Advertisement delivery method and system based on advertisement drainage effect monitoring and evaluation

Abstract

The invention relates to the technical field of advertisement evaluation, and discloses an advertisement delivery method and system based on advertisement drainage effect monitoring evaluation, and the method comprises the steps: receiving an advertisement delivery plan of a target advertisement, obtaining an interface heat map of a delivery platform, and carrying out the statistics of the number of effective browsers, the advertisement click rate and the click conversion rate; the click cost and the conversion cost are further calculated in combination with advertisement input; performing statistics based on a historical benefit log to generate a benefit time table, marking the benefit quantity corresponding to each channel identifier, and performing statistics on the advertisement benefit quantity and the non-advertisement benefit quantity during the target advertisement putting period; inputting the advertisement click rate, the click conversion rate, the click cost and the conversion cost into a drainage evaluation model, and calculating drainage evaluation parameters based on a drainage evaluation calculation formula; performing numerical value matching on the drainage evaluation parameter and a preset effect interval set to determine a drainage effect rating result of the target advertisement; the method has the effect of improving the evaluation accuracy of the advertisement drainage effect.

Description

Technical Field

[0001] The present application relates to the technical field of advertising evaluation, and in particular to an advertising delivery method and system based on monitoring and evaluation of advertising traffic generation effects. Background Art

[0002] In order to increase product sales, more and more businesses choose to purchase advertising services in order to increase product sales. Therefore, the evaluation of the drainage effect of advertising services is crucial for businesses to make decisions when choosing to place advertisements. Advertisements with strong drainage effects are conducive to reducing the customer acquisition costs of businesses, and can also reduce the selection costs of customers when purchasing goods. The customer acquisition costs and selection costs are not only reflected in economic benefits. Reducing the placement of invalid advertisements and improving the drainage effect of advertisements actually saves the use of computer resources, power consumption and reduces the burden on human resources. At present, the drainage effect of advertising services is mainly determined by statistically analyzing the changes in product sales over a period of time after the advertisement is placed and evaluating them. However, there are many factors that affect product sales, and it is difficult to simply judge directly based on the changes in product sales. Therefore, the above-mentioned related technologies have the problem of inaccurate evaluation of the drainage effect of advertisements. Summary of the invention

[0003] In order to improve the accuracy of advertising traffic generation effect evaluation, the present application provides an advertising delivery method and system based on advertising traffic generation effect monitoring and evaluation.

[0004] The first invention objective of this application is achieved by adopting the following technical solution: Advertisement delivery methods based on monitoring and evaluation of advertising traffic generation effects include: Receive the target advertisement delivery plan, obtain the interface heat map of the delivery platform, and count the number of effective viewers based on the interface heat map , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost ; Generate a benefit time table based on historical benefit logs, mark the benefit amount corresponding to each channel ID in the benefit time table, and count the advertising benefit amount during the target advertising period and non-advertising benefits ; The advertisement click-through rate, click-through conversion rate, click cost, and conversion cost are input into the traffic evaluation model, and the traffic evaluation parameters are calculated based on the traffic evaluation calculation formula. ; Numerically match the traffic evaluation parameters with the preset effect interval set to determine the traffic effect rating result of the target advertisement; The advertising plan records the advertising investment, delivery platform, delivery interface, and delivery period; the historical benefit log records each benefit item and the corresponding channel identifier, and the channel identifier includes advertising channels and non-advertising channels; The drainage evaluation calculation formula is: ; ; in, is the advertising effectiveness coefficient, is the non-advertising benefit coefficient, The intercept term is used to represent the impact of the merchant's basic traffic level on the traffic evaluation parameters in the absence of targeted advertising activities; , , , is the main effect indicator, is the benchmark click cost, is the base conversion cost, , , , is the main effect weight corresponding to each main effect indicator; is the first-order error term, which is used to represent the impact of omitted variables and random errors on drainage assessment parameters.

[0005] By adopting the above technical solution, the advertising delivery plan of the target advertisement is received to determine the delivery information of the target advertisement such as the advertising investment, delivery platform, delivery interface, and delivery time period, and the interface heat map of the delivery platform is obtained to count the number of effective viewers, advertisement click-through rate, and click-through conversion rate of the target advertisement, and further calculate the click cost and conversion cost in combination with the advertising investment; based on the historical benefit log, the occurrence time of various benefit events and the time distribution of each benefit event are obtained, and the benefit event form is generated according to the historical benefit log statistics, and the benefit quantity corresponding to each channel identifier is marked, so as to count the advertising benefit amount and non-advertising benefit amount during the target advertisement delivery period, so as to facilitate the subsequent evaluation of the contribution of the target advertisement to the merchant's traffic diversion effect. ; Input the advertisement click-through rate, click-through conversion rate, click cost, and conversion cost into the traffic evaluation model to calculate the traffic evaluation parameters according to the traffic evaluation calculation formula, wherein the traffic evaluation parameters include an intercept term used to represent the basic traffic level of the merchant, the product of the advertisement click-through rate and the corresponding main effect weight, the product of the click-through conversion rate and the corresponding main effect weight, the calculation term of the click cost, the benchmark click cost, and the corresponding main effect weight, the calculation term of the conversion cost, the benchmark conversion cost, and the corresponding main effect weight, and the first-order error term, so as to evaluate the comprehensive traffic effect of the target advertisement according to each main effect indicator; numerically match the traffic evaluation parameters with the preset effect interval set, and determine the traffic effect rating result of the target advertisement based on the matching result.

