Advertisement budget control method and device and electronic equipment

Abstract

The invention relates to the technical field of advertisements, in particular to an advertisement budget control method and device and electronic equipment. The method comprises the steps of obtaining theoretical total delivery consumption, a theoretical delivery consumption curve and an actual budget consumption curve of a target account in a current period; based on the theoretical total delivery consumption and a theoretical delivery consumption curve, determining theoretical delivery consumption accumulated by each resource niche in the already-passed delivery time period; based on the actual budget consumption curve, determining actual delivery consumption accumulated by each resource niche in the already-passed delivery time period; determining a bidding probability based on a difference value between the actual delivery consumption and the theoretical delivery consumption; and putting the advertisement of the target account in the resource niche of the unpassed putting time period according to the bidding probability.

Description

Technical Field

[0001] The present disclosure relates to the field of advertising technologies, and in particular, to an advertising budget control method, apparatus, and electronic device. Background Art

[0002] Currently, during the process of advertising placement, users need to spend a limited budget on appropriate traffic to achieve a good advertising conversion rate.

[0003] However, during the process of advertising placement, it often occurs that even if the budget is spent on appropriate traffic, the accuracy of the advertisement push is low, thereby resulting in a low advertising conversion rate.

[0004] Therefore, how to ensure the accuracy of the advertisement push during the advertising placement process to improve the advertising conversion rate has become an urgent problem to be solved. Summary of the Invention

[0005] To solve the above technical problems, the present disclosure provides an advertising budget control method, apparatus, and electronic device.

[0006] The technical solution of the present disclosure is as follows:

[0007] In a first aspect, the present disclosure provides an advertising budget control method, including: obtaining the theoretical total placement consumption, theoretical placement consumption curve, and actual budget consumption curve of a target account in the current period; where the current period includes at least one placement time period, the theoretical placement consumption curve is obtained by fitting based on the historical data of the target account, and the historical data includes the historical placement consumption of resource positions at different placement locations, and the historical placement parameters of each resource position in each period, and the historical placement parameters include one or more of placement cost, return on investment, and secondary retention rate; determining the cumulative theoretical placement consumption of each resource position in the passed placement time periods based on the theoretical total placement consumption and the theoretical placement consumption curve; determining the cumulative actual placement consumption of each resource position in the passed placement time periods based on the actual budget consumption curve; determining a bidding probability based on the difference value between the actual placement consumption and the theoretical placement consumption; and placing the advertisement of the target account in the resource positions of the unpassed placement time periods according to the bidding probability.

[0008] Second aspect, the present disclosure provides an advertising budget control device, including: an acquisition unit configured to acquire the theoretical total delivery consumption, the theoretical delivery consumption curve, and the actual budget consumption curve of a target account in a current period; wherein the current period includes at least one delivery time period, the theoretical delivery consumption curve is obtained by fitting based on the historical data of the target account, and the historical data includes the historical delivery consumption of resource positions at different delivery positions, and the historical delivery parameters of each resource position in each period, and the historical delivery parameters include one or more of delivery cost, return on investment, and secondary retention rate; a processing unit configured to determine the cumulative theoretical delivery consumption of each resource position in the elapsed delivery time period based on the theoretical total delivery consumption and the theoretical delivery consumption curve acquired by the acquisition unit; the processing unit is further configured to determine the cumulative actual delivery consumption of each resource position in the elapsed delivery time period based on the actual budget consumption curve acquired by the acquisition unit; the processing unit is further configured to determine a bidding probability based on the difference value between the actual delivery consumption and the theoretical delivery consumption; the processing unit is further configured to deliver the advertisement of the target account to the resource positions in the unelapsed delivery time period according to the bidding probability.

[0009] Third aspect, the present disclosure provides an electronic device, including: a memory and a processor, the memory is configured to store a computer program; the processor is configured to, when executing the computer program, enable the electronic device to implement the advertising budget control method according to any one of the second aspect.

[0010] Fourth aspect, the present invention provides a computer-readable storage medium, including: a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to implement the advertising budget control method according to any one of the second aspect.

[0011] Fifth aspect, the present invention provides a computer program product, when the computer program product runs on a computer, enabling the computer to execute the advertising budget control method according to any one of the second aspect.

[0012] It should be noted that the above computer instructions can be stored in whole or in part on a first computer-readable storage medium. Wherein, the first computer-readable storage medium can be packaged together with the processor of the electronic device, or can be packaged separately from the processor of the electronic device, and the present disclosure does not make a limitation in this regard.

[0013] The descriptions of the second aspect, the third aspect, the fourth aspect, and the fifth aspect in the present disclosure can refer to the detailed description of the first aspect; and, for the beneficial effects of the descriptions of the second aspect, the third aspect, the fourth aspect, and the fifth aspect, reference can be made to the analysis of the beneficial effects of the first aspect, and details are not described herein again.

[0014] In the present disclosure, the names of the above-mentioned electronic devices do not constitute a limitation to the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear under other names. As long as the functions of each device or functional module are similar to those of the present disclosure and fall within the scope of the claims of the present disclosure and equivalent technologies.

[0015] These aspects or other aspects of the present disclosure will be made more concise and understandable in the following description.

[0016] The advertising budget control method provided by the present disclosure includes: obtaining the theoretical total delivery consumption, theoretical delivery consumption curve, and actual budget consumption curve of a target account in the current period; then, based on the theoretical total delivery consumption and the theoretical delivery consumption curve, determining the cumulative theoretical delivery consumption of each resource position in the elapsed delivery time period (time dimension); at the same time, based on the actual budget consumption curve, determining the cumulative actual delivery consumption of each resource position in the elapsed delivery time period; then, based on the difference value between the actual delivery consumption and the theoretical delivery consumption, determining the bidding probability. Finally, advertising of the target account is placed in the resource positions of the unelapsed delivery time period according to the bidding probability. It can be seen that the bidding probability of the advertising placed by the target account in the resource positions of different delivery positions (space dimension) is adjusted according to the actual delivery consumption and the theoretical delivery consumption of the resource positions at different delivery positions. Since the bidding probability can adjust the exposure of the advertising placed by the target account, the theoretical total delivery consumption of the target account and the advertising conversion rate of the advertising placed by the target account can be controlled. At the same time, since both the actual delivery consumption and the theoretical delivery consumption consider the influence of the resource positions at different delivery positions on the advertising delivery data (i.e., time + space dimension), avoiding the situation where the influencing factor is only a single time dimension, making the loss assessment of the advertising budget more accurate and solving the problem of how to ensure the advertising conversion rate during the advertising delivery process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present disclosure and used together with the specification to explain the principles of the present disclosure.

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 FIG. 1 is one of the flow diagrams of the advertising budget control method provided by the embodiments of the present disclosure;

[0020] Figure 2 FIG. 2 is a schematic diagram of the delivery time period and delivery consumption in the prior art;

[0021] Figure 3 It is a schematic diagram of the three elements of the placement time period, resource position, and placement consumption in the advertising budget control method provided by the embodiments of the present disclosure;

[0022] Figure 4 It is a schematic diagram of the architecture of the server for the advertising budget control method provided by the embodiments of the present disclosure;

[0023] Figure 5 It is the second schematic diagram of the process flow of the advertising budget control method provided by the embodiments of the present disclosure;

[0024] Figure 6 It is the third schematic diagram of the process flow of the advertising budget control method provided by the embodiments of the present disclosure;

[0025] Figure 7 It is the fourth schematic diagram of the process flow of the advertising budget control method provided by the embodiments of the present disclosure;

[0026] Figure 8 It is the fifth schematic diagram of the process flow of the advertising budget control method provided by the embodiments of the present disclosure;

[0027] Figure 9 It is the sixth schematic diagram of the process flow of the advertising budget control method provided by the embodiments of the present disclosure;

[0028] Figure 10 It is the seventh schematic diagram of the process flow of the advertising budget control method provided by the embodiments of the present disclosure;

[0029] Figure 11 It is a schematic diagram of the structure of the advertising budget control device provided by the embodiments of the present disclosure;

[0030] Figure 12 It is a schematic diagram of the structure of the server provided by the embodiments of the present disclosure;

[0031] Figure 13 It is a schematic diagram of the structure of a computer program product for an advertising budget control method provided by the embodiments of the present disclosure. Detailed implementation manners

[0032] In order to be able to more clearly understand the above-mentioned objects, features, and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0033] Many specific details are set forth in the following description in order to provide a thorough understanding of the present disclosure, but the present disclosure may be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all of the embodiments.

