embodiments of the present application.

[0186] In addition, it should be noted that the device embodiments described above are merely illustrative. 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 to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present application, the connection relationships between the modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines.

[0187] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware. Of course, it can also be implemented by dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. Generally, functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structures for implementing the same function can also be various, such as analog circuits, digital circuits or dedicated circuits, etc. However, for the present application, in more cases, software program implementation is a better implementation manner. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a readable storage medium, such as a floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disc of a computer, etc., and includes several instructions for causing a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in various embodiments of the present application.

[0188] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product.

[0189] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices. 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, computer, training device or data center to another website, computer, training device or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

Claims

1. An advertising floor price adjustment method, characterized in that, include: Acquire the advertisement flow information corresponding to the target advertisement position, the demander device identification information and the transaction weighted price information of the current time step, wherein the transaction weighted price information of the current time step is obtained according to the transaction price information of the historical time step and the transaction price information of the current time step, and the demander device identification information refers to the identification information of the device used by the demander who needs to purchase the target advertisement position; Generate initial reserve price information according to the advertisement flow information and the demand side device identification information; Determining whether to adjust the initial reserve price information according to the transaction weighted price information of the current time step; If not, the initial reserve price information is determined as the target reserve price information when the demander purchases the target advertising space at the current time step; If so, obtain the negative feedback coefficient of the current time step, adjust the initial reserve price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step, and obtain the target reserve price information when the demander purchases the target advertising space at the current time step.

2. The advertising floor price adjustment method according to claim 1, wherein The determining whether to adjust the initial reserve price information according to the transaction weighted price information of the current time step includes: Determining whether the transaction weighted price information at the current time step is greater than a preset transaction price threshold; If so, it is determined to adjust the initial reserve price information; otherwise, it is determined not to adjust the initial reserve price information.

3. The advertising floor price adjustment method according to claim 1, characterized in that The process of determining the transaction price information at the current time step includes: According to the transaction price information of the historical time step, the target reserve price information when the demander purchased the target advertising space in the previous time step is obtained, wherein the previous time step refers to the time step adjacent to the current time step, and the historical time step includes the previous time step; Get the demand side bidding information of the current time step; Determine whether the bid information of the demander at the current time step is greater than the target reserve price information when the demander purchased the target advertising space at the previous time step; If so, the transaction price information of the current time step is determined according to the demand side bidding information of the current time step.

4. The advertising floor price adjustment method according to any one of claims 1 to 3, characterized in that, The step of obtaining the negative feedback coefficient of the current time step includes: Get the actual bid rate of the current time step, the actual bid rate of the previous time step, the predicted bid rate of the previous time step, the negative feedback coefficient of the previous time step, and the Kalman gain of the current time step; According to the actual bid rate of the previous time step, the predicted bid rate of the previous time step, the negative feedback coefficient of the previous time step and the Kalman gain of the current time step, a Kalman filter algorithm is used to obtain a target bid rate of the current time step; The negative feedback coefficient of the current time step is obtained according to the target bid rate of the current time step, the actual bid rate of the current time step and the negative feedback coefficient of the previous time step.

5. The advertising floor price adjustment method according to claim 4, wherein The process of obtaining the Kalman gain of the current time step includes: Obtaining the predicted bid rate variance of the previous time step and the Kalman gain of the previous time step, wherein if the previous time step is the first time step, the predicted bid rate variance of the previous time step and the Kalman gain of the previous time step are both preset values; Determining a target bid rate variance for the previous time step according to the predicted bid rate variance for the previous time step and the Kalman gain for the previous time step; Determining a predicted bid rate variance at a current time step according to the negative feedback coefficient at the previous time step and the target bid rate variance at the previous time step; The Kalman gain of the current time step is determined according to the predicted bid rate variance of the current time step.

6. The advertising floor price adjustment method according to claim 4, wherein The step of obtaining the negative feedback coefficient of the current time step according to the target bid rate of the current time step, the actual bid rate of the current time step and the negative feedback coefficient of the previous time step includes: Calculating the difference between the target bid rate at the current time step and the actual bid rate at the current time step; If the difference is a positive value and the absolute value of the difference is greater than a preset difference threshold, the negative feedback coefficient of the previous time step is lowered according to the preset first step length to obtain the negative feedback coefficient of the current time step; If the difference is a negative value and the absolute value of the difference is greater than the difference threshold, the negative feedback coefficient of the previous time step is increased according to a preset second step size to obtain the negative feedback coefficient of the current time step.

7. The advertising floor price adjustment method according to claim 1, wherein The step of adjusting the initial reserve price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step to obtain the target reserve price information when the demander purchases the target advertising space at the current time step includes: Determining the reserve price adjustment amount information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step; The reserve price adjustment amount information and the initial reserve price information are added together, and the sum is used as the target reserve price information when the demander purchases the target advertising space at the current time step.

8. An advertising reserve price adjustment device, characterized in that include: A data acquisition module is used to acquire the advertisement flow information corresponding to the target advertisement position, the demander device identification information and the transaction weighted price information of the current time step, wherein the transaction weighted price information of the current time step is obtained according to the transaction price information of the historical time step and the transaction price information of the current time step, and the demander device identification information refers to the identification information of the device used by the demander who needs to purchase the target advertisement position; An initial reserve price generating module, used to generate initial reserve price information according to the advertisement flow information and the demand side device identification information; An adjustment judgment module, used to judge whether to adjust the initial reserve price information according to the transaction weighted price information of the current time step; A first target reserve price generating module, configured to determine the initial reserve price information as the target reserve price information when the demander purchases the target advertising space at the current time step when the adjustment judgment module determines that the initial reserve price information is not to be adjusted; The second target reserve price generating module is used for obtaining the negative feedback coefficient of the current time step when the adjustment judgment module determines to adjust the initial reserve price information, and adjusting the initial reserve price information according to the negative feedback coefficient of the current time step and the transaction weighted price information of the current time step to obtain the target reserve price information when the demander purchases the target advertising space at the current time step.

9. An electronic device, characterized in that, Comprising at least one processor and a memory connected to the processor, wherein: The memory is used for storing a computer program; The processor is used for executing the computer program so that the electronic device can implement the advertising floor price adjustment method described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the advertising floor price adjustment method described in any one of claims 1 to 7.

Images