Digital marketing budget dynamic allocation and resource scheduling optimization method, system and device
By cleaning and modeling historical marketing campaign data, the system predicts key performance indicators for future campaigns. Under budget and performance target constraints, it uses algorithms to combine influencer resources and allocate budgets. This solves the problems of existing technologies, such as budget allocation relying on human experience, unpredictable campaign results, and low resource scheduling efficiency, and achieves more efficient digital marketing budget allocation and resource scheduling.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING ZHIDING CULTURE MEDIA CO LTD
- Filing Date
- 2026-04-30
- Publication Date
- 2026-07-21
AI Technical Summary
Existing digital marketing budget allocation methods rely on human experience or static rules, making it difficult to adapt to the dynamically changing market environment, lacking predictive capabilities, unable to simultaneously meet multiple objective constraints, and resulting in low efficiency in influencer combination selection.
By cleaning and modeling historical marketing data of enterprises, key performance indicators are predicted for future campaigns. Under budget and performance target constraints, algorithms are used to combine and calculate influencer resources and allocate budgets, thus constructing a dynamic budget allocation and resource scheduling optimization system.
It improves the scientific nature of budget decision-making, supports multi-objective and multi-constraint optimization, enhances the efficiency of human resource utilization, realizes dynamic adjustment and closed-loop optimization, reduces the cost of manual decision-making, and enhances the system's dynamic adaptability.
Smart Images
Figure CN122434603A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, and in particular to a method, system, and device for dynamic allocation and resource scheduling optimization of digital marketing budgets. Background Technology
[0002] With the popularization of digital marketing, businesses are continuously increasing their investment in social media, content platforms, and feed advertising. Influencer marketing, content delivery, and feed promotion are gradually becoming important means for businesses to acquire users and convert them. However, in practice, the allocation of marketing budgets and the deployment of influencer resources still mainly rely on manual experience or static rules, making it difficult to adapt to the dynamically changing market environment.
[0003] The main methods for allocating digital marketing budgets are as follows: (1) Budget allocation driven by human experience Businesses typically have their operations or campaign staff manually allocate budgets to different platforms, influencers, or content based on historical experience. The drawbacks of this approach are: heavy reliance on personal experience and high subjectivity; difficulty in handling real-time changes in data performance; and inability to perform globally optimal combination calculations within a large pool of influencers.
[0004] (2) Allocation method based on historical average or fixed rules Some systems use simple rules, such as allocating budgets based on historical average impressions or click performance; setting fixed budget caps or percentages for individual influencers. The drawbacks are: ignoring data volatility and uncertainty; being unable to predict future campaign performance; and difficulty in simultaneously meeting multiple objectives (such as impressions, CPV, CPE).
[0005] (3) Single-indicator optimized delivery system Some existing advertising systems are optimized only around a single metric (such as minimum CPC). Their drawbacks include: inability to comprehensively consider brand exposure, engagement, and conversion; unsuitability for non-standardized advertising scenarios such as influencer marketing; and insufficient flexibility in resource allocation.
[0006] The main limitations of existing technologies are: (1) Insufficient depth of data utilization, specifically manifested in the fact that historical data has not been systematically cleaned and modeled; (2) Lack of predictive ability, specifically manifested in the inability to assess the effectiveness of deployment in advance; (3) The ability to handle multi-objective constraints is weak, specifically in that it is difficult to simultaneously meet budget, effectiveness and cost requirements; (4) The efficiency of expert combination selection is low, specifically in that it is impossible to find the optimal combination in a large pool of experts. Summary of the Invention
[0007] The purpose of this invention is to provide a method for dynamic allocation of digital marketing budgets and optimization of resource scheduling. By cleaning and modeling historical marketing data of enterprises, the method predicts the key performance indicators of influencers or resources in the future campaign cycle. Under the constraints of budget and performance targets, the method uses an algorithm to combine and calculate the influencer resources and allocate the budget, thereby solving the problems of budget allocation relying on human experience, unpredictable campaign results, and low resource scheduling efficiency in the existing technology.