[0034] The display device provided by the embodiments of the present disclosure can have various implementation forms. For example, it can be a television, a smart TV, a laser projection device, a monitor, an electronic bulletin board, an electronic table, etc. Figure 1 and Figure 5 is a specific implementation manner of the display device of the present disclosure.

[0035] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0036] In some examples, the bidding probability provided by the embodiments of the present disclosure refers to the possibility for an advertiser to win a display opportunity during the advertising bidding process.

[0037] In some examples, the secondary retention rate provided by the embodiments of the present disclosure is an indicator for measuring user retention in the context of an advertising and marketing campaign. It refers to the secondary retention rate of users attracted through an advertising channel after they have contacted the advertisement and first used the product. The calculation method is similar to that of the secondary retention rate of a general product, that is, the advertising secondary retention rate = (the number of users who still use the product on the second day among the new users attracted on the first day through the advertisement / the number of new users attracted on the first day through the advertisement) × 100%.

[0038] Exemplarily, taking the execution subject of the advertising budget control method provided by the embodiments of the present disclosure as a server as an example, the advertising budget control method provided by the embodiments of the present disclosure will be described.

[0039] In some examples, the wavelet smoothing process provided by the embodiments of the present disclosure is a signal or data smoothing process method based on wavelet transform.

[0040] In some examples, the elapsed delivery time period provided by the embodiments of the present disclosure refers to the delivery time period before the current delivery time period; for example, if the current delivery time period is from 09:27:00 on February 8, 2025 to 09:37:00 on February 8, 2025, then the delivery time period before the current delivery time period is the delivery time period before 09:27:00 on February 8, 2025; similarly, the unelapsed delivery time period refers to the delivery time period after the current delivery time period, for example, if the current delivery time period is from 09:27:00 on February 8, 2025 to 09:37:00 on February 8, 2025, then the delivery time period after the current delivery time period is the delivery time period after 09:37:00 on February 8, 2025.

[0041] Figure 1 is a flowchart of an advertising budget control method shown according to an exemplary embodiment, such as Figure 1 shown, including: S11 - S15.

[0042] S11. Obtain the theoretical total delivery consumption, theoretical delivery consumption curve, and actual budget consumption curve of the target account in the current period. Wherein, the current period includes at least one delivery time period, the theoretical delivery consumption curve is obtained by fitting based on the historical data of the target account, and the historical data includes the historical delivery consumption of resource positions at different delivery positions, and the historical delivery parameters of each resource position in each period, and the historical delivery parameters include one or more of delivery cost, return on investment (ROI), and secondary retention rate.

[0043] In some examples, the theoretical total delivery consumption is equal to the budget value for the target account to deliver advertisements in the current period.

[0044] In some examples, the actual budget consumption curve is drawn based on the cumulative delivery consumption of each resource position in the elapsed delivery time period.

[0045] In some examples, the resource positions at different delivery positions include resource positions at different display positions on the same page (such as the home page of an application (APP), a certain-level playback page, etc.), and / or resource positions at different display positions on different pages.

[0046] S12. Based on the theoretical total delivery consumption and the theoretical delivery consumption curve, determine the cumulative theoretical delivery consumption of each resource position in the elapsed delivery time period.

[0047] In some examples, when calculating the theoretical delivery consumption, the expected budget consumption of each resource position of the target account in each delivery time period of the current cycle can be determined based on the theoretical total delivery consumption and the theoretical delivery consumption curve; based on the expected budget consumption, the cumulative theoretical delivery consumption of each resource position in the elapsed delivery time period can be determined.

[0048] Alternatively, the theoretical total delivery consumption and the theoretical delivery consumption curve are input into an accumulation model for calculation to determine the cumulative theoretical delivery consumption of each resource position in the elapsed delivery time period. Among them, the training process of the accumulation model includes:

[0049] Obtain the first training sample data and the first labeling result of the first training sample data. Among them, the first training sample data includes the historical total delivery consumption and the historical delivery consumption curve, and the first labeling result includes the cumulative historical delivery consumption of each resource position of the historical account corresponding to each historical total delivery consumption and the historical delivery consumption curve in the elapsed delivery time period.

[0050] Input the first training sample data into the first neural network model for learning to obtain the first prediction result of the first neural network model for the first training sample data.

[0051] Based on the first prediction result and the first labeling result, adjust the network parameters of the first neural network model until the first neural network model converges to obtain the accumulation model.

[0052] S13. Based on the actual budget consumption curve, determine the cumulative actual delivery consumption of each resource position in the elapsed delivery time period.

[0053] In some examples, after the target account places the advertisement on the resource positions at different locations, if the user clicks on the advertisement at this resource position, it means that the advertisement has been converted once. At this time, the server will increment the conversion count of the advertisement by 1. Then, the server based on the conversion count of the advertisement in the resource positions at different locations in each delivery time period, thereby obtaining the actual delivery consumption of this resource position, such as: the sum of the actual advertisement delivery values generated by the resource positions where the advertisement of the target account has been placed in the currently delivered delivery time period, such as: the actual advertisement delivery value can be the product of the total number of times the user clicks on the advertisement of the target account and a preset value.

[0054] S14. Based on the difference value between the actual delivery consumption and the theoretical delivery consumption, determine the bidding probability.

[0055] In some examples, the server can query a preset relationship table based on the difference between the actual delivery consumption and the theoretical delivery consumption to obtain the bidding probability.

[0056] Exemplarily, the preset relationship table is shown in Table 1.

[0057] Table 1

[0058] Difference Bidding probability Difference 1 Bidding probability 1 Difference 2 Bidding probability 2

[0059] Thus, when the server determines that the difference between the actual delivery consumption and the theoretical delivery consumption is difference 1, by querying Table 1, it can be known that the bidding probability is bidding probability 1.

[0060] In some examples, the actual delivery consumption and the theoretical delivery consumption can be input into the bidding probability formula to obtain the bidding probability. For example, the bidding probability f is equal to P * (the current actual delivery consumption - the current theoretical delivery consumption) + D * (the current actual delivery consumption - the previous actual delivery consumption). Where P and D are real numbers. S15. Place the advertisement of the target account in the resource positions in the next delivery time period according to the bidding probability.

[0061] In some examples, the architecture of the server to which the advertising budget control method provided by the embodiments of the present disclosure is applied is as Figure 4 shown, including an offline calculation module, a real-time calculation module, and an advertisement display module. Among them, the offline calculation module includes a consumption sub-module and a budget sub-module, the real-time calculation module includes a data collection sub-module and an adjustment sub-module, and the advertisement display module includes a cache sub-module and a display sub-module.

[0062] In some examples, after the budget sub-module obtains the theoretical total delivery consumption of the target account in the current period, it can input the theoretical total delivery consumption into the consumption sub-module. Then, the consumption sub-module determines the cumulative theoretical delivery consumption of each resource position in the passed delivery time period based on the theoretical total delivery consumption and the theoretical delivery consumption curve. At the same time, the data collection sub-module adopts a distributed stream processing platform (such as: Kafka), so that it can determine the cumulative actual delivery consumption of each resource position in the passed delivery time period based on the actual budget consumption curve, and send the actual delivery consumption to the adjustment sub-module. Then, the consumption sub-module sends the theoretical delivery consumption to the adjustment sub-module of the real-time calculation module. The adjustment sub-module determines the bidding probability based on the actual delivery consumption and the theoretical delivery consumption, and sends the bidding probability to the cache sub-module. The display sub-module places the advertisement of the target account in the resource positions in the next delivery time period according to the bidding probability in the cache sub-module.

[0063] S15. Place the advertisement of the target account in the resource positions in the unpassed delivery time period according to the bidding probability.

