Advertisement putting bidding strategy determination method and device, equipment and storage medium

Abstract

The present disclosure relates to the technical field of computer, and discloses a method and device for determining a bidding strategy, equipment and a readable storage medium. The method comprises: receiving a target request input by a user for an advertisement to be launched, the target request comprising account information corresponding to the advertisement to be launched, the account information comprising a plurality of launch plans and a launch effective range; determining a target perturbation coefficient corresponding to each launch plan within the launch effective range based on the account information carried in the target request; determining current evaluation information corresponding to each launch plan based on the target perturbation coefficient; and sorting each launch plan according to the current evaluation information to generate a bidding strategy for representing a sorting result of the plurality of launch plans. Through the implementation of the scheme of the present disclosure, the generation of the bidding strategy does not depend on human experience, overcomes the influence of human subjective factors on the evaluation of the launch plan, and ensures that the generation of the bidding strategy is more accurate and objective.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to a method, apparatus, device, and storage medium for determining bidding strategies for advertising placement. Background Technology

[0002] Traffic volume is the fundamental requirement in online marketing and advertising, reflecting the basic needs of advertising to a certain extent. However, with the slowdown in the overall growth of the traffic market and increased competition among advertisers, achieving traffic volume has become more difficult for clients.

[0003] However, with the increase in ad spending, ad accounts will also experience a significant increase in costs. Currently, ad placement strategies are primarily generated manually using bidding strategies for campaign plans, followed by budget allocation based on these strategies. However, the success of an ad placement strategy depends heavily on human prediction of the current ad environment. This method relies excessively on human experience, is influenced by subjective factors, and makes it difficult to guarantee the accuracy of the bidding strategy for the campaign plan. Summary of the Invention

[0004] In view of this, the present disclosure provides a method, apparatus, device and readable storage medium for determining bidding strategies for advertising placement, in order to solve the problem that advertising placement plans rely too much on human experience and it is difficult to guarantee the accuracy of the bidding strategies generated for the placement plans.

[0005] According to a first aspect, embodiments of this disclosure provide a method for determining a bidding strategy for advertising placement, comprising: receiving a target request input by a user for an advertisement to be placed, the target request including account information corresponding to the advertisement to be placed, the account information including multiple placement plans and a placement effective range; determining a target perturbation coefficient corresponding to each placement plan within the placement effective range based on the account information carried in the target request; determining current evaluation information corresponding to each placement plan based on the target perturbation coefficient; and sorting each placement plan according to the current evaluation information to generate a bidding strategy for characterizing the sorting result of the multiple placement plans.

[0006] The advertising bidding strategy determination method provided in this disclosure, upon receiving a target request for an advertisement to be placed, determines the target perturbation coefficient corresponding to each placement plan of the advertisement to be placed within the effective scope of the placement based on the account information carried in the target request. Then, it determines the evaluation information of each placement plan based on the target perturbation coefficient to generate a bidding strategy for the advertisement to be placed. The target perturbation coefficient in this method is related to the current effective scope of the placement and does not rely on human experience. Therefore, it can overcome the influence of subjective human factors on the evaluation of placement plans, ensuring that the final generated bidding strategy is more accurate and objective.

[0007] In conjunction with the first aspect, in the first embodiment of the first aspect, determining the target disturbance coefficient corresponding to each of the advertising plans within the effective range of the advertising based on the account information carried in the target request includes: obtaining historical advertising data of multiple advertising plans corresponding to the account information; determining the plan disturbance coefficient corresponding to each of the advertising plans based on the historical advertising data; analyzing the traffic data of each of the advertising plans to determine the traffic differentiation coefficient corresponding to each of the advertising plans; and determining the target disturbance coefficient corresponding to each of the advertising plans based on the plan disturbance coefficient and the traffic differentiation coefficient.

[0008] The advertising placement bidding strategy determination method provided in this embodiment analyzes historical placement data to determine the plan disturbance coefficient, analyzes the traffic data of each placement plan to determine the traffic differentiation coefficient, and then combines the plan disturbance coefficient and the traffic differentiation coefficient to determine the final target disturbance coefficient, ensuring that the target disturbance coefficient is optimal within the placement range, which facilitates optimal advertising placement.

[0009] In conjunction with the first embodiment of the first aspect, in the second embodiment of the first aspect, determining the target disturbance coefficient corresponding to each of the delivery plans based on the plan disturbance coefficient and the traffic differentiation coefficient includes: performing budget control on each of the delivery plans to determine the budget coefficient corresponding to each of the delivery plans; and determining the product of the budget coefficient, the plan disturbance coefficient and the traffic differentiation coefficient as the target disturbance coefficient.

[0010] The advertising bidding strategy determination method provided in this disclosure determines the optimal target perturbation coefficient within a reasonable budget range by considering the budget coefficient of the placement plan.

