Advertisement putting optimization method and system based on flow consumption

Abstract

The invention discloses an advertisement putting optimization method and system based on flow consumption, and belongs to the technical field of advertisement putting, the advertisement putting optimization method and system based on flow consumption comprise the following specific steps: step 1, multi-dimensional data real-time collection: collection objects comprise request number, advertisement filling response, effective exposure and previous display cost; 2, sliding time window modeling: adopting a dynamic sliding time window (default window length T is equal to 24 hours), dividing data in the window into a plurality of sub-intervals (every 5 minutes is a storage unit) according to time slices, using a ring buffer to store the window data, and when new data enter, eliminating the oldest data block exceeding the window length. According to the invention, a mathematical model is established for the bandwidth cost of the network layer and the economic benefit of the service layer, a dynamic regulation and control mechanism based on statistical process control is proposed, and a hybrid architecture combining SDN and big data processing is designed, so that the bandwidth cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of advertisement delivery, and in particular relates to an advertisement delivery optimization method and system based on traffic consumption. Background Art

[0002] The advertising optimization method based on traffic consumption refers to a type of optimization strategy that focuses on traffic acquisition, allocation, and conversion efficiency during the advertising process, and achieves "lower cost acquisition of high-value traffic, more accurate allocation of traffic resources, and maximization of traffic conversion benefits" through data-driven and strategy adjustment. Its core logic is: traffic is not unlimited, and refined operations are needed to make each traffic consumption generate higher value.

[0003] The current advertising delivery optimization methods and systems based on traffic consumption have the following technical defects: the fixed traffic allocation strategy causes high-request and low-conversion advertising slots to occupy too much bandwidth resources; the traditional CPM settlement method does not establish a correlation model between request volume and consumption amount; the existing system lacks a dynamic control mechanism based on economic efficiency indicators. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the above-mentioned prior art and provide an advertisement delivery optimization method and system based on traffic consumption.

[0005] The technical solution adopted to solve the above technical problem is: an advertising delivery optimization method based on traffic consumption, including the following specific steps: Step 1: Real-time collection of multi-dimensional data: The collection objects include: number of requests, ad filling response, effective exposure, and previous display cost; Step 2: Sliding time window modeling: A dynamic sliding time window (default window length T = 24 hours) is used. The data in the window is divided into multiple sub-intervals according to time slices (every 5 minutes is a storage unit). A ring buffer is used to store window data. When new data enters, the oldest data block that exceeds the window length is eliminated. Step 3: Efficiency evaluation: The flow efficiency coefficient is calculated by using a formula, and then the flow efficiency coefficient is dynamically smoothed; Step 4: Dynamic Control: First, build a control decision matrix, then set interval division and control rules, and then perform elastic bandwidth allocation; Step 5: Real-time traffic control: Bandwidth quota instructions are sent to edge nodes through the OpenFlow protocol to adjust the queue scheduling algorithm, limit the request sending rate of inefficient advertising slots, reserve bandwidth buffers for efficient advertising slots, and ensure elastic expansion in the event of burst traffic.

[0006] Through the above technical solution, a mathematical model is established between the network layer bandwidth cost and the business layer economic benefit, a dynamic regulation mechanism based on statistical process control is proposed, and a hybrid architecture combining SDN and big data processing is designed to reduce bandwidth costs.

[0007] Furthermore, the flow efficiency coefficient is calculated using the following formula: For each ad slot , calculate its flow efficiency coefficient The specific formula is as follows: Among them, numerator: the sum of the consumption amounts corresponding to all exposures in the statistical window ( is the unit price of the i-th exposure, is the corresponding exposure); Denominator: the total number of requests generated by ad slot k during the window period .

[0008] Furthermore, the dynamic smoothing process adopts the following formula: Exponentially Weighted Moving Average: Introducing a Smoothing Factor ,right Smooth the time series to suppress short-term fluctuations: in, This is a smoothed ad slot. In time slice The efficiency coefficient, It's a time slice Calculated based on the latest window data , after each time slice, recalculate based on the latest window data And compared with the smoothed value of the previous period Weighted fusion.

[0009] Furthermore, the control decision matrix includes the following formula: Global statistics calculation: System average efficiency :Count all ad slots Mean, Refers to the advertising space The smoothing efficiency coefficient of Standard Deviation :calculate The standard deviation of , which measures the dispersion of efficiency distribution; when When the traffic quota is increased, When the current quota is maintained, When the quota is reduced in stages.

[0010] Furthermore, the graded decreasing quota adopts the following specific formula: .