[0064] In some examples, in the prior art, when calculating the bidding probability, it is only calculated based on the delivery consumption of the target account in different delivery time periods, resulting in a problem of low accuracy in the loss assessment of the advertising budget, such as: such as Figure 2As shown, since the prior art only considers the advertising consumption of the target account in different advertising periods to calculate the bidding probability, only the total advertising consumption of the target account in the advertising period is counted when calculating the advertising loss. In order to meet the evaluation parameters of the target account, the advertising consumption in the unpassed advertising periods will be continuously increased, resulting in more ineffective advertisements and a lower actual advertisement conversion rate. However, for the advertising budget control method provided by the embodiments of the present disclosure, when calculating the actual advertising consumption and the theoretical advertising consumption, the influence of the resource positions at different advertising positions on the advertising data (i.e., the time + space dimension) is considered, avoiding the situation where the influencing factor is only a single time dimension, and making the loss evaluation of the advertising budget more accurate. For example Figure 3 As shown, taking resource position 1 as an example, when the target account advertises in resource position 1, the difference value between the theoretical advertising consumption and the actual advertising consumption in advertising period 1 of resource position 1 is calculated to determine the bidding probability 1. Then, in advertising period 2 of resource position 1, the advertisement of the target account is placed according to the bidding probability 1. At this time, it can be seen that the actual advertising consumption of the target account in advertising period 2 of resource position 1 has increased significantly, which may result in more ineffective advertisements and a lower actual advertisement conversion rate. At this time, by calculating the difference value between the theoretical advertising consumption and the actual advertising consumption in advertising period 2 of resource position 1, the bidding probability 2 is determined. Then, in advertising period 3 of resource position 1, the advertisement of the target account is placed according to the bidding probability 2. At this time, it can be seen that the actual advertising consumption of the target account in advertising period 2 of resource position 1 has decreased significantly, thereby reducing the exposure rate of the advertisements placed by the target account. While reducing the actual advertising consumption, the advertisement conversion rate can be guaranteed. Therefore, the influence of the resource positions at different advertising positions on the advertising data (i.e., the time + space dimension) can be combined, avoiding the situation where the influencing factor is only a single time dimension, and making the loss evaluation of the advertising budget more accurate.

[0065] As can be seen from the above, for the advertising budget control method provided by the embodiments of the present disclosure, the bidding probability of the advertisement placed by the target account on the resource positions at different advertising positions (space dimension) is adjusted according to the actual advertising consumption and the theoretical advertising consumption. Since the bidding probability can be adjusted to affect the exposure of the advertisement placed by the target account, the theoretical total advertising consumption of the target account and the advertisement conversion rate of the advertisement placed by the target account can be controlled. At the same time, since both the actual advertising consumption and the theoretical advertising consumption consider the influence of the resource positions at different advertising positions on the advertising data (i.e., the time + space dimension), avoiding the situation where the influencing factor is only a single time dimension, the loss evaluation of the advertising budget is made more accurate.

[0066] In some feasible examples, in combination with Figure 1 , such as Figure 5 As shown, the above S12 can be specifically implemented by the following S120 and S121.

[0067] S120. Based on the theoretical total delivery consumption and the theoretical delivery consumption curve, determine the expected budget consumption of each resource position of the target account in each delivery time period of the current cycle.

[0068] In some examples, when calculating the theoretical delivery consumption, based on the theoretical total delivery consumption, the expected budget consumption of each resource position in each delivery time period can be determined. Take the expected budget consumption as the theoretical delivery consumption. At this time, although the theoretical delivery consumption of each resource position in each delivery time period is a fixed value, it can greatly reduce the occupation of computing resources, thereby improving the user experience.

[0069] Alternatively, based on the theoretical total delivery consumption, determine the expected budget consumption of each resource position in each delivery time period. Based on the expected budget consumption, determine the cumulative theoretical delivery consumption of each resource position in the passed delivery time periods.

[0070] In some examples, PID operations can be performed based on the theoretical budget consumption (i.e., the theoretical consumption of the resource position in a delivery time period), the expected budget consumption, and the evaluation parameters of each resource position to determine the theoretical delivery consumption of each resource position in each delivery time period.

[0071] In some examples, the theoretical budget consumption, the expected budget consumption, and the evaluation parameters can be input into a dynamic allocation model to determine the theoretical delivery consumption of each resource position in each delivery time period. Among them, the training process of the dynamic allocation model includes:

[0072] Obtain the third training sample data and the third labeling result of the third training sample data. Among them, the third training sample data includes historical training parameters, and the third labeling result includes the theoretical delivery consumption of each resource position in each delivery time period corresponding to the historical training parameters. The historical training parameters include the historical theoretical budget consumption, the expected budget consumption, and the evaluation parameter input.

[0073] Input the third training sample data into the third neural network model for learning to obtain the third prediction result of the third neural network model for the third training sample data.

[0074] Based on the third prediction result and the third labeling result, adjust the network parameters of the third neural network model until the third neural network model converges to obtain the dynamic allocation model.

[0075] S121. Based on the expected budget consumption, determine the cumulative theoretical delivery consumption of each resource position in the passed delivery time periods.

[0076] In some examples, the theoretical delivery consumption is equal to the sum of the expected budget consumptions corresponding to the resource positions where the advertisements of the target account have been delivered during the currently delivered delivery time period.

[0077] As can be seen from the above, the advertisement budget control method provided by the embodiments of the present disclosure includes obtaining the theoretical total delivery consumption, the theoretical delivery consumption curve, and the actual budget consumption curve of the target account in the current cycle; then, based on the theoretical total delivery consumption and the theoretical delivery consumption curve, determining the expected budget consumption of each resource position of the target account in each delivery time period in the current cycle; based on the expected budget consumption, determining the accumulated theoretical delivery consumption of each resource position in the passed delivery time period; at the same time, based on the actual budget consumption curve, determining the accumulated actual delivery consumption of each resource position in the passed delivery time period; then, based on the difference value between the actual delivery consumption and the theoretical delivery consumption, determining the bidding probability; in this way, the bidding probability of the advertisement of the target account can be adjusted based on the actual delivery consumption and the theoretical delivery consumption in the resource position, and further, the display probability of the advertisement of the target account in the resource position can be dynamically adjusted. Finally, the advertisement of the target account is delivered in the resource position of the unpassed delivery time period according to the bidding probability. It can be seen that the bidding probability of the advertisement delivered by the target account in the resource positions at different delivery positions (spatial dimension) is adjusted according to the actual delivery consumption and the theoretical delivery consumption. Since the bidding probability can adjust the exposure of the advertisement delivered by the target account, the theoretical total delivery consumption of the target account and the advertisement conversion rate of the advertisement delivered by the target account can be controlled. At the same time, since both the actual delivery consumption and the theoretical delivery consumption consider the influence of the resource positions at different delivery positions on the advertisement delivery data (i.e., time + spatial dimension), avoiding the influence factor being only a single time dimension, making the loss assessment of the advertisement budget more accurate.

[0078] In some feasible examples, in combination with Figure 5 , as Figure 6 shown, the advertisement budget control method provided by the embodiments of the present disclosure further includes S16, and the above S120 can be specifically implemented by the following S1200-S1202.

[0079] S16. Obtain the assessment parameters of the target account in the current cycle. Among them, the assessment parameters include one or more of the delivery cost, the return on investment, and the secondary retention rate.

[0080] In some examples, the assessment parameter is set by the target account itself in the current period. For example, when the target account requires the secondary retention rate in the current period to be greater than the secondary retention threshold, the assessment parameter can be set to the secondary retention rate; or, when the target account requires the advertising cost in the current period to be lower than the cost threshold, the assessment parameter can be set to the advertising cost; or, when the target account requires the return on investment in the current period to be greater than the return threshold, the assessment parameter can be set to the return on investment. In this way, the target account can set the assessment parameter based on actual needs.

[0081] S1200. Determine the theoretical advertising consumption curve corresponding to the assessment parameter based on the assessment parameter. Among them, different theoretical advertising consumption curves correspond to different assessment parameters.

[0082] In some examples, for the advertising budget control method provided by the embodiments of the present disclosure, by obtaining the historical data of different assessment parameters, and then fitting the historical data, the theoretical advertising consumption curve for the next period corresponding to the assessment parameter is generated. For example, when the assessment parameter is any one of the advertising cost, return on investment, and secondary retention rate, at this time, the historical parameters include the historical advertising consumption of the resource positions of the target account at different advertising positions, and the assessment parameter of each resource position in each period. Then, by fitting the historical advertising consumption of the resource positions at different advertising positions and the assessment parameter of each resource position in each period, the predicted advertising consumption curve corresponding to the assessment parameter is obtained. For example, when the assessment parameter is the advertising cost, at this time, the historical parameters include the historical advertising consumption of the resource positions of the target account at different advertising positions, and the advertising cost of each resource position in each period. Then, by fitting the historical advertising consumption of the resource positions at different advertising positions and the advertising cost of each resource position in each period, the predicted advertising consumption curve corresponding to the advertising cost is obtained.