[0011] In conjunction with the first embodiment of the first aspect, in the third embodiment of the first aspect, determining the plan disturbance coefficient corresponding to each of the deployment plans based on the historical deployment data includes: classifying the deployment plans based on the historical deployment data to determine the classification result of the deployment plans; and performing differential processing on each of the deployment plans based on the classification result to obtain the plan disturbance coefficient corresponding to each of the deployment plans.

[0012] The advertising placement bidding strategy determination method provided in this embodiment analyzes historical placement data to classify various placement plans, and then determines the plan disturbance coefficient corresponding to each placement plan based on the classification results. This achieves the differentiation of different placement plans and facilitates the planning of effective strategies for each placement plan based on the plan disturbance coefficient.

[0013] In conjunction with the first embodiment of the first aspect, in the third embodiment of the first aspect, the step of analyzing the traffic data of each of the advertising plans and determining the traffic differentiation coefficient corresponding to each of the advertising plans includes: determining the historical delivery rate corresponding to each of the advertising plans based on the historical traffic data of each of the advertising plans; obtaining the current delivery rate and the historical delivery frequency corresponding to each of the advertising plans; performing a logarithmic transformation on the historical delivery rate and the current delivery rate to determine the traffic evaluation coefficient corresponding to each of the advertising plans; performing a credibility assessment on the traffic evaluation coefficient based on the historical delivery frequency to determine the credibility coefficient corresponding to each of the advertising plans; and determining the traffic differentiation coefficient corresponding to each of the advertising plans based on the product of the traffic evaluation coefficient and the credibility coefficient.

[0014] The advertising bidding strategy determination method provided in this disclosure evaluates the traffic data of each campaign to determine the traffic differentiation coefficient corresponding to each campaign. This facilitates the judgment of the traffic quality of the campaign based on the traffic differentiation coefficient, thereby identifying high-quality traffic and low-quality traffic.

[0015] In conjunction with the fourth embodiment of the first aspect, in the fifth embodiment of the first aspect, determining the traffic differentiation coefficient corresponding to each of the delivery plans based on the product of the traffic evaluation coefficient and the credibility coefficient includes: obtaining the preset price increase coefficient corresponding to each of the delivery plans; and determining the traffic differentiation coefficient based on the product of the preset price increase coefficient, the traffic evaluation coefficient, and the credibility coefficient.

[0016] The advertising bidding strategy determination method provided in this embodiment combines a preset price increase coefficient, a traffic evaluation coefficient, and a reliability coefficient when determining the traffic differentiation coefficient. This ensures the accuracy of traffic quality prediction and improves the accuracy of the subsequently determined target disturbance coefficient.

[0017] In conjunction with the first aspect, in the sixth embodiment of the first aspect, determining the current evaluation information corresponding to each of the deployment plans based on the target perturbation coefficient includes: obtaining historical evaluation information corresponding to multiple deployment plans; and determining the current evaluation information corresponding to each of the deployment plans based on the correlation between the target perturbation coefficient and the historical evaluation information.

[0018] The advertising placement bidding strategy determination method provided in this embodiment combines historical evaluation information with the correlation between the target disturbance coefficient to determine the current evaluation information of the placement plan. This enables an objective evaluation of the placement plan based on historical evaluation information, so that the current evaluation information can fully reflect the placement strategy for the placement scope and ensure the rationality of the incremental consumption generated by the advertising placement.

[0019] According to a second aspect, embodiments of this disclosure provide an apparatus for determining bidding strategies for advertising placement, comprising: an acquisition module, configured to receive a target request input by a user for an advertisement to be placed, the target request including account information corresponding to the advertisement to be placed, the account information including multiple placement plans and a placement effective range; a first determination module, configured to determine a target perturbation coefficient corresponding to each placement plan within the placement effective range based on the account information carried in the target request; a second determination module, configured to determine current evaluation information corresponding to each placement plan based on the target perturbation coefficient; and a generation module, configured to sort each placement plan according to the current evaluation information to generate a bidding strategy for characterizing the sorting result of the multiple placement plans.

[0020] According to a third aspect, this disclosure provides an electronic device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the bidding strategy determination method for advertising placement as described in the first aspect or any embodiment of the first aspect.

[0021] According to a fourth aspect, embodiments of this disclosure provide a computer-readable storage medium storing computer instructions for causing a computer to perform the bidding strategy determination method for advertising placement as described in the first aspect or any embodiment of the first aspect.