[0006] In a preferred example of the present application: In the drainage evaluation calculation formula: ; in, It is a synergistic effect indicator of advertising click-through rate and click-through conversion rate. Synergy effect indicator The corresponding interaction weights are, It is the synergy indicator of advertising click-through rate and click cost. Synergy effect indicator The corresponding interaction weights are, It is a synergistic effect indicator of click-through conversion rate and conversion cost. Synergy effect indicator The corresponding interaction term weights; is the second-order error term, which is used to represent the impact of random errors on drainage assessment parameters.

[0007] By adopting the above technical solution, the first-order error term also includes the synergistic effect indicators of advertising click-through rate and click-through conversion rate, advertising click-through rate and click cost, click-through conversion rate and conversion cost, and the product of the corresponding interaction term weights, as well as the second-order error term, which facilitates further evaluation of the impact of possible synergistic effects among the four main effect indicators of advertising click-through rate, click-through conversion rate, click cost, and conversion cost on the drainage evaluation parameters.

[0008] In a preferred example of the present application: the receiving advertisement delivery plan of the target advertisement, obtaining the interface heat map of the delivery platform, and counting the number of effective browsing users based on the interface heat map , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost ,include: Receive the target advertisement delivery plan, extract the corresponding interface heat map based on the delivery platform, and count the number of visitors based on the interface heat map , number of effective viewers, number of ad clicks and number of ad conversions; Calculate the quotient of the number of ad clicks and the number of effective viewers to get the ad click rate, and further calculate the quotient of the number of ad conversions and the number of ad clicks to get the click-through conversion rate; Calculate the quotient of the number of ad clicks and the advertising investment to get the click cost, and calculate the quotient of the number of ad conversions and the advertising investment to get the conversion cost; The number of visitors refers to the number of accounts that visit the page where the target advertisement is located, the number of effective viewers refers to the number of accounts that stay on the page where the target advertisement is displayed for more than a certain period of time, and the number of advertisement conversions refers to orders that are completed through clicking on the advertisement channel.

[0009] By adopting the above technical solution, an advertising delivery plan for a target advertisement is received, a corresponding interface heat map is extracted based on the delivery platform of the target advertisement, and data such as the number of visitors to the interface where the target advertisement is located, the number of effective viewers of the target advertisement, the number of advertisement clicks, and the number of advertisement conversions are counted based on the interface heat map, so as to facilitate subsequent evaluation of the traffic-generating effect of the target advertisement; the advertisement click-through rate is determined based on the quotient of the number of advertisement clicks and the number of effective viewers, and the click-through conversion rate is determined based on the quotient of the number of advertisement conversions and the number of advertisement clicks, so as to evaluate the attractiveness of the advertising campaign to customers; the click cost is determined based on the quotient of the number of advertisement clicks and the advertising investment, and the conversion cost is determined based on the quotient of the number of advertisement conversions and the advertising investment, so as to evaluate the cost-effectiveness of the investment in the advertising campaign relative to its traffic-generating effect.

[0010] In a preferred example of the present application: In the drainage evaluation calculation formula: ; ; ; is the basic drainage coefficient, is the adjacent sales parameter, where is the competitive product benefit of each neighboring competitive product merchant, is the distinguishing mark of the neighboring competing merchants, and n is the number of neighboring competing merchants.

[0011] By adopting the above technical solution, the intercept term is determined by the basic drainage coefficient and the adjacent sales parameter. Since advertising also has a certain promoting effect on the sales of similar competing products, the adjacent sales parameter is the average value of the competitive product benefit data of neighboring competing merchants. There is no need to distinguish whether the competitive product benefit of neighboring competing merchants is the benefit of the advertising channel, and the basic drainage coefficient is determined based on the ratio of non-advertising benefit to total benefit, which makes it easier to improve the accuracy of the assessment of the basic drainage level of merchants in the absence of targeted advertising activities.

[0012] In a preferred example of the present application: In the drainage evaluation calculation formula, the weight of each main effect , , , and the weights of each interaction term , , The setting method is: When the merchant to be evaluated has no historical advertising activity records, the traffic evaluation calculation formula of similar merchants is matched based on the attribute information of the merchant to be evaluated and set as the initial traffic evaluation calculation formula; When the merchant to be evaluated has a record of historical advertising activities, obtain the advertising evaluation data set of all historical advertising activities, and substitute it into the undetermined drainage evaluation calculation formula with the weights of each main effect and the weights of the interaction items as unknowns to generate several historical advertising evaluation calculation formulas; Input the historical advertising evaluation formula into Python and use the statsmodels library to perform stepwise regression algorithm to set the weight of each main effect. , , , and the weights of each interaction term , , , generate the traffic evaluation calculation formula corresponding to the merchant to be evaluated; The attribute information includes several items of data such as business type, business scale and business circle traffic; the advertising evaluation data set includes advertising benefit coefficient , non-advertising benefit coefficient , advertising effectiveness , non-advertising benefits , Ad click-through rate , click-through conversion rate , click cost , conversion cost , effective number of visitors , advertising investment , Benchmark Click Cost , Baseline conversion cost , first-order error term .

[0013] By adopting the above technical solution, for merchants to be evaluated that have no historical advertising activity records, the traffic evaluation formula of similar merchants is matched according to their business type, merchant scale, business district traffic flow and other attribute information as the initial traffic evaluation formula, so as to evaluate the drainage effect of the target advertisement; for merchants to be evaluated that have historical advertising activity records, the advertising evaluation data set of all historical advertising activities is obtained, and substituted into the pending drainage evaluation formula with the main effect weights and interaction item weights as unknowns, so as to generate several historical advertising evaluation formulas for subsequent stepwise regression processing; each historical advertising evaluation formula is input into Python and processed by the stepwise regression algorithm using the statsmodels library to calculate and set the main effect weights , , , and the weights of each interaction term , , , thereby generating a traffic evaluation formula that is specially optimized for the merchant to be evaluated, in order to improve the accuracy of the evaluation of the advertising traffic effect.