[0083] Similarly, when the assessment parameter is multiple of the advertising cost, return on investment, and secondary retention rate, at this time, the historical parameters include the historical advertising consumption of the resource positions of the target account at different advertising positions, and the assessment parameter of each resource position in each period. Then, by fitting the historical advertising consumption of the resource positions at different advertising positions and the assessment parameter of each resource position in each period, the predicted advertising consumption curve corresponding to the assessment parameter is obtained. For example, when the assessment parameter is the advertising cost and the return on investment, at this time, the historical parameters include the historical advertising consumption of the resource positions of the target account at different advertising positions, and the advertising cost and return on investment of each resource position in each period. Then, by fitting the historical advertising consumption of the resource positions at different advertising positions and the advertising cost and return on investment of each resource position in each period, the predicted advertising consumption curve corresponding to the advertising cost and return on investment is obtained.

[0084] In this way, the server can pre-store the predicted delivery consumption curves corresponding to different evaluation parameters in the memory.

[0085] Exemplarily, when the evaluation parameter is one or more of the delivery cost, return on investment, and secondary retention rate, the corresponding relationship between the pre-stored predicted delivery consumption curve and the evaluation parameter is shown in Table 2.

[0086] Table 2

[0087] Assessment parameter Predicted delivery consumption curve Delivery cost Predicted delivery consumption curve 1 Return on investment Predicted delivery consumption curve 2 Secondary retention rate Predicted delivery consumption curve 3 Delivery cost, return on investment Predicted delivery consumption curve 4 Delivery cost, secondary retention rate Predicted delivery consumption curve 5 Return on investment, secondary retention rate Predicted delivery consumption curve 6 Delivery cost, return on investment, secondary retention rate Predicted delivery consumption curve 7

[0088] At this time, if the evaluation parameter is the delivery cost, the server can determine, by querying Table 2, that the predicted delivery consumption curve corresponding to the evaluation parameter delivery cost is the predicted delivery consumption curve 1. Then the server takes the predicted delivery consumption curve 1 as the theoretical delivery consumption curve corresponding to the evaluation parameter delivery cost.

[0089] S1201. Determine the delivery ratio of each resource position in each delivery time period based on the theoretical delivery consumption curve corresponding to the evaluation parameter.

[0090] In some examples, when determining the delivery ratio of each resource position in each delivery time period based on the theoretical delivery consumption curve corresponding to the evaluation parameter, the first consumption ratio of each resource position can be determined based on the theoretical delivery consumption curve corresponding to the evaluation parameter; the second consumption ratio of each resource position in each delivery time period can be determined based on the theoretical delivery consumption curve corresponding to the evaluation parameter; and the delivery ratio of each resource position in each delivery time period can be determined based on the first consumption ratio and the second consumption ratio.

[0091] In some examples, when the delivery ratio is equal to the product of the first consumption ratio and the second consumption ratio of the resource position, and the evaluation parameter includes the delivery cost, the historical parameters at this time include the historical delivery consumption of the resource positions at different delivery positions of the target account, and the delivery cost of each resource position in each period. Then, based on the ratio of the sum of the historical delivery consumptions of each resource position at different delivery positions, the first consumption ratio of each resource position is determined. At the same time, based on the ratio of the sum of the delivery costs of each resource position in each delivery time period at different delivery positions, the second consumption ratio of each resource position in each delivery time period is determined. Then, based on the first consumption ratio and the second consumption ratio, the delivery ratio of each resource position in each delivery time period is determined. For example: The delivery time periods included in the current period include 3 time periods, namely delivery time period 1, delivery time period 2, and delivery time period 3. The resource positions that the target account has delivered to include resource position 1, resource position 2, and resource position 3. The sum of the historical delivery consumptions of resource position 1 is 1, the sum of the historical delivery consumptions of resource position 2 is 2, the sum of the historical delivery consumptions of resource position 3 is 3, and the sum of the delivery costs of resource position 1 in delivery time period 1 is equal to The sum of the placement costs of Resource Slot 1 during Placement Time Period 2 is equal to The sum of the placement costs of Resource Slot 1 during Placement Time Period 3 is equal to The sum of the placement costs of Resource Slot 2 during Placement Time Period 1 is equal to The sum of the placement costs of Resource Slot 2 during Placement Time Period 2 is equal to The sum of the placement costs of Resource Slot 2 during Placement Time Period 3 is equal to The sum of the placement costs of Resource Slot 3 during Placement Time Period 1 is equal to The sum of the placement costs of Resource Slot 3 during Placement Time Period 2 is equal to The sum of the placement costs of Resource Slot 3 during Placement Time Period 3 is equal to Thus, it can be determined that the first consumption ratios of Resource Slot 1, Resource Slot 2, and Resource Slot 3 are 1:2:3. The second consumption ratios of Resource Slot 1 during Placement Time Period 1, Placement Time Period 2, and Placement Time Period 3 are 1:2:3. The second consumption ratios of Resource Slot 2 during Placement Time Period 1, Placement Time Period 2, and Placement Time Period 3 are 2:1:3. The second consumption ratios of Resource Slot 3 during Placement Time Period 1, Placement Time Period 2, and Placement Time Period 3 are 3:1:2. In this way, the placement ratio of Resource Slot 1 during Placement Time Period 1 is The placement ratio of Resource Slot 1 during Placement Time Period 2 is The placement ratio of Resource Slot 1 during Placement Time Period 3 is The placement ratio of Resource Slot 2 during Placement Time Period 1 is The placement ratio of Resource Slot 2 during Placement Time Period 2 is The placement ratio of Resource Slot 2 during Placement Time Period 3 is The placement ratio of Resource Slot 3 during Placement Time Period 1 is The placement ratio of Resource Slot 3 during Placement Time Period 2 is The placement ratio of Resource Slot 3 during Placement Time Period 3 is

[0092] In some examples, when the placement ratio is equal to the product of the first consumption ratio and the second consumption ratio of the resource position, and the evaluation parameter includes the return on investment, the historical parameters at this time include the historical placement consumption of the resource positions at different placement positions of the target account, and the return on investment of each resource position in each period. Then, based on the ratio of the sum of the historical placement consumptions of each resource position at different placement positions, the first consumption ratio of each resource position is determined. At the same time, based on the ratio of the sum of the return on investments of each resource position at different placement positions in each placement time period, the second consumption ratio of each resource position in each placement time period is determined. Then, based on the first consumption ratio and the second consumption ratio, the placement ratio of each resource position in each placement time period is determined. For example: The placement time periods included in the current period include 3 time periods, namely placement time period 1, placement time period 2, and placement time period 3. The resource positions that the target account has placed on include resource position 1, resource position 2, and resource position 3. The sum of the historical placement consumptions of resource position 1 is 1, the sum of the historical placement consumptions of resource position 2 is 2, and the sum of the historical placement consumptions of resource position 3 is 3. The sum of the return on investments of resource position 1 in placement time period 1 is equal to The sum of the return on investments of resource position 1 in placement time period 2 is equal to The sum of the return on investments of resource position 1 in placement time period 3 is equal to The sum of the return on investments of resource position 2 in placement time period 1 is equal to The sum of the return on investments of resource position 2 in placement time period 2 is equal to The sum of the return on investments of resource position 2 in placement time period 3 is equal to The sum of the return on investments of resource position 3 in placement time period 1 is equal to The sum of the return on investments of resource position 3 in placement time period 2 is equal to The sum of the return on investments of resource position 3 in placement time period 3 is equal to Thus, the first consumption ratios of resource position 1, resource position 2, and resource position 3 can be determined to be 1:2:3. The second consumption ratios of resource position 1 in placement time period 1, placement time period 2, and placement time period 3 are 1:2:3. The second consumption ratios of resource position 2 in placement time period 1, placement time period 2, and placement time period 3 are 2:1:3. The second consumption ratios of resource position 3 in placement time period 1, placement time period 2, and placement time period 3 are 3:1:2. In this way, the placement ratio of resource position 1 in placement time period 1 can be determined to be The placement ratio of resource position 1 in placement time period 2 is The placement ratio of resource position 1 in placement time period 3 is The placement ratio of resource position 2 in placement time period 1 is The placement ratio of resource position 2 in placement time period 2 is The placement ratio of resource position 2 in placement time period 3 is The placement ratio of resource slot 3 during placement time period 1 is The placement ratio of resource slot 3 during placement time period 2 is The placement ratio of resource slot 3 during placement time period 3 is