[0022] It should be noted that the beneficial effects of the advertising bidding strategy determination device, electronic device, and computer-readable storage medium provided in the embodiments of this disclosure can be found in the description of the corresponding content in the advertising bidding strategy determination method, and will not be repeated here. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the specific embodiments of this disclosure or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for determining a bidding strategy for advertising placement according to an embodiment of this disclosure;

[0025] Figure 2 This is another flowchart of the method for determining the bidding strategy for advertising placement according to embodiments of the present disclosure;

[0026] Figure 3 This is yet another flowchart of the method for determining the bidding strategy for advertising placement according to embodiments of this disclosure;

[0027] Figure 4 This is a structural block diagram of an advertising placement bidding strategy determination device according to an embodiment of the present disclosure;

[0028] Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this disclosure. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0030] As advertising spending increases, advertising accounts will also experience a significant increase in spending. Currently, advertising strategies are primarily generated manually through bidding strategies for campaign plans. However, the success of these strategies relies heavily on human prediction of the current advertising environment. This method is overly dependent on human experience, introduces subjective factors, and makes it difficult to guarantee the accuracy of the bidding strategies for campaign plans.

[0031] Based on this, the technical solution disclosed herein determines the target disturbance coefficient corresponding to each advertising campaign within the effective range of the campaign. Since the target disturbance coefficient is related to the current effective range of the campaign, it does not rely on human experience, thus ensuring the accuracy and objectivity of the final generated bidding strategy.

[0032] According to embodiments of this disclosure, an embodiment for generating a bidding strategy is provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] This embodiment provides a method for determining bidding strategies for advertising, which can be used on electronic devices such as mobile phones, tablets, computers, and servers. Figure 1 This is a flowchart of a method for determining a bidding strategy for advertising placement according to an embodiment of this disclosure, such as... Figure 1 As shown, the process includes the following steps:

[0034] S11, Receive user input of a target request for the advertisement to be delivered.

[0035] The target request includes the account information corresponding to the advertisement to be placed, and the account information includes multiple placement plans and the scope of the placement.

[0036] The target request is an ad delivery request. This target request can be an initial delivery request or an additional delivery request for an already delivered ad. This target request represents the ad delivery message that the user expects to achieve.

[0037] For the same advertisement to be delivered, there are multiple delivery plans. By setting up multiple delivery plans, it can cover multiple delivery points. The target request contains the account information of the advertisement to be delivered, which represents the relevant information of each delivery plan for the advertisement.

[0038] Specifically, account information includes multiple campaign plans and the scope of campaign effectiveness. Each campaign plan has a corresponding budget, such as the initial budget and additional budget. The scope of campaign effectiveness is used to indicate the duration, location, and time of the campaign.

[0039] S12, based on the account information carried in the target request, determine the target disturbance coefficient corresponding to each campaign within the effective scope of the campaign.

[0040] The target perturbation coefficient is used to characterize the bidding strategy coefficient of each campaign when vying for ad placements. This coefficient is used to adjust the bids of each campaign within the current effective range for securing ad placements. Specifically, by parsing the account information carried in the target request, the effective range of the ad campaign can be determined. Then, based on the historical campaign data and traffic data of each campaign, its target perturbation coefficient during the ad delivery process can be determined.

[0041] S13, determine the current evaluation information corresponding to each deployment plan based on the target disturbance coefficient.

[0042] The current evaluation information is used to assess the optimal bid coefficient for each campaign to achieve the best impressions / spend under the target perturbation coefficient. This optimal impressions / spend includes the impressions / spend that can be obtained with the original bidding method, as well as the additional impressions / spend obtained with the strategic bidding method.

[0043] Within the effective range of the campaign, the impressions / spend of each campaign in the account information is adjusted using the target perturbation coefficient to obtain the impressions / spend that each campaign can obtain under the original bidding method and the additional impressions / spend obtained under the strategy bidding method. Then, the bidding coefficient of each campaign in the process of seizing the placement position is optimally adjusted using the impressions / spend of each campaign to obtain the optimal bidding coefficient of each campaign, that is, the current evaluation information corresponding to each campaign.

[0044] S14, rank each campaign based on the current evaluation information to generate a bidding strategy that represents the ranking results of multiple campaigns.

[0045] The campaigns are ranked according to their optimal exposure / spend as represented by the current evaluation information. A bidding strategy is then generated for each campaign based on this ranking, displaying the current evaluation information for each campaign. This current evaluation information determines the likelihood of each campaign securing ad space during the campaign, enabling budget control and allocation of budget or incremental budgets to each campaign.

[0046] For example, the bidding score represents the current evaluation information. The higher the bidding score, the greater the possibility that the campaign can secure an ad slot. At this point, the bidding score can be used to obtain a bidding strategy for each campaign, and the budget allocated to each campaign can be controlled according to the bidding strategy.

[0047] The advertising bidding strategy determination method provided in this embodiment, upon receiving a target request for an advertisement to be placed, determines the target perturbation coefficient corresponding to each placement plan of the advertisement to be placed within the effective scope of the placement based on the account information carried in the target request. Then, it determines the evaluation information of each placement plan based on the target perturbation coefficient to generate a bidding strategy for the advertisement to be placed. The target perturbation coefficient in this method is related to the current effective scope of the placement and does not rely on human experience. Therefore, it can overcome the influence of subjective human factors on the evaluation of placement plans, ensuring that the final generated bidding strategy is more accurate and objective.