[0011] Furthermore, the elastic bandwidth allocation adopts the following formula: in, is the amount of bandwidth dynamically allocated to advertisements, is the total bandwidth that can be allocated to the system, is the total number of ad slots, To control the intensity coefficient, The bandwidth ratio of high-efficiency ad slots is strengthened, and the denominator is the efficiency coefficient of all ad slots. The sum of the powers ensures that the total bandwidth allocation ratio is normalized.

[0012] The above technical solution can improve the flexibility of bandwidth allocation.

[0013] Furthermore, the real-time flow control adopts a feedback closed loop and recalculates every 30 minutes. Update the regulation decision. If an ad slot is in a decreasing range for three consecutive cycles, a warning will be triggered and its effectiveness will be manually reviewed.

[0014] Through the above technical solution, the overall update speed can be improved to avoid the waste of traffic caused by misjudgment of the program.

[0015] Furthermore, it includes a traffic monitoring terminal, an efficiency calculation engine, a control decision center and a traffic controller. The traffic monitoring terminal is a data collection probe deployed at the CDN edge node. The efficiency calculation engine is based on a Storm streaming processing cluster. The control decision center includes a sliding window memory, a Bayesian dynamic parameter adjustment module and a weight allocation matrix generator. The traffic controller is a bandwidth dynamic allocation component of the SDN architecture.

[0016] The beneficial effects of the present invention are as follows: the present invention reduces bandwidth costs by establishing a mathematical model between network layer bandwidth costs and business layer economic benefits, proposing a dynamic regulation mechanism based on statistical process control, and designing a hybrid architecture combining SDN with big data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] like Figure 1 As shown, the method and system for optimizing advertisement delivery based on traffic consumption of this embodiment include the following specific steps: Step 1: Real-time collection of multi-dimensional data: The collection objects include: number of requests, ad filling response, effective exposure, and previous display cost; Step 2: Sliding time window modeling: A dynamic sliding time window (default window length T = 24 hours) is used. The data in the window is divided into multiple sub-intervals according to time slices (every 5 minutes is a storage unit). A ring buffer is used to store window data. When new data enters, the oldest data block that exceeds the window length is eliminated. Step 3: Efficiency evaluation: The flow efficiency coefficient is calculated by using a formula, and then the flow efficiency coefficient is dynamically smoothed; Step 4: Dynamic Control: First, build a control decision matrix, then set interval division and control rules, and then perform elastic bandwidth allocation; Step 5: Real-time traffic control: Bandwidth quota instructions are sent to edge nodes through the OpenFlow protocol to adjust the queue scheduling algorithm, limit the request sending rate of inefficient advertising slots, reserve bandwidth buffers for efficient advertising slots, and ensure elastic expansion in the event of burst traffic.

[0020] By establishing a mathematical model of network layer bandwidth cost and business layer economic benefits, a dynamic regulation mechanism based on statistical process control is proposed, and a hybrid architecture combining SDN and big data processing is designed to reduce bandwidth costs.

[0021] The flow efficiency coefficient is calculated using the following formula: For each ad slot , calculate its flow efficiency coefficient The specific formula is as follows: Among them, numerator: the sum of the consumption amounts corresponding to all exposures in the statistical window ( is the unit price of the i-th exposure, is the corresponding exposure); Denominator: the total number of requests generated by ad slot k during the window period .

[0022] The dynamic smoothing process uses the following formula: Exponentially Weighted Moving Average: Introducing a Smoothing Factor ,right Smooth the time series to suppress short-term fluctuations: in, This is a smoothed ad slot. In time slice The efficiency coefficient, It's a time slice Calculated based on the latest window data , after each time slice, recalculate based on the latest window data And compared with the smoothed value of the previous period Weighted fusion.

[0023] The control decision matrix includes the following formula: Global statistics calculation: System average efficiency :Count all ad slots Mean, Refers to the advertising space The smoothing efficiency coefficient of Standard Deviation :calculate The standard deviation of , which measures the dispersion of efficiency distribution; when When the traffic quota is increased, When the current quota is maintained, When the quota is reduced in stages.

[0024] The tiered decreasing quota adopts the following specific formula: .

[0025] The elastic bandwidth allocation adopts the following formula: in, is the amount of bandwidth dynamically allocated to advertisements, is the total bandwidth that can be allocated to the system, is the total number of ad slots, To control the intensity coefficient, The bandwidth ratio of high-efficiency ad slots is strengthened, and the denominator is the efficiency coefficient of all ad slots. The sum of the powers ensures that the total bandwidth allocation ratio is normalized, which can improve the flexibility of bandwidth allocation.

