Advertisement putting strategy adjustment method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses an advertisement putting strategy adjustment method and device, equipment and a storage medium, and the method comprises the steps: obtaining advertisement data collected in real time, carrying out the data cleaning of the advertisement data, and obtaining target advertisement data; performing index extraction on the target advertisement data to obtain a plurality of target key indexes, and determining an abnormal index according to fluctuation data of each target key index in a preset time period; and region splitting, creative splitting and time splitting are carried out on the abnormal indexes, and the advertisement putting strategies corresponding to the abnormal indexes are adjusted based on the splitting results of the abnormal indexes and the target advertisement data. The method can adapt to a complex advertisement putting scene, can accurately and quickly determine the reason causing the abnormal index, and improves the advertisement putting effect.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device and storage medium for adjusting advertising placement strategies. Background Technology

[0002] With the rapid development of mobile internet, big data, and artificial intelligence technologies, advertising scenarios are becoming increasingly diversified, covering multiple channels such as search engines, social media, and e-commerce platforms. This has led to an explosive growth in the scale of advertising data, and the data types are becoming increasingly complex, including structured and unstructured data such as user behavior data, ad display and click data, and conversion data. This makes it difficult to extract valuable information in a timely and accurate manner, and also makes it impossible to understand the effectiveness of advertising in real time.

[0003] In related technologies, abnormal indicators are usually identified by simply comparing real-time collected advertising data with historical data. This approach lacks the ability to deeply mine advertising data and make intelligent predictions. It is unable to adapt to complex advertising scenarios, and it is also difficult to efficiently process massive and complex data. It is also unable to accurately and quickly determine the causes of abnormal indicators and the corresponding advertising strategies, thereby affecting the effectiveness of advertising. Summary of the Invention

[0004] This application provides an advertising placement strategy adjustment method, apparatus, device, and storage medium, which solves the problems in the prior art of lacking in-depth data mining and intelligent prediction capabilities for advertising data, being unable to adapt to complex advertising placement scenarios, and being unable to accurately and quickly determine the causes of abnormal indicators and corresponding advertising placement strategies. It can improve the processing efficiency of unstructured data by cleaning the collected advertising data, and can adapt to various advertising placement scenarios. By detecting and decomposing abnormal indicators, it can analyze the causes of indicator anomalies from multiple dimensions, and make targeted adjustments to the advertising placement strategy based on the causes of anomalies, improving the accuracy and timeliness of anomaly detection, as well as the flexibility and effectiveness of the advertising placement strategy.

[0005] In a first aspect, embodiments of this application provide a method for adjusting an advertising delivery strategy, including: Acquire real-time collected advertising data, perform data cleaning on the advertising data, and obtain target advertising data; The target advertising data is subjected to indicator extraction to obtain multiple target key indicators, and abnormal indicators are determined based on the fluctuation data of each target key indicator within a preset time period. The abnormal indicators are segmented by region, creative content, and time. Based on the segmentation results of the abnormal indicators and the target advertising data, the advertising delivery strategy corresponding to the abnormal indicators is adjusted.

[0006] Optionally, the fluctuation data includes fluctuation frequency and fluctuation range, and the step of determining abnormal indicators based on the fluctuation data of each target key indicator within a preset time period includes: Determine whether the fluctuation frequency is less than a preset fluctuation frequency threshold and whether the changing trends of the target key indicators are consistent to obtain a first judgment result; Determine whether the fluctuation range is within the corresponding preset indicator range. If the fluctuation range is not within the preset indicator range, calculate the abnormal ratio of the target key indicator to the preset indicator range, determine whether the abnormal ratio is less than a preset abnormal ratio threshold, and obtain a second determination result. The target key indicator whose first judgment result and the second judgment result are both abnormal is identified as an abnormal indicator.

[0007] Optionally, the step of performing geographical segmentation, creative segmentation, and time segmentation on the abnormal indicators includes: Determine the fine-grained regional segmentation corresponding to the index type of the abnormal index, and perform regional segmentation on the abnormal index based on the fine-grained regional segmentation. Determine the creative segmentation dimension corresponding to the creative type of the abnormal indicator, and perform creative segmentation on the abnormal indicator based on the creative segmentation dimension. The creative type includes any one or more of copywriting creativity, visual creativity, formal creativity and action command creativity. The time segmentation dimension is determined based on the advertising scenario corresponding to the abnormal indicator, and the abnormal indicator is then segmented over time based on the time segmentation dimension.

[0008] Optionally, determining the time segmentation dimension based on the advertising delivery scenario corresponding to the abnormal indicator includes: Determine the target time period associated with the advertising scenario corresponding to the abnormal indicator, match the target time period with the current time period corresponding to the abnormal indicator, and if the match is consistent, determine the time segmentation dimension as the first time dimension. In the event of a mismatch, the time split dimension is determined to be the second time dimension, where the first time dimension is smaller than the second time dimension.

[0009] Optionally, the breakdown results of the abnormal indicators include a first abnormal indicator, a second abnormal indicator, and a third abnormal indicator. Adjusting the advertising strategy corresponding to the abnormal indicators based on the breakdown results and the target advertising data includes: The analysis results are obtained by performing abnormal regional analysis on the first abnormal indicator, inefficient creative analysis on the second abnormal indicator, and sudden abnormal period analysis on the third abnormal indicator. Based on the analysis results and the target advertising data, the advertising strategy corresponding to the abnormal indicators is adjusted.