[0048] This embodiment provides a method for determining bidding strategies for advertising, which can be used on electronic devices such as mobile phones, tablets, computers, and servers. Figure 2 This is a flowchart of a method for determining a bidding strategy for advertising placement according to an embodiment of this disclosure, such as... Figure 2 As shown, the process includes the following steps:

[0049] S21, Receive a target request from the user for the advertisement to be delivered. The target request includes the account information corresponding to the advertisement to be delivered, and the account information includes multiple delivery plans and the scope of the delivery.

[0050] For detailed explanations, please refer to the relevant descriptions corresponding to the above embodiments, which will not be repeated here.

[0051] S22, based on the account information carried in the target request, determine the target disturbance coefficient corresponding to each campaign within the effective scope of the campaign.

[0052] Optionally, step S22 above may include:

[0053] S221, retrieve historical delivery data for multiple delivery plans corresponding to the account information.

[0054] Historical campaign data refers to the performance data of a campaign over a past period. Specifically, historical campaign data includes the campaign's lifecycle, conversion goals, clicks, etc.

[0055] Electronic devices are equipped with applications that record the advertising process, such as ByteDance's advertising platform. These applications allow users to query multiple campaigns for the current ad over a past period, obtaining historical data such as the campaign's lifecycle, conversion goals, and click-through rates.

[0056] S222, determine the plan disturbance coefficient corresponding to each deployment plan based on historical deployment data.

[0057] The plan disturbance coefficient is a differentiation coefficient generated based on different campaign plans. Historical campaign data can be used to predict the future performance of each campaign plan, and then the effectiveness of each campaign plan can be differentiated based on the predicted performance, resulting in the plan disturbance coefficient for each campaign plan under the account information.

[0058] Specifically, step S222 above may include:

[0059] (1) Classify the deployment plans based on historical deployment data and determine the classification results of the deployment plans.

[0060] Based on historical campaign data, the performance of each campaign is predicted for the future. Based on this performance prediction, each campaign is categorized using tags. These tags can include categories such as "potential" or "low-quality," thus classifying the campaigns into categories.

[0061] (2) Based on the classification results, the differentiating processing of each deployment plan is carried out to obtain the plan disturbance coefficient corresponding to each deployment plan.

[0062] Based on the performance of each campaign within the current campaign scope and the estimated classification results, differentiated activation strategies are generated for campaigns with different lifecycles, conversion goals, and classification tags (potential / low quality, etc.). Based on these differentiated activation strategies, the campaign perturbation coefficient AdCoefi corresponding to each campaign under the current advertising account information is calculated, where i is a positive integer representing the i-th campaign of the advertising to be launched.

[0063] By analyzing historical campaign data to categorize each campaign, and then determining the campaign disturbance coefficient for each campaign based on the categorization results, it is possible to differentiate between different campaigns and facilitate the planning of effective strategies for each campaign based on the campaign disturbance coefficient.

[0064] S223, Analyze the traffic data of each campaign and determine the traffic differentiation coefficient corresponding to each campaign.

[0065] The traffic differentiation coefficient is used to measure the number of clicks generated by each campaign, thus distinguishing the quality of traffic from different campaigns. Each campaign generates a certain number of clicks after completion, and these clicks constitute the traffic data for each campaign. Different campaigns exhibit variations in their traffic data; these variations determine the quality of traffic for each campaign, and the traffic differentiation coefficient is then determined based on this quality.

[0066] Specifically, step S223 above may include:

[0067] (1) Based on the historical traffic data of each campaign, determine the historical delivery rate of each campaign.

[0068] Historical delivery rate represents the delivery rate of a campaign over a past period, i.e., the proportion of each campaign among all campaigns. It's calculated by statistically analyzing the traffic data generated by each campaign over a past period. There's a positive correlation between historical traffic data and historical delivery rate; the higher the proportion of a campaign, the more traffic it generates. By querying historical traffic data, the historical delivery efficiency of each campaign over a given period can be determined.

[0069] (2) Obtain the current delivery rate and historical delivery frequency for each delivery plan.

[0070] The current delivery rate is the delivery rate desired by the user, which can be obtained from the user's target request. Historical delivery counts are the number of times each campaign has been executed within a past period, determined by analyzing past delivery information for each campaign.

[0071] (3) Perform logarithmic transformation on the historical delivery rate and the current delivery rate to determine the traffic evaluation coefficient corresponding to each delivery plan.

[0072] By querying the historical delivery rate list (recent_pvr_list) for the ad to be delivered, the historical delivery rate of each campaign over the past period can be obtained. The historical delivery rate (pvr) of the i-th campaign is then compared with the current delivery rate (pvr) in the target request. cur By comparing the historical and current delivery rates, a logarithmic transformation is performed to preprocess them, reducing differences in magnitude and variance, to obtain the traffic evaluation coefficient QuantileValue corresponding to the i-th delivery plan. The specific expression is as follows:

[0073]

[0074] Among them, avg(log b (pvr)) represents the average of the historical delivery rates after logarithmic transformation for the i-th delivery plan. b is the base, which is set according to actual needs and is not limited here.