[0093] In some examples, when the placement ratio is equal to the product of the first consumption ratio and the second consumption ratio of the resource slot, and the evaluation parameter includes the secondary retention rate, the historical parameters at this time include the historical placement consumption of the resource slots at different placement positions of the target account, and the secondary retention rate of each resource slot in each period. Then, based on the ratio of the sum of the historical placement consumptions of each resource slot at different placement positions, the first consumption ratio of each resource slot is determined. At the same time, based on the ratio of the sum of the secondary retention rates of each resource slot at different placement positions in each placement time period, the second consumption ratio of each resource slot in each placement time period is determined. Then, based on the first consumption ratio and the second consumption ratio, the placement ratio of each resource slot in each placement time period is determined. For example: The placement time periods included in the current period include 3 time periods, namely placement time period 1, placement time period 2, and placement time period 3. The resource slots placed by the target account include resource slot 1, resource slot 2, and resource slot 3. The sum of the historical placement consumptions of resource slot 1 is 1, the sum of the historical placement consumptions of resource slot 2 is 2, and the sum of the historical placement consumptions of resource slot 3 is 3. The sum of the secondary retention rates of resource slot 1 during placement time period 1 is equal to The sum of the secondary retention rates of resource slot 1 during placement time period 2 is equal to The sum of the secondary retention rates of resource slot 1 during placement time period 3 is equal to The sum of the secondary retention rates of resource slot 2 during placement time period 1 is equal to The sum of the secondary retention rates of resource slot 2 during placement time period 2 is equal to The sum of the secondary retention rates of resource slot 2 during placement time period 3 is equal to The sum of the return on investment rates of resource slot 3 during placement time period 1 is equal to The sum of the secondary retention rates of resource slot 3 during placement time period 2 is equal to The sum of the secondary retention rates of resource slot 3 during placement time period 3 is equal to Thus, the first consumption ratios of resource slot 1, resource slot 2, and resource slot 3 can be determined to be 1:2:3. The second consumption ratios of resource slot 1 during placement time periods 1, 2, and 3 are 1:2:3. The second consumption ratios of resource slot 2 during placement time periods 1, 2, and 3 are 2:1:3. The second consumption ratios of resource slot 3 during placement time periods 1, 2, and 3 are 3:1:2. In this way, the placement ratio of resource slot 1 during placement time period 1 can be determined to be The placement ratio of resource slot 1 during placement time period 2 is The delivery ratio of resource slot 1 during the delivery time period 3 is The delivery ratio of resource slot 2 during the delivery time period 1 is The delivery ratio of resource slot 2 during the delivery time period 2 is The delivery ratio of resource slot 2 during the delivery time period 3 is The delivery ratio of resource slot 3 during the delivery time period 1 is The delivery ratio of resource slot 3 during the delivery time period 2 is The delivery ratio of resource slot 3 during the delivery time period 3 is

[0094]

[0095] In some examples, when the delivery ratio is equal to the product of the first consumption ratio and the second consumption ratio of the resource slot, and the evaluation parameters include the delivery cost and the return on investment, the historical parameters at this time include the historical delivery consumption of the resource slots at different delivery positions of the target account, as well as the delivery cost and the return on investment of each resource slot in each period. Then, based on the ratio of the sum of the historical delivery consumptions of each resource slot at different delivery positions, the first consumption ratio of each resource slot is determined. At the same time, based on the ratio of the sum of the delivery cost and the return on investment of each resource slot at each delivery time period at different delivery positions, the second consumption ratio of each resource slot in each delivery time period is determined. Then, based on the first consumption ratio and the second consumption ratio, the delivery ratio of each resource slot in each delivery time period is determined. For example: The delivery time periods included in the current period are 3 time periods, namely delivery time period 1, delivery time period 2, and delivery time period 3. The resource slots that the target account has delivered include resource slot 1, resource slot 2, and resource slot 3. The sum of the historical delivery consumptions of resource slot 1 is 1, the sum of the historical delivery consumptions of resource slot 2 is 2, and the sum of the historical delivery consumptions of resource slot 3 is 3. The sum of the delivery costs of resource slot 1 during the delivery time period 1 is equal to The sum of the delivery costs of resource slot 1 during the delivery time period 2 is equal to The sum of the delivery costs of resource slot 1 during the delivery time period 3 is equal to The sum of the delivery costs of resource slot 2 during the delivery time period 1 is equal to The sum of the delivery costs of resource slot 2 during the delivery time period 2 is equal to The sum of the delivery costs of resource slot 2 during the delivery time period 3 is equal to The sum of the delivery costs of resource slot 3 during the delivery time period 1 is equal to The sum of the delivery costs of resource slot 3 during the delivery time period 2 is equal to The sum of the delivery costs of resource slot 3 during the delivery time period 3 is equal to The sum of the return on investments of resource slot 1 during the delivery time period 1 is equal to The sum of the return on investments of resource slot 1 during the delivery time period 2 is equal to The sum of the return on investment (ROI) of Resource Slot 1 during the placement time period 3 is equal to The sum of the return on investment (ROI) of Resource Slot 2 during the placement time period 1 is equal to The sum of the return on investment (ROI) of Resource Slot 2 during the placement time period 2 is equal to The sum of the return on investment (ROI) of Resource Slot 2 during the placement time period 3 is equal to The sum of the return on investment (ROI) of Resource Slot 3 during the placement time period 1 is equal to The sum of the return on investment (ROI) of Resource Slot 3 during the placement time period 2 is equal to The sum of the return on investment (ROI) of Resource Slot 3 during the placement time period 3 is equal to After that, it is determined that the sum of the placement cost and the return on investment (ROI) of Resource Slot 1 during the placement time period 1 is equal to The sum of the placement costs of Resource Slot 1 during the placement time period 2 is equal to The sum of the placement costs of Resource Slot 1 during the placement time period 3 is equal to The sum of the placement cost and the return on investment (ROI) of Resource Slot 2 during the placement time period 1 is equal to The sum of the placement costs of Resource Slot 2 during the placement time period 2 is equal to The sum of the placement costs of Resource Slot 2 during the placement time period 3 is equal to The sum of the placement cost and the return on investment (ROI) of Resource Slot 3 during the placement time period 1 is equal to The sum of the placement costs of Resource Slot 3 during the placement time period 2 is equal to The sum of the placement costs of Resource Slot 3 during the placement time period 3 is equal to Thus, it can be determined that the first consumption ratios of Resource Slot 1, Resource Slot 2, and Resource Slot 3 are 1:2:3. The second consumption ratios of Resource Slot 1 during the placement time periods 1, 2, and 3 are 1:2:3. The second consumption ratios of Resource Slot 2 during the placement time periods 1, 2, and 3 are 2:1:3. The second consumption ratios of Resource Slot 3 during the placement time periods 1, 2, and 3 are 3:1:2. In this way, the placement ratio of Resource Slot 1 during the placement time period 1 can be determined as The placement ratio of Resource Slot 1 during the placement time period 2 is The placement ratio of Resource Slot 1 during the placement time period 3 is The placement ratio of Resource Slot 2 during the placement time period 1 is The placement ratio of Resource Slot 2 during the placement time period 2 is The placement ratio of Resource Slot 2 during the placement time period 3 is The placement ratio of Resource Slot 3 during the placement time period 1 is The placement ratio of Resource Slot 3 during the placement time period 2 is The placement ratio of Resource Slot 3 during the placement time period 3 is

[0096] It should be noted that when the placement ratio is equal to the product of the first consumption ratio and the second consumption ratio of the resource position, and the evaluation parameters include the return on investment and the secondary retention rate, the calculation process of calculating the placement ratio of each resource position in each placement time period is similar to the calculation process of calculating the placement ratio of each resource position in each placement time period when the placement ratio is equal to the product of the first consumption ratio and the second consumption ratio of the resource position, and the evaluation parameters include the placement cost and the return on investment, and will not be elaborated here.

[0097] Similarly, when the placement ratio is equal to the product of the first consumption ratio and the second consumption ratio of the resource position, and the evaluation parameters include the placement cost, the return on investment and the secondary retention rate, the calculation process of calculating the placement ratio of each resource position in each placement time period is similar to the calculation process of calculating the placement ratio of each resource position in each placement time period when the placement ratio is equal to the product of the first consumption ratio and the second consumption ratio of the resource position, and the evaluation parameters include the placement cost and the return on investment, and will not be elaborated here.

[0098] S1202. Determine the expected budget consumption of each resource position of the target account in each placement time period in the current cycle based on the product of the placement ratio and the theoretical total placement consumption.