[0014] The second invention objective of this application is achieved by the following technical solution: An advertisement delivery system based on advertisement diversion effect monitoring and evaluation is applied to any of the above-mentioned advertisement delivery methods based on advertisement diversion effect monitoring and evaluation, including: The interface heat map statistics module is used to receive the advertising plan of the target advertisement, obtain the interface heat map of the delivery platform, and count the number of effective viewers based on the interface heat map. , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost ; The benefit quantity classification statistics module is used to generate benefit time tables based on historical benefit logs, mark the benefit quantities corresponding to various channel identifiers in the benefit time tables, and count the advertising benefit quantities during the target advertising delivery period. and non-advertising benefits ; The flow evaluation parameter calculation module is used to input the advertisement click-through rate, click-through conversion rate, click cost, and conversion cost into the flow evaluation model, and calculate the flow evaluation parameters based on the flow evaluation calculation formula. ; A traffic diversion effect rating module is used to numerically match the traffic diversion evaluation parameters with a preset effect interval set to determine the traffic diversion effect rating result of the target advertisement; The advertising plan records the advertising investment, delivery platform, delivery interface, and delivery period; the historical benefit log records each benefit item and the corresponding channel identifier, and the channel identifier includes advertising channels and non-advertising channels; The drainage evaluation calculation formula is: ; ; in, is the advertising effectiveness coefficient, is the non-advertising benefit coefficient, The intercept term is used to represent the impact of the merchant's basic traffic level on the traffic evaluation parameters in the absence of targeted advertising activities; , , , is the main effect indicator, is the benchmark click cost, is the base conversion cost, , , , is the main effect weight corresponding to each main effect indicator; is the first-order error term, which is used to represent the impact of omitted variables and random errors on drainage assessment parameters.

[0015] In a preferred example of the present application: the interface heat map statistics module includes: The interface heat map extraction submodule is used to receive the advertising plan of the target advertisement, extract the corresponding interface heat map based on the delivery platform, and count the number of visitors based on the interface heat map , number of effective viewers, number of ad clicks and number of ad conversions; A click-through conversion rate calculation submodule is used to calculate the quotient of the number of advertisement clicks and the number of effective viewers to obtain the advertisement click-through rate, and further calculate the quotient of the number of advertisement conversions and the number of advertisement clicks to obtain the click-through conversion rate; The conversion cost calculation submodule is used to calculate the quotient of the number of advertisement clicks and the advertisement investment to obtain the click cost, and calculate the quotient of the number of advertisement conversions and the advertisement investment to obtain the conversion cost; The number of visitors refers to the number of accounts that visit the page where the target advertisement is located, the number of effective viewers refers to the number of accounts that stay on the page where the target advertisement is displayed for more than a certain period of time, and the number of advertisement conversions refers to orders that are completed through clicking on the advertisement channel.

[0016] In a preferred example of the present application: the drainage evaluation parameter calculation module includes: The initial traffic evaluation calculation formula setting submodule is used to match the traffic evaluation calculation formula of similar merchants based on the attribute information of the merchant to be evaluated and set it as the initial traffic evaluation calculation formula when the merchant to be evaluated has no historical advertising activity records; The historical advertising evaluation calculation formula generation submodule is used to obtain the advertising evaluation data set of all historical advertising activities when the merchant to be evaluated has historical advertising activity records, and substitute the undetermined drainage evaluation calculation formula with the weights of each main effect and the weights of the interaction items as unknowns to generate several historical advertising evaluation calculation formulas; The submodule for generating the traffic evaluation formula is used to input the historical advertising evaluation formula into Python and use the statsmodels library to perform stepwise regression algorithm processing to set the weights of each main effect. , , , and the weights of each interaction term , , , generate the traffic evaluation calculation formula corresponding to the merchant to be evaluated; The attribute information includes several items of data such as business type, business scale and business circle traffic; the advertising evaluation data set includes advertising benefit coefficient , non-advertising benefit coefficient , advertising effectiveness , non-advertising benefits , Ad click-through rate , click-through conversion rate , click cost , conversion cost , effective number of visitors , advertising investment , Benchmark Click Cost , Baseline conversion cost , first-order error term .

[0017] The third invention objective of this application is achieved by the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned advertising delivery method based on monitoring and evaluation of advertising traffic diversion effects are implemented.

[0018] The fourth invention objective of this application is achieved by the following technical solution: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned advertising delivery method based on monitoring and evaluation of advertising traffic diversion effects.

[0019] In summary, the present application includes at least one of the following beneficial technical effects: 1. Receive the target advertisement delivery plan to determine the target advertisement delivery information such as advertising investment, delivery platform, delivery interface, delivery time period, etc., obtain the interface heat map of the delivery platform, count the number of effective viewers, advertisement click-through rate, and click-through conversion rate of the target advertisement, and further calculate the click cost and conversion cost based on the advertising investment; obtain the occurrence time of various benefit events based on the historical benefit log, as well as the time distribution of each benefit event, generate a benefit event form based on the historical benefit log statistics, and mark the benefit quantity corresponding to various channel identifiers, so as to count the advertising benefit quantity and non-advertising benefit quantity during the target advertisement delivery period, so as to facilitate the subsequent evaluation of the contribution of the target advertisement to the merchant's traffic diversion effect; The click rate, click-through rate, click cost, and conversion cost are input into the drainage evaluation model to calculate the drainage evaluation parameters according to the drainage evaluation calculation formula, wherein the drainage evaluation parameters include an intercept term for representing the basic drainage level of the merchant, the product of the advertisement click-through rate and the corresponding main effect weight, the product of the click-through rate and the corresponding main effect weight, the calculation term of the click cost, the benchmark click cost, and the corresponding main effect weight, the calculation term of the conversion cost, the benchmark conversion cost, and the corresponding main effect weight, and a first-order error term, so as to evaluate the comprehensive drainage effect of the target advertisement according to various main effect indicators; the drainage evaluation parameters are numerically matched with the preset effect interval set, and the drainage effect rating result of the target advertisement is determined based on the matching result.