[0026] The real-time flow control adopts a feedback closed loop and recalculates every 30 minutes Update the regulation decision. If an ad slot is in a decreasing range for three consecutive cycles, a warning will be triggered and its effectiveness will be manually reviewed.

[0027] It can improve the overall update speed and avoid wasting traffic due to program misjudgment.

[0028] It includes a traffic monitoring terminal, an efficiency calculation engine, a control decision center and a traffic controller. The traffic monitoring terminal is a data collection probe deployed at the CDN edge node. The efficiency calculation engine is based on the Storm streaming processing cluster. The control decision center includes a sliding window memory, a Bayesian dynamic parameter adjustment module and a weight allocation matrix generator. The traffic controller is a bandwidth dynamic allocation component of the SDN architecture.

[0029] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. An advertising delivery optimization method based on traffic consumption, characterized in that: The specific steps include: Step 1: Real-time collection of multi-dimensional data: The collection objects include: number of requests, ad filling response, effective exposure, and previous display cost; Step 2: Sliding time window modeling: A dynamic sliding time window is used, with a default window length of T = 24 hours. The data in the window is divided into multiple sub-intervals according to time slices, with each 5 minutes as a storage unit. A ring buffer is used to store window data. When new data enters, the oldest data block that exceeds the window length is eliminated. Step 3: Efficiency evaluation: The flow efficiency coefficient is calculated by using a formula, and then the flow efficiency coefficient is dynamically smoothed; Step 4: Dynamic Control: First, build a control decision matrix, then set interval division and control rules, and then perform elastic bandwidth allocation; Step 5: Real-time traffic control: Bandwidth quota instructions are sent to edge nodes through the OpenFlow protocol to adjust the queue scheduling algorithm, limit the request sending rate of inefficient advertising slots, reserve bandwidth buffers for efficient advertising slots, and ensure elastic expansion in the event of burst traffic.

2. The method for optimizing advertisement delivery based on traffic consumption according to claim 1, characterized in that: The flow efficiency coefficient is calculated using the following formula: For each ad slot , calculate its flow efficiency coefficient The specific formula is as follows: Among them, the numerator is the sum of the consumption amounts corresponding to all exposures in the statistical window. is the unit price of the i-th exposure, is the corresponding exposure; Denominator: the total number of requests generated by ad slot k during the window period .

3. The method for optimizing advertisement delivery based on traffic consumption according to claim 2, characterized in that: The dynamic smoothing process uses the following formula: Exponentially Weighted Moving Average: Introducing a Smoothing Factor ,right Smooth the time series to suppress short-term fluctuations: in, This is a smoothed ad slot. In time slice The efficiency coefficient, It's a time slice Calculated based on the latest window data , after each time slice, recalculate based on the latest window data And compared with the smoothed value of the previous period Weighted fusion.

4. The method for optimizing advertisement delivery based on traffic consumption according to claim 3, characterized in that: The control decision matrix includes the following formula: Global statistics calculation: System average efficiency :Count all ad slots Mean, Refers to the advertising space The smoothing efficiency coefficient of Standard Deviation :calculate The standard deviation of , which measures the dispersion of efficiency distribution; when When the traffic quota is increased, When the current quota is maintained, When the quota is reduced in stages.

5. The method for optimizing advertisement delivery based on traffic consumption according to claim 4, characterized in that: The tiered decreasing quota adopts the following specific formula: 。 6. The method for optimizing advertisement delivery based on traffic consumption according to claim 5, characterized in that: The elastic bandwidth allocation adopts the following formula: in, is the amount of bandwidth dynamically allocated to advertisements, is the total bandwidth that can be allocated to the system, is the total number of ad slots, To control the intensity coefficient, The bandwidth ratio of high-efficiency ad slots is strengthened, and the denominator is the efficiency coefficient of all ad slots. The sum of the powers ensures that the total bandwidth allocation ratio is normalized.

7. The method for optimizing advertisement delivery based on traffic consumption according to claim 6, characterized in that: The real-time flow control adopts a feedback closed loop and recalculates every 30 minutes Update the regulation decision. If an ad slot is in a decreasing range for three consecutive cycles, a warning will be triggered and its effectiveness will be manually reviewed.

8. A system for the method for optimizing advertisement delivery based on traffic consumption as claimed in claim 7, characterized in that: It includes a traffic monitoring terminal, an efficiency calculation engine, a control decision center and a traffic controller. The traffic monitoring terminal is a data collection probe deployed at the CDN edge node. The efficiency calculation engine is based on the Storm streaming processing cluster. The control decision center includes a sliding window memory, a Bayesian dynamic parameter adjustment module and a weight allocation matrix generator. The traffic controller is a bandwidth dynamic allocation component of the SDN architecture.

Images