[0099] As described above, the advertising budget control method provided by the embodiments of the present disclosure obtains the assessment parameters, theoretical total delivery consumption, theoretical delivery consumption curve, and actual budget consumption curve of the target account in the current period; then, based on the assessment parameters, determines the theoretical delivery consumption curve corresponding to the assessment parameters, and based on the theoretical delivery consumption curve corresponding to the assessment parameters, determines the delivery ratio of each resource position in each delivery time period. Based on the product of the delivery ratio and the theoretical total delivery consumption, determines the expected budget consumption of each resource position of the target account in each delivery time period in the current period; based on the expected budget consumption, determines the cumulative theoretical delivery consumption of each resource position in the elapsed delivery time periods; at the same time, based on the actual budget consumption curve, determines the cumulative actual delivery consumption of each resource position in the elapsed delivery time periods; then, based on the difference value between the actual delivery consumption and the theoretical delivery consumption, determines the bidding probability; in this way, the bidding probability of the advertisement of the target account can be adjusted based on the actual delivery consumption and the theoretical delivery consumption in the resource position, and then the display probability of the advertisement of the target account in the resource position can be dynamically adjusted. Finally, the advertisement of the target account is delivered in the resource positions of the unelapsed delivery time periods according to the bidding probability. It can be seen that the actual delivery consumption and the theoretical delivery consumption of the resource positions at different delivery positions (spatial dimension) are used to adjust the bidding probability of the advertisement delivered by the target account on the resource positions at different delivery positions. Since the bidding probability can adjust the exposure of the advertisement delivered by the target account, the theoretical total delivery consumption of the target account and the advertisement conversion rate of the advertisement delivered by the target account can be controlled. At the same time, since both the actual delivery consumption and the theoretical delivery consumption consider the influence of the resource positions at different delivery positions on the advertisement delivery data (i.e., time + spatial dimension), the situation where the influencing factor is only a single time dimension is avoided, making the loss assessment of the advertising budget more accurate.

[0100] In some feasible examples, in combination with Figure 6 , such as Figure 7 shown, the above S1201 can be specifically implemented through the following S12010 - S12012.

[0101] S12010. Based on the theoretical delivery consumption curve corresponding to the assessment parameters, determine the first consumption ratio of each resource position;

[0102] S12011. Based on the theoretical delivery consumption curve corresponding to the assessment parameters, determine the second consumption ratio of each resource position in each delivery time period;

[0103] S12012. Based on the first consumption ratio and the second consumption ratio, determine the delivery ratio of each resource position in each delivery time period.

[0104] In some examples, the delivery ratio is equal to the product of the first consumption ratio and the second consumption ratio of the resource position; or, the delivery ratio is equal to the sum of the first consumption ratio and the second consumption ratio of the resource position; or, the delivery ratio is obtained by substituting the first consumption ratio and the second consumption ratio into a delivery formula. For example, the delivery formula is: z = ax + by + c, where z represents the delivery ratio, x represents the first consumption ratio, y represents the second consumption ratio, and a, b, and c are constants.

[0105] As can be seen from the above, the advertising budget control method provided by the embodiments of the present disclosure includes obtaining the assessment parameters, theoretical total delivery consumption, theoretical delivery consumption curve, and actual budget consumption curve of the target account in the current period; then, based on the assessment parameters, determining the theoretical delivery consumption curve corresponding to the assessment parameters, and based on the theoretical delivery consumption curve corresponding to the assessment parameters, determining the first consumption ratio of each resource position; based on the theoretical delivery consumption curve corresponding to the assessment parameters, determining the second consumption ratio of each resource position in each delivery time period; based on the first consumption ratio and the second consumption ratio, determining the delivery ratio of each resource position in each delivery time period, and based on the product of the delivery ratio and the theoretical total delivery consumption, determining the expected budget consumption of each resource position of the target account in each delivery time period in the current period; based on the expected budget consumption, determining the cumulative theoretical delivery consumption of each resource position in the elapsed delivery time periods; at the same time, based on the actual budget consumption curve, determining the cumulative actual delivery consumption of each resource position in the elapsed delivery time periods; then, based on the difference value between the actual delivery consumption and the theoretical delivery consumption, determining the bidding probability; in this way, the bidding probability of the advertisement of the target account can be adjusted based on the actual delivery consumption and the theoretical delivery consumption in the resource position, and further, the display probability of the advertisement of the target account in the resource position can be dynamically adjusted. Finally, the advertisement of the target account is delivered in the resource positions of the unelapsed delivery time periods according to the bidding probability. It can be seen that the bidding probability of the advertisement delivered by the target account in the resource positions at different delivery locations (spatial dimension) is adjusted according to the actual delivery consumption and the theoretical delivery consumption. Since the bidding probability can adjust the exposure of the advertisement delivered by the target account, the theoretical total delivery consumption of the target account and the advertisement conversion rate of the advertisement delivered by the target account can be controlled. At the same time, since both the actual delivery consumption and the theoretical delivery consumption consider the influence of the resource positions at different delivery locations on the advertisement delivery data (i.e., time + spatial dimension), it is avoided that the influencing factor is only a single time dimension, making the loss assessment of the advertising budget more accurate.

[0106] In some feasible examples, in combination with Figure 1 , such as Figure 8 shown, the advertising budget control method provided by the embodiments of the present disclosure further includes S17 and S18.

[0107] S17. Obtain the historical data of the target account; wherein, the historical data includes the historical delivery consumption of resource positions at different delivery locations, and is obtained by fitting the historical delivery parameters of each resource position in each period. The historical delivery parameters include one or more of the delivery cost, return on investment, and secondary retention rate. The historical delivery parameters include one or more of the delivery cost, return on investment, and secondary retention rate.

[0108] S18. Fit the historical data to generate the theoretical delivery consumption curve for the next period.

[0109] As can be seen from the above, the advertising budget control method provided by the embodiments of the present disclosure obtains the historical data of the target account and fits the historical data to generate the theoretical delivery consumption curve for the next period. Thus, in the current period, the theoretical total delivery consumption, the theoretical delivery consumption curve, and the actual budget consumption curve of the target account in the current period can be obtained; then, based on the theoretical total delivery consumption and the theoretical delivery consumption curve, determine the cumulative theoretical delivery consumption of each resource position in the delivered time period that has passed; at the same time, based on the actual budget consumption curve, determine the cumulative actual delivery consumption of each resource position in the delivered time period that has passed; then, based on the difference value between the actual delivery consumption and the theoretical delivery consumption, determine the bidding probability; in this way, based on the actual delivery consumption and the theoretical delivery consumption in the resource position, the bidding probability of the advertisement of the target account can be adjusted, and then the display probability of the advertisement of the target account in the resource position can be dynamically adjusted. Finally, place the advertisement of the target account in the resource position of the undelivered time period according to the bidding probability. It can be seen that, for the actual delivery consumption and the theoretical delivery consumption of the resource positions at different delivery locations (spatial dimension), adjust the bidding probability of the advertisement placed by the target account on the resource positions at different delivery locations. Since the bidding probability can adjust the exposure of the advertisement placed by the target account, the theoretical total delivery consumption of the target account and the advertisement conversion rate of the advertisement placed by the target account can be controlled. At the same time, since both the actual delivery consumption and the theoretical delivery consumption consider the influence of the resource positions at different delivery locations on the advertisement delivery data (i.e., time + spatial dimension), avoiding the influence factor being only a single time dimension, making the loss assessment of the advertising budget more accurate.

[0110] In some feasible examples, in combination with Figure 8 , such as Figure 9 shown, the above S18 can be specifically implemented through the following S180 - S182.

[0111] S180. Based on the historical data, perform fitting to generate a predicted consumption curve.

[0112] S181. Smooth the predicted consumption curve to obtain a smoothed consumption curve.

[0113] In some examples, the smoothing process can be a wavelet smoothing process.

[0114] S182. Use the smoothed consumption curve as the theoretical delivery consumption curve for the next cycle.

[0115] As can be seen from the above, since the obtained theoretical delivery consumption curve is not smooth, in order to ensure the smoothness of the theoretical delivery consumption curve, the advertising budget control method provided by the embodiments of the present disclosure smooths the predicted consumption curve to obtain a smoothed consumption curve, and uses the smoothed consumption curve as the theoretical delivery consumption curve for the next cycle, so that the smoothness of the theoretical delivery consumption curve for the next cycle is better, ensuring the user experience.