[0020] 2. The first-order error term also includes the synergistic effect indicators of advertising click-through rate and click-through conversion rate, advertising click-through rate and click cost, click-through conversion rate and conversion cost, and the product of the corresponding interaction term weights, as well as the second-order error term, which is convenient for further evaluating the impact of the possible synergistic effects between the four main effect indicators of advertising click-through rate, click-through conversion rate, click cost, and conversion cost on the drainage evaluation parameters.

[0021] 3. Receive the advertising delivery plan of the target advertisement, extract the corresponding interface heat map based on the delivery platform of the target advertisement, and count the number of visitors to the interface where the target advertisement is located, the number of effective viewers, the number of advertisement clicks and the number of advertisement conversions of the target advertisement based on the interface heat map, so as to facilitate the subsequent evaluation of the traffic diversion effect of the target advertisement; determine the advertisement click-through rate based on the quotient of the number of advertisement clicks and the number of effective viewers, and determine the click-through conversion rate based on the quotient of the number of advertisement conversions and the number of advertisement clicks, so as to evaluate the attractiveness of the advertising campaign to customers; determine the click cost based on the quotient of the number of advertisement clicks and the advertising investment, and determine the conversion cost based on the quotient of the number of advertisement conversions and the advertising investment, so as to evaluate the cost-effectiveness of the investment in the advertising campaign relative to its traffic diversion effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of the advertising delivery method based on the monitoring and evaluation of the advertising traffic diversion effect in the first embodiment of the present application.

[0023] Figure 2 It is a principle block diagram of an advertising delivery system based on advertising traffic effect monitoring and evaluation in Example 2 of the present application.

[0024] Figure 3 It is a schematic diagram of the equipment in Example 3 of the present application. DETAILED DESCRIPTION

[0025] The following is combined with Figures 1 to 3 This application is described in further detail.

[0026] Embodiment 1 Reference Figure 1 The present application discloses an advertisement delivery method based on advertisement diversion effect monitoring and evaluation, which specifically comprises the following steps: S10: Receive the advertising plan of the target advertisement, obtain the interface heat map of the delivery platform, and count the number of effective viewers based on the interface heat map , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost .

[0027] In this embodiment, the advertisement delivery plan records the advertisement investment, delivery platform, delivery interface, and delivery period, wherein the delivery interface refers to the interface position of the advertisement on the delivery platform, and the delivery interface includes multiple pages.

[0028] Specifically, the advertising delivery plan of the target advertisement is received to determine the delivery information of the target advertisement such as the advertising investment, delivery platform, delivery interface, and delivery time period, and the interface heat map of the delivery platform is obtained to count the number of effective viewers of the target advertisement, the advertisement click-through rate, and the click-through conversion rate, and further calculate the click cost and conversion cost based on the advertising investment.

[0029] Wherein, in step S10, it includes: S11: receiving the advertising plan of the target advertisement, extracting the corresponding interface heat map based on the delivery platform, and counting the number of visitors based on the interface heat map , effective browsing numbers, ad clicks and ad conversions.

[0030] In this embodiment, the number of visitors refers to the number of accounts that visit the page where the target advertisement is located, the number of effective viewers refers to the number of accounts that stay on the page where the target advertisement is displayed for more than a certain period of time, where the number of people can also be set to person-times according to actual needs; the number of advertising conversions refers to orders that are completed through clicking on the advertising channel.

[0031] Specifically, an advertising delivery plan for a target advertisement is received, a corresponding interface heat map is extracted based on the delivery platform of the target advertisement, and data such as the number of visitors to the interface where the target advertisement is located, the number of effective viewers of the target advertisement, the number of advertisement clicks, and the number of advertisement conversions are counted based on the interface heat map, so as to facilitate subsequent evaluation of the drainage effect of the target advertisement.

[0032] S12: Calculate the quotient of the number of advertisement clicks and the number of effective page views to obtain the advertisement click rate, and further calculate the quotient of the number of advertisement conversions and the number of advertisement clicks to obtain the click conversion rate.

[0033] Specifically, the advertisement click rate is determined based on the quotient of the number of advertisement clicks and the number of effective viewers, and the click-through conversion rate is determined based on the quotient of the number of advertisement conversions and the number of advertisement clicks, so as to evaluate the attractiveness level of the advertising campaign to customers.

[0034] S13: Calculate the quotient of the number of advertisement clicks and the advertisement investment to obtain the click cost, and calculate the quotient of the number of advertisement conversions and the advertisement investment to obtain the conversion cost.

[0035] Specifically, the click cost is determined based on the quotient of the number of advertisement clicks and the advertisement investment, and the conversion cost is determined based on the quotient of the number of advertisement conversions and the advertisement investment, so as to evaluate the cost-effectiveness of the investment in the advertising campaign relative to its traffic-generating effect.

[0036] S20: Generate a benefit time table based on historical benefit logs, mark the benefit amount corresponding to each channel identifier in the benefit time table, and count the advertising benefit amount during the target advertising delivery period and non-advertising benefits .