[0075] (4) Based on the historical number of campaigns, the credibility of the traffic evaluation coefficient is evaluated to determine the credibility coefficient of each campaign plan.

[0076] The reliability of the traffic evaluation coefficient QuantileValue is assessed based on the historical frequency of each campaign. For campaigns whose confidence level does not meet the preset requirements, a reliability coefficient Confidence is introduced to determine whether the traffic evaluation coefficient QuantileValue is reliable. Specifically, the expression for the reliability coefficient Confidence is as follows:

[0077]

[0078] Among them, len(recent_pvr_list) is used to count the number of times the campaign has been launched in the past period.

[0079] (5) Based on the product of the traffic evaluation coefficient and the credibility coefficient, determine the traffic differentiation coefficient corresponding to each delivery plan.

[0080] Traffic Differentiation Coefficient ReqCoef i The determination method is as follows:

[0081] ReqCoef i = (QuantileValue × Confidence × C + 1)

[0082] Wherein, QuantileValue represents the traffic evaluation coefficient, Confidence represents the credibility coefficient, and C represents a constant, which can be set according to different campaign plans and is not specifically limited here.

[0083] By evaluating the traffic data of each campaign, the traffic differentiation coefficient corresponding to each campaign can be determined. This coefficient can then be used to judge the traffic quality of the campaign and identify high-quality and low-quality traffic.

[0084] As an optional implementation, step (5) above may include:

[0085] (51) Obtain the preset price increase coefficient corresponding to each campaign.

[0086] (52) Determine the flow differentiation coefficient based on the product of the preset price increase coefficient, flow evaluation coefficient and credibility coefficient.

[0087] The preset bid increase coefficient is a constant set based on different campaign plans. The traffic differentiation coefficient (ReqCoef) is determined by combining the preset bid increase coefficient, traffic evaluation coefficient, and credibility coefficient. i The method is as follows:

[0088] ReqCoef i = (QuantileValue × Confidence × ConstantValue + 1)

[0089] Among them, QuantileValue represents the traffic evaluation coefficient, Confidence represents the credibility coefficient, and ConstantValue represents the preset price increase coefficient. The preset price increase coefficient is set according to the actual scenario of the campaign, and there is no limit to the specific value of ConstantValue.

[0090] When determining the traffic differentiation coefficient, it is combined with the preset price increase coefficient, traffic evaluation coefficient, and credibility coefficient. This ensures the accuracy of traffic quality prediction and improves the accuracy of the subsequently determined target disturbance coefficient.

[0091] S224, based on the planned disturbance coefficient and the traffic differentiation coefficient, determines the target disturbance coefficient corresponding to each delivery plan.

[0092] By combining the plan perturbation coefficient and traffic differentiation coefficient corresponding to each campaign, the optimal target perturbation coefficient is determined based on the data performance of the campaign within the effective range. This target perturbation coefficient is then used to explore the bidding for each campaign, achieving controllability of advertising costs and facilitating improved ad performance.

[0093] Specifically, step S224 above may include:

[0094] (1) Budget control is carried out for each deployment plan, and the budget coefficient corresponding to each deployment plan is determined.

[0095] By analyzing the account information of the ads to be launched, the budget usage progress, cost, and budget limits for each campaign can be determined. Based on the budget usage progress, cost, and budget limits of each campaign, budget control is performed to obtain the budget coefficient P. Specifically, the expression for the budget coefficient P is as follows:

[0096] P = Pacing (Budget usage schedule, deployment cost, budget boundary)

[0097] Among them, the budget boundary is an empirical value obtained from multiple simulation experiments; the budget usage progress is the budget consumed by the current advertisement to be placed; and the placement cost is the budget cost required to place the advertisement.

[0098] (2) The product of the budget coefficient, the planned disturbance coefficient and the flow differentiation coefficient is determined as the target disturbance coefficient.

[0099] The expression for determining the target disturbance coefficient is as follows:

[0100] Coef i =P×AdCoef i ×ReqCoef i

[0101] Where P represents the budget coefficient; AdCoef i ReqCoefi represents the planned disturbance coefficient; ReqCoefi represents the flow differentiation coefficient.

[0102] By considering the budget coefficient of the campaign, the optimal target perturbation coefficient can be determined within a reasonable budget range. This allows for better control of campaign costs while continuously expanding the advertising account, achieving a reasonable increase in the cost-to-performance ratio.

[0103] S23, determine the current evaluation information corresponding to each deployment plan based on the target disturbance coefficient.

[0104] For detailed explanations, please refer to the relevant descriptions corresponding to the above embodiments, which will not be repeated here.