[0008] In a first aspect, embodiments of the present invention provide a method for dynamic allocation and resource scheduling optimization of digital marketing budgets, comprising the following steps: S1. Historical Marketing Data Collection, Cleaning and Standardization: Collect historical data of the company's past digital marketing activities and perform cleaning and standardization on the collected historical data; S2. Key performance indicator prediction model: After data cleaning, a performance prediction model is built based on historical data to predict the performance of each influencer or resource in the future campaign period. S3. Budget Constraints and Target Parameterization: Receives marketing campaign constraints input by the enterprise and transforms them into parameterized constraints that can be used for algorithm calculations. The above constraints are then input into the subsequent optimization calculation process as parameters. S4. Influencer Resource Unit Modeling and Resource Pool Construction: Each influencer or resource allocation is abstracted into a resource unit. An influencer resource pool is constructed based on the above resource units for subsequent combination optimization calculations. S5. Budget Dynamic Allocation and Expert Combination Optimization Calculation: After obtaining the resource pool and constraints, construct an optimization model for budget allocation and resource scheduling, perform budget allocation and expert combination calculation, select the optimal or near-optimal expert combination that meets the conditions, and calculate the budget allocation result for each expert. S6. Campaign Execution and Actual Results Data Collection: Based on the budget allocation and influencer combination results, execute the corresponding marketing campaigns and collect actual results data during the campaign process. These actual results data include, but are not limited to, actual impressions, actual interactions, and actual costs. S7. Results Feedback and Model Update: Compare and analyze the actual deployment results with the prediction results, calculate the prediction deviation, and update the prediction model parameters based on the deviation results.
[0009] In one possible implementation, in step S1, The historical data includes at least: historical placement records of influencers or content resources; the corresponding exposure, interaction, and conversion rates; placement costs and settlement prices; and information on the placement platform type, content format, and publication time. The collected historical data is cleaned, including: removing abnormal data and severely missing data records; mapping data metrics across different platforms to a unified standard; and standardizing time, cost, and performance metrics.
[0010] In other possible implementations, the key metrics predicted in step S2 include, but are not limited to: expected exposure, cost per exposure (CPV), and cost per interaction (CPE); the prediction model takes the influencer's historical performance, content type, platform characteristics, and time characteristics as input features and outputs the corresponding predicted metric values.
[0011] In another possible implementation, in step S3, the constraints include: a total budget cap; a target exposure volume or exposure range; acceptable CPV and CPE thresholds; and restrictions on the number of influencers or platform distribution.
[0012] In other possible implementations, in step S4, each influencer or ad placement resource is abstracted into a resource unit, and the following attributes are defined for each resource unit: predicted exposure; predicted CPV and predicted CPE; budget required for a single ad placement; number of ad placements or scheduling constraints.
[0013] In another possible implementation, in step S5, the optimization objectives of the optimization model include: maximizing the total predicted exposure under budget constraints; or minimizing the total campaign cost while achieving the target exposure.
[0014] Secondly, the present invention also provides a digital marketing budget dynamic allocation and resource scheduling optimization system, which is used to implement the methods described in the above method embodiments, and the system includes: The historical marketing data collection module is used to collect historical data from a company's past digital marketing activities. The data cleaning and standardization module is used to perform cleaning and standardization processing on the collected historical data. The campaign performance prediction module is used to build a campaign performance prediction model based on historical data after data cleaning is completed, and to predict the campaign performance of each influencer or resource in the future campaign period. The budget constraint and campaign target setting module is used to receive marketing campaign constraints input by enterprises and convert them into parameterized constraints that can be used for algorithm calculation. The above constraints are input into the subsequent optimization calculation process in the form of parameters. The Influencer Resource Pool Construction Module is used to abstract each influencer or resource allocation into a resource unit, and build an influencer resource pool based on the above resource units for subsequent combination optimization calculations; The budget dynamic allocation and resource scheduling optimization module is used to construct an optimization model for budget allocation and resource scheduling after obtaining the resource pool and constraints, perform budget allocation and expert combination calculations, select the optimal or near-optimal expert combination that meets the conditions, and calculate the budget allocation result for each expert. The campaign execution module is used to execute corresponding marketing campaigns based on budget allocation and influencer combination results, and to collect actual performance data during the campaign process. This actual performance data includes, but is not limited to, actual impressions, actual interactions, and actual costs. The effect feedback and model update module is used to compare and analyze the actual deployment effect with the prediction result, calculate the prediction deviation, and update the prediction model parameters based on the deviation result.