[0037] In this embodiment, the historical benefit log records each benefit item and the corresponding channel identifier, wherein the benefit item may be one or more of a transaction, an order, a payment, a favorite / follow / add to cart, and a link click to view behavior. When different types of benefit items are used to count the corresponding benefit quantities, different weight coefficients may be set according to their different economic benefits to the merchant; channel identifiers include advertising channels and non-advertising channels.

[0038] Specifically, based on the historical benefit logs, we can know the occurrence time of various benefit events and the time distribution of each benefit event. According to the historical benefit log statistics, we can generate a benefit event form, and mark the benefit quantities corresponding to various channel identifiers, so as to count the advertising benefit and non-advertising benefit during the target advertising period, which is convenient for the subsequent evaluation of the contribution of the target advertising to the merchant's traffic generation effect.

[0039] S30: Input the advertisement click-through rate, click-through conversion rate, click cost, and conversion cost into the traffic evaluation model, and calculate the traffic evaluation parameters based on the traffic evaluation calculation formula. .

[0040] In this embodiment, the drainage evaluation model has a built-in drainage evaluation calculation formula; the drainage evaluation calculation formula is: ; ; in, is the advertising effectiveness coefficient, is the non-advertising benefit coefficient, The intercept term is used to represent the impact of the merchant's basic traffic level on the traffic evaluation parameters in the absence of targeted advertising activities; , , , is the main effect indicator, is the benchmark click cost, is the base conversion cost, , , , is the main effect weight corresponding to each main effect indicator; is the first-order error term, which is used to represent the impact of omitted variables and random errors on the drainage evaluation parameters; among them, the main effect index is used to evaluate the direct impact of these coefficients on the drainage evaluation parameters, the benchmark click cost is used to represent the benchmark value of the click cost set within the industry or the merchant, and the benchmark conversion cost is used to represent the benchmark value of the conversion cost set within the industry or the merchant; the weight of each main effect can be set according to the actual needs of the evaluation of the advertising drainage effect; the weight of each interaction item can be set according to the actual needs of the evaluation of the advertising drainage effect.

[0041] Specifically, the advertisement click-through rate, click-through conversion rate, click cost, and conversion cost are input into the traffic evaluation model to calculate the traffic evaluation parameters according to the traffic evaluation formula, wherein the traffic evaluation parameters include an intercept term for representing the basic traffic level of the merchant, the product of the advertisement click-through rate and the corresponding main effect weight, the product of the click-through conversion rate and the corresponding main effect weight, a calculation term of the click cost, the benchmark click cost, and the corresponding main effect weight, a calculation term of the conversion cost, the benchmark conversion cost, and the corresponding main effect weight, and a first-order error term, so as to facilitate the evaluation of the comprehensive traffic effect of the target advertisement according to various main effect indicators.

[0042] Furthermore, the drainage evaluation calculation formula is: ; in, It is a synergistic effect indicator of advertising click-through rate and click-through conversion rate. Synergy effect indicator The corresponding interaction weights are, It is the synergy indicator of advertising click-through rate and click cost. Synergy effect indicator The corresponding interaction weights are, It is a synergistic effect indicator of click-through conversion rate and conversion cost. Synergy effect indicator The corresponding interaction term weights; is the second-order error term, which is used to represent the impact of random errors on drainage assessment parameters.

[0043] Specifically, the first-order error term also includes the synergistic effect indicators of advertising click-through rate and click-through conversion rate, advertising click-through rate and click cost, click-through conversion rate and conversion cost, and the product of the corresponding interaction term weights, as well as the second-order error term, which is convenient for further evaluating the impact of the possible synergistic effects between the four main effect indicators of advertising click-through rate, click-through conversion rate, click cost, and conversion cost on the drainage evaluation parameters.

[0044] Furthermore, the drainage evaluation calculation formula is: ; ; ; is the basic drainage coefficient, is the adjacent sales parameter, where is the competitive product benefit of each neighboring competitive product merchant, is a distinguishing mark of neighboring competing merchants, n is the number of neighboring competing merchants, wherein the upper and lower scripts of the summation item are not shown, and those skilled in the art may set and adjust it according to actual needs. A neighboring competing merchant refers to a merchant that is within a certain range from the merchant to be evaluated and has competing business with the merchant to be evaluated. The specific scope of recognition of the neighboring relationship may be determined based on the delivery range and the distance from the merchant to be evaluated.

[0045] Specifically, the intercept term is determined by the basic drainage coefficient and the adjacent sales parameter. Since advertising also has a certain promoting effect on the sales of similar competing products, the adjacent sales parameter is the average value of the competitive product benefit data of neighboring competing merchants. There is no need to distinguish whether the competitive product benefit of neighboring competing merchants is the benefit of the advertising channel. The basic drainage coefficient is determined based on the ratio of non-advertising benefit to total benefit, which facilitates improving the accuracy of the assessment of the basic drainage level of merchants in the absence of targeted advertising activities.

[0046] Among them, in step S30, in the drainage evaluation calculation formula, the weight of each main effect , , , and the weights of each interaction term , , The setting methods include: S31: When the merchant to be evaluated has no historical advertising activity record, the traffic evaluation calculation formula of similar merchants is matched based on the attribute information of the merchant to be evaluated and set as the initial traffic evaluation calculation formula.

[0047] In this embodiment, the attribute information includes several items of data including business type, merchant scale and traffic volume in the business district. The specific indicator type and indicator quantity can be set and adjusted according to actual needs.

[0048] Specifically, for merchants to be evaluated that have no historical records of advertising activities, the traffic evaluation formula of similar merchants is matched according to their business type, merchant scale, business district traffic flow and other attribute information as the initial traffic evaluation formula to evaluate the traffic diversion effect of the target advertisement.