[0105] S24, Sort each campaign based on the current evaluation information to generate a bidding strategy that represents the ranking results of multiple campaigns.

[0106] For detailed explanations, please refer to the relevant descriptions corresponding to the above embodiments, which will not be repeated here.

[0107] The advertising bidding strategy determination method provided in this embodiment determines the plan disturbance coefficient by analyzing historical advertising data, determines the traffic differentiation coefficient by analyzing the traffic data of each advertising plan, and then determines the final target disturbance coefficient by combining the plan disturbance coefficient and the traffic differentiation coefficient, ensuring that the target disturbance coefficient is optimal within the advertising range, which facilitates optimal advertising placement.

[0108] This embodiment provides a method for determining bidding strategies for advertising, which can be used on electronic devices such as mobile phones, tablets, computers, and servers. Figure 3 This is a flowchart of a method for determining a bidding strategy for advertising placement according to an embodiment of this disclosure, such as... Figure 3 As shown, the process includes the following steps:

[0109] S31, Receive a target request from the user for the advertisement to be delivered. The target request includes the account information corresponding to the advertisement to be delivered, and the account information includes multiple delivery plans and the scope of the delivery.

[0110] For detailed explanations, please refer to the relevant descriptions corresponding to the above embodiments, which will not be repeated here.

[0111] S32, based on the account information carried in the target request, determines the target disturbance coefficient corresponding to each campaign within the effective scope of the campaign.

[0112] For detailed explanations, please refer to the relevant descriptions corresponding to the above embodiments, which will not be repeated here.

[0113] S33, determine the current evaluation information corresponding to each deployment plan based on the target disturbance coefficient.

[0114] Optionally, step S33 above may include:

[0115] S331, obtain historical evaluation information corresponding to multiple campaign plans.

[0116] Historical evaluation information represents the evaluation information of each campaign corresponding to the ad to be launched during the historical campaign process. In other words, the historical bid information of each campaign can be determined through this historical evaluation information. By statistically analyzing the historical campaign data of each campaign, the historical bid information of each campaign can be obtained from the historical campaign data. By sorting the campaigns according to the historical bid information, the historical evaluation information corresponding to multiple campaigns of the ad to be launched can be obtained.

[0117] S332, based on the correlation between the target disturbance coefficient and historical evaluation information, determines the current evaluation information corresponding to each deployment plan.

[0118] Within the effective scope of the campaign, both the strategic bidding method and the original bidding method under the account are effective simultaneously. The impressions / spends obtained by the original bidding method are used to evaluate the base bid coefficient, while the additional impressions / spends obtained by the strategic bidding method are used to evaluate the incremental bid coefficient. The base bid coefficient determines the original budget allocation for the campaign, and the incremental bid coefficient determines the incremental budget allocation for the campaign.

[0119] Specifically, NewRankBid represents the current evaluation information, OldRankBid represents the historical evaluation information, and Coef represents the historical evaluation information. i Let represent the target perturbation coefficient of the i-th delivery plan within the current delivery effective range. Then, the current evaluation information NewRankBid is expressed as:

[0120]

[0121] CpaBid represents the bid set by the user for this campaign.

[0122] S34, rank the various campaigns based on the current evaluation information to generate a bidding strategy that represents the ranking results of the multiple campaigns.

[0123] For detailed explanations, please refer to the relevant descriptions corresponding to the above embodiments, which will not be repeated here.

[0124] The advertising bidding strategy determination method provided in this embodiment combines the correlation between historical evaluation information and target disturbance coefficient to determine the current evaluation information of the advertising plan. This enables an objective evaluation of the advertising plan based on historical evaluation information, so that the current evaluation information can fully reflect the advertising strategy for the advertising scope and ensure the rationality of the incremental consumption generated by advertising.

[0125] This embodiment also provides an advertising bidding strategy determination device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated for details already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0126] This embodiment provides a device for determining the bidding strategy for advertising placement, such as... Figure 4 As shown, it includes:

[0127] The acquisition module 41 is used to receive a target request from the user for the advertisement to be delivered. The target request includes the account information corresponding to the advertisement to be delivered, and the account information includes multiple delivery plans and the scope of the delivery.

[0128] The first determining module 42 is used to determine the target disturbance coefficient corresponding to each delivery plan within the effective delivery range based on the account information carried in the target request.

[0129] The second determining module 43 is used to determine the current evaluation information corresponding to each deployment plan based on the target disturbance coefficient.

[0130] The generation module 44 is used to sort the various campaigns based on the current evaluation information to generate a bidding strategy that represents the ranking results of the multiple campaigns.

[0131] Optionally, the first determining module 42 may include:

[0132] The first acquisition submodule is used to acquire historical delivery data for multiple delivery plans corresponding to account information.

[0133] The first determination submodule is used to determine the plan disturbance coefficient corresponding to each deployment plan based on historical deployment data.

[0134] The analysis submodule is used to analyze the traffic data of each campaign and determine the traffic differentiation coefficient corresponding to each campaign.