[0015] In other possible implementations, the system also includes a system control and parameter configuration module. The output of the system control and parameter configuration module is connected to the data cleaning and standardization module, the campaign effect prediction module, the budget constraint and campaign target setting module, and the budget dynamic allocation and resource scheduling optimization module, respectively. The system control and parameter configuration module is used to control the data cleaning and standardization module, the campaign effect prediction module, the budget constraint and campaign target setting module, and the budget dynamic allocation and resource scheduling optimization module, as well as to configure and manage the system parameters.
[0016] Thirdly, embodiments of the present invention also provide a computer-readable storage medium comprising a program that, when run on an electronic device, causes the electronic device to perform any of the possible implementations of the first aspect described above.
[0017] Fourthly, the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a program that can run on the processor, and when the program is executed by the processor, the electronic device performs the method as described in any of the embodiments of the first aspect above.
[0018] Fifthly, embodiments of the present invention also provide a computer program product that, when the program product is run on an electronic device, causes the electronic device to perform any of the possible implementation methods of the first aspect described above.
[0019] Compared with the prior art, the present invention has the following advantages: (1) Introduce a forecasting mechanism to improve the scientific nature of budget decision-making: Through the effect forecasting model, the budget allocation no longer depends on historical averages or human experience.
[0020] (2) Supports multi-objective and multi-constraint optimization: It can simultaneously constrain budget, exposure and cost indicators, and is suitable for complex marketing scenarios.
[0021] (3) Improve the efficiency of influencer resource utilization: Improve the overall delivery effect by combining and optimizing algorithms.
[0022] (4) Achieve dynamic adjustment and closed-loop optimization: Achieve continuous optimization during the deployment process through real-time data feedback.
[0023] (5) Improve budget utilization efficiency: Through prediction and optimization algorithms, a limited budget can achieve higher exposure and interaction effects.
[0024] (6) Reduce the cost of human decision-making: Transform the selection of experts and budget allocation from human experience to algorithm calculation.
[0025] (7) Supports multi-target delivery strategy: It can simultaneously constrain multiple indicators such as exposure, CPV, and CPE.
[0026] (8) Enhance the system’s dynamic adaptability: respond to market and data changes through real-time feedback and model updates.
[0027] In summary, this invention cleanses and models historical marketing campaign data to predict key performance indicators of influencers or campaign resources in future campaign cycles. Under budget and performance target constraints, it uses algorithms to combine influencer resources and allocate budgets, thereby solving the problems of budget allocation relying on human experience, unpredictable campaign results, and low resource scheduling efficiency in existing technologies. Attached Figure Description
[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0029] Figure 1 A flowchart illustrating the budget allocation and expert combination optimization method provided in this embodiment of the invention; Figure 2 This is a schematic diagram illustrating the collaboration between the prediction model and the optimization algorithm provided in an embodiment of the present invention. Figure 3 This is a timing diagram of the deployment execution and effect feedback provided in an embodiment of the present invention; Figure 4 A schematic diagram of the digital marketing budget dynamic allocation system architecture provided in this embodiment of the invention; Figure 5 This is a schematic diagram of an electronic device structure provided in an embodiment of the present invention. Detailed Implementation
[0030] In the description of embodiments of the present invention, the terminology used in the following embodiments is for the purpose of describing particular embodiments only and is not intended to be a limitation of the invention. As used in the specification and appended claims of the present invention, the singular expressions “a,” “the,” “the,” “the,” and “this” are intended to also include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of the present invention, “at least one” and “one or more” refer to one or more (including two). The term “and / or” is used to describe the relationship between related objects, indicating that three relationships may exist; for example, A and / or B can indicate: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character “ / ” generally indicates that the preceding and following related objects are in an “or” relationship.
[0031] References to "one embodiment" or "some embodiments" as used in this specification mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the invention. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless otherwise specifically emphasized. The term "connection" includes both direct and indirect connections, unless otherwise stated. "First" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features.