[0049] S32: When the merchant to be evaluated has a record of historical advertising activities, obtain the advertising evaluation data set of all historical advertising activities, and substitute it into the undetermined drainage evaluation calculation formula with the weights of each main effect and the weights of the interaction items as unknowns to generate several historical advertising evaluation calculation formulas.

[0050] In this embodiment, the advertisement evaluation data set includes the advertisement benefit coefficient , non-advertising benefit coefficient , advertising effectiveness , non-advertising benefits , Ad click-through rate , click-through conversion rate , click cost , conversion cost , effective number of visitors , advertising investment , Benchmark Click Cost , Baseline conversion cost , first-order error term .

[0051] Specifically, for merchants to be evaluated that have historical records of advertising activities, the advertising evaluation data set of all historical advertising activities is obtained and substituted into the to-be-determined traffic evaluation calculation formula with the weights of each main effect and the weights of the interaction terms as unknowns, thereby generating several historical advertising evaluation calculation formulas for subsequent stepwise regression processing.

[0052] S33: Input the historical advertising evaluation formula into Python and use the statsmodels library to perform stepwise regression algorithm to set the weights of each main effect , , , and the weights of each interaction term , , , generate the corresponding drainage evaluation calculation formula for the merchant to be evaluated.

[0053] Specifically, the historical advertising evaluation formulas are input into Python and processed using the statsmodels library for stepwise regression to calculate and set the weights of each main effect. , , , and the weights of each interaction term , , , thereby generating a traffic evaluation formula that is specially optimized for the merchant to be evaluated, in order to improve the accuracy of the evaluation of the advertising traffic effect.

[0054] S40: numerically matching the traffic evaluation parameter with a preset effect interval set to determine a traffic effect rating result of the target advertisement.

[0055] Specifically, the traffic evaluation parameters are numerically matched with a preset effect interval set, and the traffic effect rating result of the target advertisement is determined based on the matching result.

[0056] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0057] Embodiment 2

[0058] An advertisement delivery system based on advertisement diversion effect monitoring and evaluation, the advertisement delivery system based on advertisement diversion effect monitoring and evaluation corresponds to the advertisement delivery method based on advertisement diversion effect monitoring and evaluation in the above-mentioned embodiment.

[0059] like Figure 2 As shown in the figure, the advertising delivery system based on the monitoring and evaluation of advertising diversion effect includes an interface heat map statistics module, a benefit classification statistics module, a diversion evaluation parameter calculation module and a diversion effect rating module. The detailed description of each functional module is as follows: The interface heat map statistics module is used to receive the advertising plan of the target advertisement, obtain the interface heat map of the delivery platform, and count the number of effective viewers based on the interface heat map. , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost ; The benefit classification statistics module is used to generate benefit time tables based on historical benefit logs, mark the benefit quantities corresponding to various channel identifiers in the benefit time tables, and count the advertising benefit quantities during the target advertising delivery period. and non-advertising benefits ; The flow evaluation parameter calculation module is used to input the advertisement click rate, click conversion rate, click cost, and conversion cost into the flow evaluation model, and calculate the flow evaluation parameters based on the flow evaluation calculation formula. ; The traffic diversion effect rating module is used to numerically match the traffic diversion evaluation parameters with the preset effect interval set to determine the traffic diversion effect rating result of the target advertisement.

[0060] Among them, the interface heat map statistics module also includes: The interface heat map extraction submodule is used to receive the advertising plan of the target advertisement, extract the corresponding interface heat map based on the delivery platform, and count the number of visitors based on the interface heat map , number of effective viewers, number of ad clicks and number of ad conversions; A click-through conversion rate calculation submodule is used to calculate the quotient of the number of advertisement clicks and the number of effective viewers to obtain the advertisement click-through rate, and further calculate the quotient of the number of advertisement conversions and the number of advertisement clicks to obtain the click-through conversion rate; The conversion cost calculation submodule is used to calculate the quotient of the number of advertisement clicks and the advertisement investment to obtain the click cost, and calculate the quotient of the number of advertisement conversions and the advertisement investment to obtain the conversion cost.

[0061] Among them, the drainage evaluation parameter calculation module also includes: The initial traffic evaluation calculation formula setting submodule is used to match the traffic evaluation calculation formula of similar merchants based on the attribute information of the merchant to be evaluated and set it as the initial traffic evaluation calculation formula when the merchant to be evaluated has no historical advertising activity records; The historical advertising evaluation calculation formula generation submodule is used to obtain the advertising evaluation data set of all historical advertising activities when the merchant to be evaluated has historical advertising activity records, and substitute the undetermined drainage evaluation calculation formula with the weights of each main effect and the weights of the interaction items as unknowns to generate several historical advertising evaluation calculation formulas; The submodule for generating the traffic evaluation formula is used to input the historical advertising evaluation formula into Python and use the statsmodels library to perform stepwise regression algorithm processing to set the weights of each main effect. , , , and the weights of each interaction term , , , generate the corresponding drainage evaluation calculation formula for the merchant to be evaluated.

[0062] For the specific limitations of the advertising delivery system based on advertising traffic effect monitoring and evaluation, please refer to the limitations of the advertising delivery method based on advertising traffic effect monitoring and evaluation in the above text, which will not be repeated here; each module in the above-mentioned advertising delivery system based on advertising traffic effect monitoring and evaluation can be fully or partially implemented by software, hardware and a combination thereof; each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0063] Embodiment 3

[0064] A computer device, which may be a server, may have an internal structure as shown in Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as advertising delivery plans, interface heat maps, effective browsing numbers, advertising click-through rates, click-through conversion rates, advertising investment, click costs, conversion costs, historical benefit logs, benefit time forms, various channel identifiers, advertising benefit quantities, non-advertising benefit quantities, drainage evaluation models, drainage evaluation calculation formulas, drainage evaluation parameters, effect interval sets, drainage effect rating results, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an advertising delivery method based on monitoring and evaluation of advertising drainage effects is implemented.