[0135] The second determination submodule is used to determine the target disturbance coefficient corresponding to each delivery plan based on the plan disturbance coefficient and the traffic differentiation coefficient.

[0136] Optionally, the first determining submodule is specifically used to classify the deployment plans based on historical deployment data and determine the classification results of the deployment plans; and to perform differential processing on each deployment plan based on the classification results to obtain the plan disturbance coefficient corresponding to each deployment plan.

[0137] Optionally, the aforementioned analysis submodule is specifically used to: determine the historical delivery rate corresponding to each delivery plan based on the historical traffic data of each delivery plan; obtain the current delivery rate and historical delivery frequency corresponding to each delivery plan; perform a logarithmic transformation on the historical delivery rate and the current delivery rate to determine the traffic evaluation coefficient corresponding to each delivery plan; perform a credibility assessment on the traffic evaluation coefficient based on the historical delivery frequency to determine the credibility coefficient corresponding to each delivery plan; and determine the traffic differentiation coefficient corresponding to each delivery plan based on the product of the traffic evaluation coefficient and the credibility coefficient.

[0138] Optionally, the aforementioned analysis submodule is further used to obtain the preset price increase coefficient corresponding to each campaign plan; and to determine the traffic differentiation coefficient based on the product of the preset price increase coefficient, the traffic evaluation coefficient, and the credibility coefficient.

[0139] Optionally, the second determining submodule is specifically used to perform budget control on each delivery plan, determine the budget coefficient corresponding to each delivery plan, and determine the product of the budget coefficient, the plan disturbance coefficient and the traffic differentiation coefficient as the target disturbance coefficient.

[0140] Optionally, the second determining module 43 may include:

[0141] The second acquisition submodule is used to acquire historical evaluation information corresponding to multiple deployment plans.

[0142] The third determination submodule is used to determine the current assessment information corresponding to each deployment plan based on the correlation between the target disturbance coefficient and historical assessment information.

[0143] In this embodiment, the advertising placement bidding strategy determination device is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0144] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0145] The advertising bidding strategy determination device provided in this embodiment, upon receiving a target request for an advertisement to be placed, determines the target perturbation coefficient corresponding to each placement plan of the advertisement to be placed within the effective scope of the placement based on the account information carried in the target request. Then, it determines the evaluation information of each placement plan based on the target perturbation coefficient to generate a bidding strategy for the advertisement to be placed. This target perturbation coefficient is related to the current effective scope of the placement and does not rely on human experience, thereby overcoming the influence of subjective human factors on the evaluation of the placement plan and ensuring that the generation of the bidding strategy is more accurate and objective.

[0146] This disclosure also provides an electronic device having the above-described features. Figure 4 The device shown is for determining the bidding strategy for advertising placement.

[0147] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an optional embodiment of this disclosure, such as... Figure 5As shown, the electronic device may include: at least one processor 501, such as a central processing unit (CPU), at least one communication interface 503, memory 504, and at least one communication bus 502. The communication bus 502 is used to enable communication between these components. The communication interface 503 may include a display screen or a keyboard; optionally, the communication interface 503 may also include a standard wired interface or a wireless interface. The memory 504 may be high-speed volatile random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 504 may also be at least one storage device located remotely from the aforementioned processor 501. The processor 501 may be combined with... Figure 4 The described apparatus has an application program stored in memory 504, and a processor 501 calls the program code stored in memory 504 to perform any of the above method steps.

[0148] The communication bus 502 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 502 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0149] The memory 504 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 504 may also include a combination of the above types of memory.

[0150] The processor 501 can be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP.

[0151] The processor 501 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0152] Optionally, memory 504 is also used to store program instructions. Processor 501 can call the program instructions to implement the functions described in this application. Figures 1 to 3 The method for determining the bidding strategy for ad placement is shown in the embodiments.

[0153] This disclosure also provides a non-transitory computer storage medium storing computer-executable instructions that can execute the bidding strategy determination method for advertising placement in any of the above method embodiments. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0154] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. An advertisement delivery bidding strategy determination method, characterized by, The method comprises the steps of: receiving a target request for an advertisement to be launched, the target request comprising account information corresponding to the advertisement to be launched, the account information comprising a plurality of launch plans and a launch effective range; determining a target perturbation coefficient corresponding to each of the launch plans within the launch effective range based on the account information carried in the target request, the target perturbation coefficient being used to represent a bidding strategy coefficient of each launch plan when occupying a launch point; determining current evaluation information corresponding to each of the launch plans based on the target perturbation coefficient; sorting each of the launch plans according to the current evaluation information to generate a bidding strategy representing a sorting result of the plurality of launch plans; wherein the step of determining a target perturbation coefficient corresponding to each of the launch plans within the launch effective range based on the account information carried in the target request comprises: obtaining historical launch data of the plurality of launch plans corresponding to the account information, the historical launch data being launch performance data of the launch plans in the past time, the historical launch data comprising a life cycle of a launch plan, a conversion target, and a click volume, the launch performance data being used to represent a launch effect of the launch plan; determining a plan perturbation coefficient corresponding to each of the launch plans based on the historical launch data, the plan perturbation coefficient being a differential coefficient generated according to different launch plans; analyzing traffic data of each of the launch plans to determine a traffic differential coefficient corresponding to each of the launch plans, the traffic differential coefficient being used to measure a click volume generated by each of the launch plans; determining a target perturbation coefficient corresponding to each of the launch plans based on the plan perturbation coefficient and the traffic differential coefficient, comprising: performing budget control on each of the launch plans to determine a budget coefficient corresponding to each of the launch plans; and determining a product value of the budget coefficient, the plan perturbation coefficient, and the traffic differential coefficient as the target perturbation coefficient.