[0032] In embodiments of the present invention, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or implementation described as "exemplarily" or "for example" in embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or implementations. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.
[0033] Reference Figures 1 to 3 The diagram shown illustrates the steps of a method for dynamically allocating and optimizing digital marketing budgets and resource scheduling, as provided in an embodiment of this specification. It should be understood that this method can be... Figure 4 The system's various modules are executed accordingly. This method may include the following steps, with clearly defined data inputs, processing procedures, and output results between each step: S1. Historical Marketing Data Collection, Cleaning, and Standardization Processing Steps This invention first collects historical data from the company's past digital marketing activities. The historical data includes at least: historical placement records of influencers or content resources; the corresponding exposure, interaction and conversion rates; placement costs and settlement prices; and information on the placement platform type, content format and release time.
[0034] The collected historical data is cleaned, including: removing abnormal data and severely missing data records; mapping data metrics across different platforms to a unified standard; and standardizing time, cost, and performance metrics.
[0035] In this step, data cleaning and standardization processes reduce the impact of noisy data on the prediction model, providing a high-quality data foundation for subsequent indicator modeling.
[0036] S2. Key Performance Indicator (KPI) Prediction Modeling Steps After data cleaning, this invention constructs a campaign performance prediction model based on historical data to predict the campaign performance of each influencer or resource in the future campaign period.
[0037] Key metrics predicted include, but are not limited to: expected exposure; cost per impression (CPV); and cost per interaction (CPE).
[0038] The prediction model takes the influencer's historical performance, content type, platform characteristics, and time characteristics as input features and outputs corresponding prediction index values.
[0039] In this step, predictive modeling transforms the previously unknowable effects into calculable predictable results, making budget allocation more forward-looking.
[0040] S3. Budget Constraints and Target Parametric Steps This invention receives marketing campaign constraints input by enterprises and transforms them into parameterized constraints that can be used for algorithm calculation. The constraints include: total budget limit; target exposure or exposure range; acceptable CPV and CPE thresholds; and restrictions on the number of influencers or platform distribution.
[0041] The above constraints are input as parameters into the subsequent optimization calculation process.
[0042] In this step, parameterized constraints are used to enable both budget objectives and performance objectives to participate in the optimization calculation simultaneously.
[0043] S4. Steps for Modeling Expert Resource Units and Constructing Resource Pools This invention abstracts each influencer or resource into a resource unit, and defines the following attributes for each resource unit: predicted exposure; predicted CPV and predicted CPE; budget required for a single campaign; number of campaigns or scheduling constraints.
[0044] Based on the above resource units, an expert resource pool is constructed for subsequent combination and optimization calculations.
[0045] In this step, the complex problem of influencer marketing is transformed into a standardized problem of resource combination optimization.
[0046] S5. Calculation steps for dynamic budget allocation and expert combination optimization After obtaining the resource pool and constraints, this invention constructs an optimization model for budget allocation and resource scheduling. Its optimization objectives include: maximizing the total predicted exposure under budget constraints; or minimizing the total campaign cost while achieving the target exposure.
[0047] Based on the above objectives and constraints, budget allocation and influencer combination calculations are performed to select the optimal or near-optimal influencer combination that meets the conditions, and the budget allocation result for each influencer is calculated.
[0048] In this step, algorithmic calculations replace manual screening to obtain a better resource allocation scheme from a large pool of experts.
[0049] S6. Steps for collecting data on campaign execution and actual results Based on the budget allocation and influencer combination results, execute the corresponding marketing campaigns and collect actual performance data during the campaign, including: actual exposure; actual interaction; and actual cost of goods and services.
[0050] This step provides real feedback data for subsequent model calibration and strategy adjustment.
[0051] S7. Effect feedback and model update steps This invention compares and analyzes the actual deployment effect with the prediction result, calculates the prediction deviation, and updates the prediction model parameters based on the deviation result.
[0052] During the campaign period, budget allocation and influencer combination calculations can be re-executed based on the remaining budget and real-time performance to achieve dynamic resource scheduling.