[0065] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: S10: Receive the advertising plan of the target advertisement, obtain the interface heat map of the delivery platform, and count the number of effective viewers based on the interface heat map , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost ; S20: Generate a benefit time table based on historical benefit logs, mark the benefit amount corresponding to each channel identifier in the benefit time table, and count the advertising benefit amount during the target advertising delivery period and non-advertising benefits ; S30: Input the advertisement click-through rate, click-through conversion rate, click cost, and conversion cost into the traffic evaluation model, and calculate the traffic evaluation parameters based on the traffic evaluation calculation formula. ; S40: numerically matching the traffic evaluation parameter with a preset effect interval set to determine a traffic effect rating result of the target advertisement.

[0066] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: S10: Receive the target advertisement delivery plan, obtain the interface heat map of the delivery platform, and count the number of effective viewers based on the interface heat map , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost ; S20: Generate a benefit time table based on historical benefit logs, mark the benefit amount corresponding to each channel identifier in the benefit time table, and count the advertising benefit amount during the target advertising delivery period and non-advertising benefits ; S30: Input the advertisement click-through rate, click-through conversion rate, click cost, and conversion cost into the traffic evaluation model, and calculate the traffic evaluation parameters based on the traffic evaluation calculation formula. ; S40: numerically matching the traffic evaluation parameter with a preset effect interval set to determine a traffic effect rating result of the target advertisement.

[0067] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink), DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0068] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0069] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the features thereof may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An advertisement delivery method based on advertisement traffic effect monitoring and evaluation, characterized in that: include: Receive the target advertisement delivery plan, obtain the interface heat map of the delivery platform, and count the number of effective viewers based on the interface heat map , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost ; Generate a benefit time table based on historical benefit logs, mark the benefit amount corresponding to each channel ID in the benefit time table, and count the advertising benefit amount during the target advertising period and non-advertising benefits ; The advertisement click-through rate, click-through conversion rate, click cost, and conversion cost are input into the traffic evaluation model, and the traffic evaluation parameters are calculated based on the traffic evaluation calculation formula. ; Numerically match the traffic evaluation parameters with the preset effect interval set to determine the traffic effect rating result of the target advertisement; The advertising plan records the advertising investment, delivery platform, delivery interface, and delivery period; the historical benefit log records each benefit item and the corresponding channel identifier, and the channel identifier includes advertising channels and non-advertising channels; The drainage evaluation calculation formula is: ； ； in, is the advertising effectiveness coefficient, is the non-advertising benefit coefficient, The intercept term is used to represent the impact of the merchant's basic traffic level on the traffic evaluation parameters in the absence of targeted advertising activities; , , , is the main effect indicator, is the benchmark click cost, is the base conversion cost, , , , is the main effect weight corresponding to each main effect indicator; is the first-order error term, which is used to represent the impact of omitted variables and random errors on drainage assessment parameters.

2. The method for delivering advertisements based on monitoring and evaluation of advertisement diversion effects according to claim 1, characterized in that: In the drainage evaluation calculation formula: ； in, It is a synergistic effect indicator of advertising click-through rate and click-through conversion rate. Synergy effect indicator The corresponding interaction weights are, It is the synergy indicator of advertising click-through rate and click cost. Synergy effect indicator The corresponding interaction weights are, It is a synergistic effect indicator of click-through conversion rate and conversion cost. Synergy effect indicator The corresponding interaction term weights; is the second-order error term, which is used to represent the impact of random errors on drainage assessment parameters.

3. The method for delivering advertisements based on monitoring and evaluation of advertisement diversion effects according to claim 1, characterized in that: The receiving advertisement delivery plan of the target advertisement, obtaining the interface heat map of the delivery platform, and counting the number of effective viewers based on the interface heat map , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost ,include: Receive the target advertisement delivery plan, extract the corresponding interface heat map based on the delivery platform, and count the number of visitors based on the interface heat map , number of effective viewers, number of ad clicks and number of ad conversions; Calculate the quotient of the number of ad clicks and the number of effective viewers to get the ad click rate, and further calculate the quotient of the number of ad conversions and the number of ad clicks to get the click-through conversion rate; Calculate the quotient of the number of ad clicks and the advertising investment to get the click cost, and calculate the quotient of the number of ad conversions and the advertising investment to get the conversion cost; The number of visitors refers to the number of accounts that visit the page where the target advertisement is located, the number of effective viewers refers to the number of accounts that stay on the page where the target advertisement is displayed for more than a certain period of time, and the number of advertisement conversions refers to orders that are completed through clicking on the advertisement channel.

4. The method for delivering advertisements based on monitoring and evaluation of advertisement diversion effects according to claim 1, characterized in that: In the drainage evaluation calculation formula: ； ； ； is the basic drainage coefficient, is the adjacent sales parameter, where is the competitive product benefit of each neighboring competitive product merchant, is the distinguishing mark of the neighboring competing merchants, and n is the number of neighboring competing merchants.