2. The method of claim 1, wherein, The step of determining a plan perturbation coefficient corresponding to each of the launch plans based on the historical launch data comprises: classifying the launch plans based on the historical launch data to determine a classification result of the launch plans; differentially processing each of the launch plans based on the classification result to obtain a plan perturbation coefficient corresponding to each of the launch plans.

3. The method of claim 1, wherein, The step of analyzing traffic data of each of the launch plans to determine a traffic differential coefficient corresponding to each of the launch plans comprises: determining a historical launch rate corresponding to each of the launch plans based on historical traffic data of each of the launch plans; obtaining a current launch rate and a historical launch frequency corresponding to each of the launch plans; performing logarithmic transformation on the historical launch rate and the current launch rate to determine a traffic evaluation coefficient corresponding to each of the launch plans; performing credibility evaluation on the traffic evaluation coefficient based on the historical launch frequency to determine a credibility coefficient corresponding to each of the launch plans; determining a traffic differential coefficient corresponding to each of the launch plans based on a product value of the traffic evaluation coefficient and the credibility coefficient.

4. The method of claim 3, wherein, The product value of the traffic evaluation coefficient and the trust coefficient is used to determine a traffic differentiation coefficient corresponding to each of the delivery plans. A preset price increase coefficient corresponding to each of the delivery plans is obtained. The product value of the preset price increase coefficient, the traffic evaluation coefficient and the trust coefficient is used to determine the traffic differentiation coefficient.

5. The method of claim 1, wherein, The target disturbance coefficient is used to determine current evaluation information corresponding to each of the delivery plans. Historical evaluation information corresponding to the delivery plans is obtained. The correlation between the target disturbance coefficient and the historical evaluation information is used to determine current evaluation information corresponding to each of the delivery plans.

6. A device for determining bidding strategies for advertising placement, characterized in that, The method comprises the following steps: An acquisition module is configured to receive a target request for a to-be-delivered advertisement input by a user, wherein the target request comprises account information corresponding to the to-be-delivered advertisement, and the account information comprises a plurality of delivery plans and a delivery effective range. A first determination module is configured to determine a target disturbance coefficient corresponding to each of the delivery plans within the delivery effective range based on the account information carried in the target request, wherein the target disturbance coefficient is used to represent a bidding strategy coefficient of each delivery plan when occupying a delivery point. A second determination module is configured to determine current evaluation information corresponding to each of the delivery plans based on the target disturbance coefficient. A generation module is configured to sort each of the delivery plans according to the current evaluation information, so as to generate a bidding strategy for representing a sorting result of the plurality of delivery plans. The first determination module comprises: a first acquisition sub-module configured to acquire historical delivery data of the plurality of delivery plans corresponding to the account information, wherein the historical delivery data is delivery performance data of the delivery plans in the past time, the historical delivery data comprises a life cycle, a conversion target and a click volume of the delivery plan, and the delivery performance data is used to represent a delivery effect of the delivery plan; a first determination sub-module configured to determine a plan disturbance coefficient corresponding to each of the delivery plans based on the historical delivery data, wherein the plan disturbance coefficient is a differentiated coefficient generated according to different delivery plans; an analysis sub-module configured to analyze traffic data of each of the delivery plans, so as to determine a traffic differentiation coefficient corresponding to each of the delivery plans, wherein the traffic differentiation coefficient is used to measure a click volume generated by each of the delivery plans; and a second determination sub-module configured to determine a target disturbance coefficient corresponding to each of the delivery plans based on the plan disturbance coefficient and the traffic differentiation coefficient, comprising: performing budget control on each of the delivery plans, so as to determine a budget coefficient corresponding to each of the delivery plans; and determining a product value of the budget coefficient, the plan disturbance coefficient and the traffic differentiation coefficient as the target disturbance coefficient.

7. An electronic device, comprising: The method comprises the following steps: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the bidding strategy determination method for the advertisement delivery according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing a computer to execute the advertisement bidding strategy determination method of any one of claims 1-5.

Images