[0053] In this step, the system is given dynamic adjustment capabilities through effect feedback and model update mechanisms, thereby improving the overall stability and long-term effectiveness of the campaign.
[0054] Reference Figure 4The diagram shows the architecture of a digital marketing budget dynamic allocation and resource scheduling optimization system provided in this embodiment of the invention. This system implements the methods described in the above embodiments, including: a historical marketing data collection module, a data cleaning and standardization module, a campaign performance prediction module, a budget constraint and campaign target setting module, an influencer resource pool construction module, a budget dynamic allocation and resource scheduling optimization module, a campaign execution module, and an effect feedback and model update module. The output of the historical marketing data collection module is connected to the input of the data cleaning and standardization module; the output of the data cleaning and standardization module is connected to the input of the campaign performance prediction module; the output of the campaign performance prediction module is connected to the input of the budget constraint and campaign target setting module; the output of the budget constraint and campaign target setting module is connected to the input of the influencer resource pool construction module; the output of the influencer resource pool construction module is connected to the input of the budget dynamic allocation and resource scheduling optimization module; the output of the budget dynamic allocation and resource scheduling optimization module is connected to the input of the campaign execution module; the output of the campaign execution module is connected to the input of the effect feedback and model update module; and the outputs of the effect feedback and model update module are respectively connected to the campaign performance prediction module and the budget dynamic allocation and resource scheduling optimization module.
[0055] In one possible embodiment, the digital marketing budget dynamic allocation and resource scheduling optimization system includes: The historical marketing data collection module is used to collect historical data from a company's past digital marketing activities. The data cleaning and standardization module is used to perform cleaning and standardization processing on the collected historical data. The campaign performance prediction module is used to build a campaign performance prediction model based on historical data after data cleaning is completed, and to predict the campaign performance of each influencer or resource in the future campaign period. The budget constraint and campaign target setting module is used to receive marketing campaign constraints input by enterprises and convert them into parameterized constraints that can be used for algorithm calculation. The above constraints are input into the subsequent optimization calculation process in the form of parameters. The Influencer Resource Pool Construction Module is used to abstract each influencer or resource allocation into a resource unit, and build an influencer resource pool based on the above resource units for subsequent combination optimization calculations; The budget dynamic allocation and resource scheduling optimization module is used to construct an optimization model for budget allocation and resource scheduling after obtaining the resource pool and constraints, perform budget allocation and expert combination calculations, select the optimal or near-optimal expert combination that meets the conditions, and calculate the budget allocation result for each expert. The campaign execution module is used to execute corresponding marketing campaigns based on budget allocation and influencer combination results, and to collect actual performance data during the campaign process. This actual performance data includes, but is not limited to, actual impressions, actual interactions, and actual costs. The effect feedback and model update module is used to compare and analyze the actual deployment effect with the prediction result, calculate the prediction deviation, and update the prediction model parameters based on the deviation result.
[0056] In other possible implementations, the system also includes a system control and parameter configuration module. The output of the system control and parameter configuration module is connected to the data cleaning and standardization module, the campaign effect prediction module, the budget constraint and campaign target setting module, and the budget dynamic allocation and resource scheduling optimization module, respectively. The system control and parameter configuration module is used to control the data cleaning and standardization module, the campaign effect prediction module, the budget constraint and campaign target setting module, and the budget dynamic allocation and resource scheduling optimization module, as well as to configure and manage the system parameters.
[0057] The above method will be illustrated with specific examples below.
[0058] Example 1: Influencer combination selection based on fixed total budget and exposure target The purpose of this embodiment is to automatically select a combination of influencers that meet the requirements, given a total marketing budget and target exposure, and output the corresponding budget allocation plan. The specific implementation steps are as follows: 1. Data Input and Cleaning The system receives influencer campaign data from the past year, including each influencer's historical exposure, engagement, campaign cost, and campaign duration, and performs outlier removal and standardization on the data.
[0059] 2. Performance Indicator Prediction Based on the cleaned historical data, the system builds a predictive model to predict the expected exposure, CPV, and CPE for each influencer in the current campaign period.
[0060] 3. Setting Constraints Enterprises should input the following campaign constraints: total budget not exceeding the preset limit; total exposure not less than the target value; and predicted CPV for a single influencer not exceeding the specified threshold.