[0116] In some feasible examples, in combination Figure 1 , as Figure 10 shown, the above S14 can be specifically implemented by the following S140 and S141.

[0117] S140. Calculate the absolute value of the difference between the actual delivery consumption and the theoretical delivery consumption.

[0118] S141. Use the absolute value as the bidding probability.

[0119] As can be seen from the above, the advertising budget control method provided by the embodiments of the present disclosure obtains the theoretical total delivery consumption, the theoretical delivery consumption curve, and the actual budget consumption curve of the target account in the current cycle; then, based on the theoretical total delivery consumption and the theoretical delivery consumption curve, determines the cumulative theoretical delivery consumption of each resource position in the elapsed delivery time period; at the same time, based on the actual budget consumption curve, determines the cumulative actual delivery consumption of each resource position in the elapsed delivery time period; then, calculates the absolute value of the difference between the actual delivery consumption and the theoretical delivery consumption. Use the absolute value as the bidding probability; in this way, based on the actual delivery consumption and the theoretical delivery consumption in the resource position, the bidding probability of the advertisement of the target account can be adjusted, and then the display probability of the advertisement of the target account in the resource position can be dynamically adjusted. Finally, the advertisement of the target account is placed in the resource position of the unelapsed delivery time period according to the bidding probability. It can be seen that for the actual delivery consumption and the theoretical delivery consumption of the resource positions at different delivery positions (spatial dimension), the bidding probability of the advertisement placed by the target account in the resource positions at different delivery positions is adjusted. Since the bidding probability can adjust the exposure of the advertisement placed by the target account, the theoretical total delivery consumption of the target account and the advertisement conversion rate of the advertisement placed by the target account can be controlled. At the same time, since both the actual delivery consumption and the theoretical delivery consumption consider the influence of the resource positions at different delivery positions on the advertisement delivery data (i.e., time + spatial dimension), avoiding the situation where the influencing factor is only a single time dimension, making the loss assessment of the advertising budget more accurate.

[0120] The above mainly introduces the solution provided by the embodiments of the present invention from the perspective of methods. To implement the above functions, it includes the corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0121] The embodiments of the present invention can divide the function modules of the advertising budget control device according to the above method examples. For example, each function module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software function module. It should be noted that the division of modules in the embodiments of the present invention is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0122] As Figure 11 shown, the embodiments of the present invention provide a schematic structural diagram of an advertising budget control device 10. The advertising budget control device 10 includes: an acquisition unit 101 and a processing unit 102.

[0123] The acquisition unit 101 is used to acquire the theoretical total delivery consumption, the theoretical delivery consumption curve, and the actual budget consumption curve of the target account in the current period; wherein, the current period includes at least one delivery time period, the theoretical delivery consumption curve is obtained by fitting based on the historical data of the target account, and the historical data includes the historical delivery consumption of resource positions in different delivery positions, and the historical delivery parameters of each resource position in each period, and the historical delivery parameters include one or more of delivery cost, return on investment, and secondary retention rate;

[0124] The processing unit 102 is used to determine the cumulative theoretical delivery consumption of each resource position in the passed delivery time period based on the theoretical total delivery consumption and the theoretical delivery consumption curve acquired by the acquisition unit 101;

[0125] The processing unit 102 is further used to determine the cumulative actual delivery consumption of each resource position in the passed delivery time period based on the actual budget consumption curve acquired by the acquisition unit 101;

[0126] The processing unit 102 is further used to determine the bidding probability based on the difference value between the actual delivery consumption and the theoretical delivery consumption;

[0127] The processing unit 102 is further configured to place the advertisement of the target account in the ad slots of the unpassed placement time periods according to the bidding probability.

[0128] In some feasible examples, the processing unit 102 is specifically configured to determine the expected budget consumption of the target account for each ad slot in each placement time period of the current cycle based on the theoretical total placement consumption and the theoretical placement consumption curve obtained by the acquisition unit 101; the processing unit 102 is specifically configured to determine the cumulative theoretical placement consumption of each ad slot in the passed placement time periods based on the expected budget consumption.

[0129] In some feasible examples, the acquisition unit 101 is further configured to acquire the assessment parameters of the target account in the current cycle; wherein, the assessment parameters include one or more of the placement cost, the return on investment, and the secondary retention rate; the processing unit 102 is specifically configured to determine the theoretical placement consumption curve corresponding to the assessment parameters based on the assessment parameters acquired by the acquisition unit 101; wherein, different theoretical placement consumption curves correspond to different assessment parameters; the processing unit 102 is specifically configured to determine the placement ratio of each ad slot in each placement time period based on the theoretical placement consumption curve corresponding to the assessment parameters; the processing unit 102 is specifically configured to determine the expected budget consumption of the target account for each ad slot in each placement time period of the current cycle based on the product of the placement ratio and the theoretical total placement consumption.

[0130] In some feasible examples, the processing unit 102 is specifically configured to determine the first consumption ratio of each ad slot based on the theoretical placement consumption curve corresponding to the assessment parameters; the processing unit 102 is specifically configured to determine the second consumption ratio of each ad slot in each placement time period based on the theoretical placement consumption curve corresponding to the assessment parameters; the processing unit 102 is specifically configured to determine the placement ratio of each ad slot in each placement time period based on the first consumption ratio and the second consumption ratio.

[0131] In some feasible examples, the acquisition unit 101 is further configured to acquire the historical data of the target account; wherein, the historical data includes the historical placement consumption of the ad slots at different placement positions, and is obtained by fitting the historical placement parameters of each ad slot in each cycle, and the historical placement parameters include one or more of the placement cost, the return on investment, and the secondary retention rate, and the historical placement parameters include one or more of the placement cost, the return on investment, and the secondary retention rate; the processing unit 102 is further configured to fit the historical data acquired by the acquisition unit 101 to generate the theoretical placement consumption curve of the next cycle.

[0132] In some implementable examples, the processing unit 102 is specifically configured to perform fitting based on the historical data obtained by the obtaining unit 101 to generate a predicted consumption curve; the processing unit 102 is specifically configured to perform smoothing processing on the predicted consumption curve to obtain a smoothed consumption curve; the processing unit 102 is specifically configured to use the smoothed consumption curve as the theoretical delivery consumption curve for the next cycle.

[0133] In some implementable examples, the processing unit 102 is specifically configured to calculate the absolute value of the difference between the actual delivery consumption and the theoretical delivery consumption; the processing unit 102 is specifically configured to use the absolute value as the bidding probability.

[0134] Of course, the advertisement budget control device 10 provided in the embodiments of the present invention includes but is not limited to the above modules. For example, the advertisement budget control device 10 may further include a storage unit 103. The storage unit 103 may be used to store the program code of the advertisement budget control device 10, and may also be used to store the data generated during the operation of the advertisement budget control device 10, such as the data in the write request.

[0135] Figure 12 The structural schematic diagram of a server provided in the embodiments of the present invention is as Figure 12 shown. The server may include: at least one processor 51, a memory 52, a communication interface 53, a communication bus 54, and a display screen 55. The following will combine Figure 12 to specifically introduce each component of the server:

[0136] Among them, the processor 51 is the control center of the server, which may be a single processor or a collective term for multiple processing elements. For example, the processor 51 is a central processing unit (CPU), or may be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as: one or more DSPs, or one or more field programmable gate arrays (FPGAs).

[0137] In a specific implementation, as an embodiment, the processor 51 may include one or more CPUs, such as Figure 12 the CPU0 and CPU1 shown in Figure 12The processors 51 and 56 shown in [figure]. Each of these processors can be a single-core processor (Single-CPU) or a multi-core processor (Multi-CPU). The processor here can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0138] The memory 52 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but not limited to this. The memory 52 can exist independently and be connected to the processor 51 through the communication bus 54. The memory 52 can also be integrated with the processor 51.

[0139] In a specific implementation, the memory 52 is used to store the data in the present invention and execute the software program of the present invention. The processor 51 can execute various functions of the air conditioner by running or executing the software program stored in the memory 52 and calling the data stored in the memory 52.

[0140] The communication interface 53 uses any device such as a transceiver for communicating with other devices or communication networks, such as a radio access network (RAN), a wireless local area network (WLAN), a terminal, the cloud, etc. The communication interface 53 can include an acquisition unit to implement the acquisition function.

[0141] The communication bus 54 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 12 it is only represented by a thick line in Figure 12 , but this does not mean that there is only one bus or one type of bus.