5. The method for delivering advertisements based on monitoring and evaluation of advertisement diversion effects according to claim 2, characterized in that: In the drainage evaluation calculation formula, the weight of each main effect , , , and the weights of each interaction term , , The setting method is: When the merchant to be evaluated has no historical advertising activity records, the traffic evaluation calculation formula of similar merchants is matched based on the attribute information of the merchant to be evaluated and set as the initial traffic evaluation calculation formula; When the merchant to be evaluated has a record of historical advertising activities, obtain the advertising evaluation data set of all historical advertising activities, and substitute it into the undetermined drainage evaluation calculation formula with the weights of each main effect and the weights of the interaction items as unknowns to generate several historical advertising evaluation calculation formulas; Input the historical advertising evaluation formula into Python and use the statsmodels library to perform stepwise regression algorithm to set the weight of each main effect. , , , and the weights of each interaction term , , , generate the traffic evaluation calculation formula corresponding to the merchant to be evaluated; The attribute information includes several items of data such as business type, business scale and business circle traffic; the advertising evaluation data set includes advertising benefit coefficient , non-advertising benefit coefficient , advertising effectiveness , non-advertising benefits , Ad click-through rate , click-through conversion rate , click cost , conversion cost , effective number of visitors , advertising investment , Benchmark Click Cost , Baseline conversion cost , first-order error term .

6. An advertising delivery system based on monitoring and evaluation of advertising traffic diversion effects, characterized in that: The advertising delivery method based on the monitoring and evaluation of the advertising traffic diversion effect as applied to any one of claims 1 to 5 comprises: The interface heat map statistics module is used to receive the advertising plan of the target advertisement, obtain the interface heat map of the delivery platform, and count the number of effective viewers based on the interface heat map. , Ad click-through rate , click-through conversion rate , combined with advertising investment Further calculation of click cost , conversion cost ; The benefit quantity classification statistics module is used to generate benefit time tables based on historical benefit logs, mark the benefit quantities corresponding to various channel identifiers in the benefit time tables, and count the advertising benefit quantities during the target advertising delivery period. and non-advertising benefits ; The flow evaluation parameter calculation module is used to input the advertisement click-through rate, click-through conversion rate, click cost, and conversion cost into the flow evaluation model, and calculate the flow evaluation parameters based on the flow evaluation calculation formula. ; A traffic diversion effect rating module is used to numerically match the traffic diversion evaluation parameters with a preset effect interval set to determine the traffic diversion effect rating result of the target advertisement; The advertising plan records the advertising investment, delivery platform, delivery interface, and delivery period; the historical benefit log records each benefit item and the corresponding channel identifier, and the channel identifier includes advertising channels and non-advertising channels; The drainage evaluation calculation formula is: ； ； in, is the advertising effectiveness coefficient, is the non-advertising benefit coefficient, The intercept term is used to represent the impact of the merchant's basic traffic level on the traffic evaluation parameters in the absence of targeted advertising activities; , , , is the main effect indicator, is the benchmark click cost, is the base conversion cost, , , , is the main effect weight corresponding to each main effect indicator; is the first-order error term, which is used to represent the impact of omitted variables and random errors on drainage assessment parameters.

7. The advertisement delivery system based on advertisement diversion effect monitoring and evaluation according to claim 6 is characterized in that: The interface heat map statistics module includes: The interface heat map extraction submodule is used to receive the advertising plan of the target advertisement, extract the corresponding interface heat map based on the delivery platform, and count the number of visitors based on the interface heat map , number of effective viewers, number of ad clicks and number of ad conversions; A click-through conversion rate calculation submodule is used to calculate the quotient of the number of advertisement clicks and the number of effective viewers to obtain the advertisement click-through rate, and further calculate the quotient of the number of advertisement conversions and the number of advertisement clicks to obtain the click-through conversion rate; The conversion cost calculation submodule is used to calculate the quotient of the number of advertisement clicks and the advertisement investment to obtain the click cost, and calculate the quotient of the number of advertisement conversions and the advertisement investment to obtain the conversion cost; The number of visitors refers to the number of accounts that visit the page where the target advertisement is located, the number of effective viewers refers to the number of accounts that stay on the page where the target advertisement is displayed for more than a certain period of time, and the number of advertisement conversions refers to orders that are completed through clicking on the advertisement channel.

8. The advertisement delivery system based on advertisement diversion effect monitoring and evaluation according to claim 6 is characterized in that: The drainage evaluation parameter calculation module includes: The initial traffic evaluation calculation formula setting submodule is used to match the traffic evaluation calculation formula of similar merchants based on the attribute information of the merchant to be evaluated and set it as the initial traffic evaluation calculation formula when the merchant to be evaluated has no historical advertising activity records; The historical advertising evaluation calculation formula generation submodule is used to obtain the advertising evaluation data set of all historical advertising activities when the merchant to be evaluated has historical advertising activity records, and substitute the undetermined drainage evaluation calculation formula with the weights of each main effect and the weights of the interaction items as unknowns to generate several historical advertising evaluation calculation formulas; The submodule for generating the traffic evaluation formula is used to input the historical advertising evaluation formula into Python and use the statsmodels library to perform stepwise regression algorithm processing to set the weights of each main effect. , , , and the weights of each interaction term , , , generate the traffic evaluation calculation formula corresponding to the merchant to be evaluated; The attribute information includes several items of data such as business type, business scale and business circle traffic; the advertising evaluation data set includes advertising benefit coefficient , non-advertising benefit coefficient , advertising effectiveness , non-advertising benefits , Ad click-through rate , click-through conversion rate , click cost , conversion cost , effective number of visitors , advertising investment , Benchmark Click Cost , Baseline conversion cost , first-order error term .

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the advertising delivery method based on advertising traffic effect monitoring and evaluation as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the advertisement delivery method based on advertisement traffic effect monitoring and evaluation as described in any one of claims 1 to 5 are implemented.

Images