[0061] 4. Calculation of Expert Resource Combinations The system treats each influencer as a resource unit, and based on prediction indicators and constraints, executes budget allocation and combinatorial optimization algorithms to calculate influencer combinations that meet the conditions.
[0062] 5. Results Output The system outputs the final list of influencer combinations and allocates a corresponding budget amount to each influencer.
[0063] The implementation effect of this first embodiment is as follows: compared with manual screening, this embodiment achieves a higher predicted exposure under the same budget conditions, significantly improving the efficiency of budget utilization.
[0064] Example 2: Dynamic Budget Adjustment and Resource Allocation During the Deployment Period The purpose of this embodiment is to dynamically adjust budget allocation and influencer combinations based on real-time campaign performance during marketing campaign execution, in order to address data fluctuations. The implementation steps are as follows: 1. Initial budget allocation The system generates an initial influencer combination and budget allocation plan according to the method in Example 1, and then executes the campaign.
[0065] 2. Feedback of effect data During the campaign, the system periodically collects data on each influencer's actual exposure, engagement, and cost.
[0066] 3. Prediction Deviation Analysis The system compares the actual results with the predicted results and calculates the deviation value to evaluate the accuracy of the prediction model.
[0067] 4. Dynamic optimization and adjustment When the system detects that some influencers' performance is below the predicted threshold, it automatically reduces their subsequent budget and redistributes the remaining budget to influencers with better predicted performance.
[0068] 5. Continuous iteration The system repeatedly performs effect feedback and optimization calculations until the campaign period ends or the budget is exhausted.
[0069] The implementation effect of this second embodiment is as follows: This embodiment realizes dynamic resource scheduling during the delivery process, effectively reduces the risk of ineffective delivery, and improves the stability and profitability of the overall marketing campaign.
[0070] In other embodiments of the present invention, an electronic device 500 is disclosed, which can integrate the above-described system, such as... Figure 5 As shown, the hardware components include: one or more processors 501; memory 502; display 503; one or more application programs (not shown); and one or more computer programs 504. These components can be connected via one or more communication buses 505. The one or more computer programs 504 are stored in the memory 502 and configured to be executed by the one or more processors 501. The one or more computer programs 504 include instructions.
[0071] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer, implements the method described in the above-described method embodiments. Specific beneficial effects can be found in the above-described method embodiments.
[0072] The present invention also provides a computer program product that, when executed by a computer, implements the method described in the above-described method embodiments. Specific beneficial effects can be found in the above-described method embodiments.
[0073] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0074] In the various embodiments of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0075] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as flash memory, portable hard disk, read-only memory, random access memory, magnetic disk, or optical disk.
[0076] The above description is merely a specific implementation of the embodiments of the present invention, but the protection scope of the embodiments of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed in the embodiments of the present invention should be covered within the protection scope of the embodiments of the present invention. Therefore, the protection scope of the embodiments of the present invention should be determined by the protection scope of the claims.
Claims
1. A method for dynamic allocation and resource scheduling optimization of digital marketing budgets, characterized in that, Includes the following steps, S1. Historical Marketing Data Collection, Cleaning and Standardization: Collect historical data of the company's past digital marketing activities and perform cleaning and standardization on the collected historical data; S2. Key performance indicator prediction model: After data cleaning, a performance prediction model is built based on historical data to predict the performance of each influencer or resource in the future campaign period. S3. Budget Constraints and Target Parameterization: Receives marketing campaign constraints input by the enterprise and transforms them into parameterized constraints that can be used for algorithm calculations. The above constraints are then input into the subsequent optimization calculation process as parameters. S4. Influencer Resource Unit Modeling and Resource Pool Construction: Each influencer or resource allocation is abstracted into a resource unit. An influencer resource pool is constructed based on the above resource units for subsequent combination optimization calculations. S5. Budget Dynamic Allocation and Expert Combination Optimization Calculation: After obtaining the resource pool and constraints, construct an optimization model for budget allocation and resource scheduling, perform budget allocation and expert combination calculation, select the optimal or near-optimal expert combination that meets the conditions, and calculate the budget allocation result for each expert. S6. Campaign Execution and Actual Results Data Collection: Based on the budget allocation and influencer combination results, execute the corresponding marketing campaigns and collect actual results data during the campaign process. These actual results data include, but are not limited to, actual impressions, actual interactions, and actual costs. S7. Results Feedback and Model Update: Compare and analyze the actual deployment results with the prediction results, calculate the prediction deviation, and update the prediction model parameters based on the deviation results.