[0142] As an example, in combination with Figure 11 , the function implemented by the acquisition unit 101 in the advertising budget control device 10 is the same as that of the communication interface 53 in Figure 12 , the function implemented by the processing unit 102 in the advertising budget control device 10 is the same as that of the processor 51 in Figure 12 , and the function implemented by the storage unit 103 in the advertising budget control device 10 is the same as that of the memory 52 in Figure 12 .

[0143] Another embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a computing device, the computing device implements the advertising budget control method according to any one of the above examples.

[0144] In some embodiments, the disclosed method can be implemented as computer program instructions encoded in a computer-readable storage medium in a machine-readable format or encoded in other non-transitory media or articles.

[0145] Figure 13 Schematically shows a conceptual partial view of a computer program product provided by an embodiment of the present invention. The computer program product includes a computer program for executing a computer process on a computing device.

[0146] In one embodiment, the computer program product is provided using a signal-bearing medium 410. The signal-bearing medium 410 can include one or more program instructions, which when run by one or more processors can provide the functions or partial functions described above for Figure 1 . Therefore, for example, referring to the embodiment shown in Figure 1 , one or more features of S11-S15 can be borne by one or more instructions associated with the signal-bearing medium 410. In addition, Figure 13 the program instructions in Figure 13 also describe example instructions.

[0147] In some examples, the signal-bearing medium 410 may include a computer-readable medium 411, such as but not limited to, a hard disk drive, a compact disc (CD), a digital video disc (DVD), a digital tape, a memory, a read-only memory (ROM), or a random access memory (RAM), and so on.

[0148] In some embodiments, the signal-bearing medium 410 may include a computer-recordable medium 412, such as but not limited to, a memory, a read / write (R / W) CD, a R / W DVD, and so on.

[0149] In some embodiments, the signal-bearing medium 410 may include a communication medium 413, such as but not limited to, a digital and / or analog communication medium (e.g., an optical fiber cable, a waveguide, a wired communication link, a wireless communication link, and so on).

[0150] The signal-bearing medium 410 may be conveyed by a wireless form of the communication medium 413 (e.g., a wireless communication medium compliant with the IEEE 802.41 standard or other transmission protocols). One or more program instructions may be, for example, computer-executable instructions or logic implementation instructions.

[0151] In some examples, such as for Figure 11 the described advertising budget control device may be configured to provide various operations, functions, or actions in response to one or more program instructions via the computer-readable medium 411, the computer-recordable medium 412, and / or the communication medium 413.

[0152] From the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional module is used as an example. In practical applications, the above functions can be allocated to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0153] In several embodiments provided by the present invention, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces. The indirect coupling or communication connection of the device or unit may be in an electrical, mechanical, or other form.

[0154] The unit described as a separation component may or may not be physically separated. The component shown as a unit may be a physical unit or multiple physical units, that is, it may be located in one place or may be distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in various embodiments of the present invention may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0156] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0157] The above are only specific implementation manners of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An advertising budget control method, characterized in that: include: Obtaining the theoretical total delivery consumption, theoretical delivery consumption curve, and actual budget consumption curve of the target account in the current cycle; wherein the current cycle includes at least one delivery time period, and the theoretical delivery consumption curve is obtained by fitting based on the historical data of the target account, the historical data includes the historical delivery consumption of resource positions at different delivery locations, and the historical delivery parameters of each resource position in each cycle, and the historical delivery parameters include one or more of delivery cost, return on investment, and secondary retention rate; Based on the theoretical total delivery consumption and the theoretical delivery consumption curve, determine the accumulated theoretical delivery consumption of each resource position in the delivery time period that has passed; Based on the actual budget consumption curve, determining the actual delivery consumption accumulated by each resource position in the elapsed delivery time period; Determining a bidding probability based on a difference between the actual delivery consumption and the theoretical delivery consumption; The advertisement of the target account is delivered in a resource slot in a non-interrupted delivery time period according to the bidding probability.

2. The advertising budget control method according to claim 1, characterized in that: The step of determining the accumulated theoretical delivery consumption of each resource position in the elapsed delivery time period based on the theoretical total delivery consumption and the theoretical delivery consumption curve includes: Determine the expected budget consumption of each resource position of the target account in each delivery time period in the current cycle based on the theoretical total delivery consumption and the theoretical delivery consumption curve; Based on the expected budget consumption, the accumulated theoretical delivery consumption of each resource position in the elapsed delivery time period is determined.

3. The advertising budget control method according to claim 2, characterized in that: The method further comprises: determining, based on the theoretical total delivery consumption and the theoretical delivery consumption curve, that each resource position of the target account in the current cycle is before the expected budget consumption in each delivery time period; Acquire the assessment parameters of the target account in the current cycle; wherein the assessment parameters include one or more of the following: delivery cost, return on investment, and retention rate; The determining, based on the theoretical total delivery consumption and the theoretical delivery consumption curve, the expected budget consumption of each resource position of the target account in each delivery time period in the current cycle includes: Based on the assessment parameters, determining a theoretical delivery consumption curve corresponding to the assessment parameters; wherein different theoretical delivery consumption curves correspond to different assessment parameters; Based on the theoretical delivery consumption curve corresponding to the assessment parameter, determine the delivery ratio of each resource position in each delivery time period; Based on the product of the delivery ratio and the theoretical total delivery consumption, the expected budget consumption of each resource position of the target account in each delivery time period of the current cycle is determined.

4. The advertising budget control method according to claim 3, characterized in that: The determining the delivery ratio of each resource position in each delivery time period based on the theoretical delivery consumption curve corresponding to the assessment parameter includes: Determine a first consumption ratio of each resource location based on a theoretical delivery consumption curve corresponding to the assessment parameter; Based on the theoretical delivery consumption curve corresponding to the assessment parameter, determine the second consumption ratio of each resource position in each delivery time period; Based on the first consumption ratio and the second consumption ratio, a delivery ratio of each resource position in each delivery time period is determined.

5. The advertising budget control method according to claim 1, characterized in that: Before obtaining the theoretical total delivery consumption, theoretical delivery consumption curve and actual budget consumption curve of the target account in the current cycle, the method further includes: Acquire historical data of the target account; wherein the historical data includes historical delivery consumption of resource positions at different delivery locations, and historical delivery parameters of each resource position in each cycle are fitted, and the historical delivery parameters include one or more of delivery cost, return on investment, and secondary retention rate; the historical delivery parameters include one or more of delivery cost, return on investment, and secondary retention rate; The historical data is fitted to generate a theoretical delivery consumption curve for the next cycle.

6. The advertising budget control method according to claim 5, characterized in that: The fitting of the historical data to generate a theoretical delivery consumption curve for the next cycle includes: Perform fitting based on the historical data to generate a predicted consumption curve; Smoothing the predicted consumption curve to obtain a smoothed consumption curve; The smoothed consumption curve is used as the theoretical delivery consumption curve for the next cycle.

7. The advertising budget control method according to claim 1, characterized in that: The determining of the bidding probability based on the difference between the actual delivery consumption and the theoretical delivery consumption includes: Calculating the absolute value of the difference between the actual delivery consumption and the theoretical delivery consumption; The absolute value is used as the bidding probability.

8. An advertising budget control device, characterized in that: include: An acquisition unit is used to acquire a theoretical total delivery consumption, a theoretical delivery consumption curve, and an actual budget consumption curve of a target account in a current cycle; wherein the current cycle includes at least one delivery time period, and the theoretical delivery consumption curve is obtained by fitting based on historical data of the target account, wherein the historical data includes historical delivery consumption of resource positions at different delivery locations, and historical delivery parameters of each resource position in each cycle, wherein the historical delivery parameters include one or more of delivery cost, return on investment, and secondary retention rate; A processing unit, configured to determine the accumulated theoretical delivery consumption of each resource position in the delivery time period that has passed based on the theoretical total delivery consumption and the theoretical delivery consumption curve acquired by the acquisition unit; The processing unit is further configured to determine the actual delivery consumption accumulated by each resource position in the elapsed delivery time period based on the actual budget consumption curve acquired by the acquisition unit; The processing unit is further used to determine the bidding probability based on the difference between the actual delivery consumption and the theoretical delivery consumption; The processing unit is further configured to place the advertisement of the target account in a resource slot in a non-interrupted delivery time period according to the bidding probability.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the advertising budget control method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the advertising budget control method according to any one of claims 1 to 7.

Images