2. The method as described in claim 1, characterized in that, In step S1, The historical data includes at least: historical placement records of influencers or content resources; the corresponding exposure, interaction, and conversion rates; placement costs and settlement prices; and information on the placement platform type, content format, and publication time. The collected historical data is cleaned, including: removing abnormal data and severely missing data records; mapping data metrics across different platforms to a unified standard; and standardizing time, cost, and performance metrics.
3. The method as described in claim 1, characterized in that, In step S2, the key indicators predicted include, but are not limited to: expected exposure, cost per exposure (CPV), and cost per interaction (CPE). The prediction model takes the influencer's historical performance, content type, platform characteristics, and time characteristics as input features and outputs the corresponding predicted indicator values.
4. The method as described in claim 1, characterized in that, In step S3, the constraints include: total budget limit; target exposure or exposure range; acceptable CPV and CPE thresholds; and restrictions on the number of influencers or platform distribution.
5. The method as described in claim 1, characterized in that, In step S4, each influencer or ad placement resource is abstracted into a resource unit, and the following attributes are defined for each resource unit: predicted exposure; predicted CPV and predicted CPE; budget required for a single ad placement; number of ad placements or scheduling constraints.
6. The method as described in claim 1, characterized in that, In step S5, the optimization objectives of the optimization model include: maximizing the total predicted exposure under budget constraints; or minimizing the total campaign cost while achieving the target exposure.
7. A dynamic allocation and resource scheduling optimization system for digital marketing budgets, characterized in that, include: The historical marketing data collection module is used to collect historical data from a company's past digital marketing activities. The data cleaning and standardization module is used to perform cleaning and standardization processing on the collected historical data. The campaign performance prediction module is used to build a campaign performance prediction model based on historical data after data cleaning is completed, and to predict the campaign performance of each influencer or resource in the future campaign period. The budget constraint and campaign target setting module is used to receive marketing campaign constraints input by enterprises and convert them into parameterized constraints that can be used for algorithm calculation. The above constraints are input into the subsequent optimization calculation process in the form of parameters. The Influencer Resource Pool Construction Module is used to abstract each influencer or resource allocation into a resource unit, and build an influencer resource pool based on the above resource units for subsequent combination optimization calculations; The budget dynamic allocation and resource scheduling optimization module is used to construct an optimization model for budget allocation and resource scheduling after obtaining the resource pool and constraints, perform budget allocation and expert combination calculations, select the optimal or near-optimal expert combination that meets the conditions, and calculate the budget allocation result for each expert. The campaign execution module is used to execute corresponding marketing campaigns based on budget allocation and influencer combination results, and to collect actual performance data during the campaign process. This actual performance data includes, but is not limited to, actual impressions, actual interactions, and actual costs. The effect feedback and model update module is used to compare and analyze the actual deployment effect with the prediction result, calculate the prediction deviation, and update the prediction model parameters based on the deviation result.
8. The system as described in claim 7, characterized in that: It also includes a system control and parameter configuration module. The output of the system control and parameter configuration module is connected to the data cleaning and standardization module, the campaign effect prediction module, the budget constraint and campaign target setting module, and the budget dynamic allocation and resource scheduling optimization module, respectively. The system control and parameter configuration module is used to control the data cleaning and standardization module, the campaign effect prediction module, the budget constraint and campaign target setting module, and the budget dynamic allocation and resource scheduling optimization module, as well as to configure and manage the system parameters.
9. A computer-readable storage medium storing a program therein, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 6.
10. An electronic device, characterized in that, The device includes a memory and a processor, wherein the memory stores a program that can run on the processor, and when the program is executed by the processor, causes the electronic device to perform the method as described in any one of claims 1 to 6.