[0010] Optionally, adjusting the advertising strategy corresponding to the abnormal indicators based on the analysis results and the target advertising data includes: If the analysis results indicate that the target region is abnormal, an adjustment ratio is determined based on the current and expected rates of return in the target advertising data, and the number of ads placed in the region corresponding to the abnormal indicator is reduced according to the adjustment ratio. If the analysis result indicates creative anomaly, determine the version update frequency associated with the advertising scenario in the target advertising data, and update the creative version corresponding to the anomaly indicator according to the version update frequency. If the analysis results indicate an abnormal period, a target time period associated with the advertising scenario in the target advertising data is determined, and the advertising time period corresponding to the abnormal indicator is adjusted to the target time period.

[0011] Optionally, after extracting metrics from the target advertising data to obtain multiple target key metrics, the method further includes: Based on each of the aforementioned target key indicators, an advertising indicator line chart is generated, and the indicator inflection points of each of the aforementioned target key indicators on the advertising indicator line chart are determined. Accordingly, the step of determining whether the fluctuation data of each target key indicator within a preset time period meets preset abnormal conditions, and determining abnormal indicators based on the determination results, includes: Determine whether the number of indicator inflection points of each target key indicator within a preset time period meets the preset fluctuation conditions, and determine abnormal indicators based on the determination results.

[0012] In a second aspect, embodiments of this application provide an advertising delivery strategy adjustment device, comprising: The data cleaning module is used to acquire real-time collected advertising data, clean the advertising data, and obtain target advertising data. The indicator extraction module is used to extract indicators from the target advertising data to obtain multiple target key indicators; An abnormal indicator determination module is used to determine abnormal indicators based on the fluctuation data of each target key indicator within a preset time period. The abnormal indicator splitting module is used to split the abnormal indicators by region, creativity, and time, respectively. The advertising strategy adjustment module is used to adjust the advertising strategy corresponding to the abnormal indicator based on the breakdown results of the abnormal indicator and the target advertising data.

[0013] In a third aspect, embodiments of this application provide an electronic device, the device comprising: one or more processors; and a storage device configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the advertising delivery strategy adjustment method described in the first aspect.

[0014] In a fourth aspect, embodiments of this application provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the advertising delivery strategy adjustment method as described in the first aspect.

[0015] This application embodiment acquires real-time collected advertising data, cleans the data to obtain target advertising data, extracts indicators from the target advertising data to obtain multiple target key indicators, and identifies abnormal indicators based on the fluctuation data of each target key indicator within a preset time period. The abnormal indicators are then segmented by region, creative content, and time. Based on the segmentation results of the abnormal indicators and the target advertising data, the advertising placement strategy corresponding to the abnormal indicators is adjusted. In the above solution, abnormal indicators can be identified by analyzing the fluctuation of data within a preset time period, and the accuracy of abnormal indicator analysis is improved by analyzing the abnormal indicators from dimensions such as region, creative content, and time. Adjusting the advertising placement strategy based on the abnormal indicators improves the effectiveness of advertising placement. Attached Figure Description

[0016] Figure 1 This is a flowchart of an advertising placement strategy adjustment method provided in an embodiment of this application; Figure 2 This is a flowchart of an abnormal indicator determination method provided in an embodiment of this application; Figure 3 This is a line chart of advertising metrics provided in an embodiment of this application; Figure 4 This is a flowchart of an abnormal indicator splitting method provided in an embodiment of this application; Figure 5 This is a flowchart of an advertising placement strategy adjustment method provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an advertising placement strategy adjustment device provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an advertising placement strategy adjustment device provided in an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0018] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0019] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0020] The following description, in conjunction with the accompanying drawings, details the advertising placement strategy adjustment and determination method, apparatus, equipment, and medium provided in this application embodiment through specific embodiments and application scenarios.

[0021] The advertising strategy adjustment method provided in this application is used in scenarios of intelligent advertising monitoring, such as monitoring advertising revenue or monitoring user conversion rates after advertising. Based on the above application scenarios, it can be understood that the executing entity of each step can be a computer device. This computer device refers to any electronic device with data computing, processing, and storage capabilities, such as mobile phones, PCs (Personal Computers), tablet computers, and other terminal devices, or it can be a server or other devices. This application does not limit this.

[0022] Figure 1 This is a flowchart of an advertising placement strategy adjustment method provided in an embodiment of this application, such as... Figure 1 As shown, it includes: Step S101: Obtain real-time collected advertising data, perform data cleaning on the advertising data, and obtain target advertising data.

[0023] Advertising data refers to various quantitative information generated during the advertising campaign. It is the core basis for measuring advertising effectiveness and optimizing campaign strategies. This advertising data can be broken down and analyzed from multiple dimensions. Data cleaning refers to the process of checking, identifying, correcting, or deleting errors, missing data, duplicates, anomalies, or non-compliant data from raw data to improve data quality, making it more accurate, complete, and consistent. This provides a reliable foundation for subsequent data analysis, modeling, or decision-making. Target advertising data refers to the set of raw data that has been systematically checked, corrected, and organized to remove errors, missing data, duplicates, and outliers, resulting in a more accurate, complete, consistent dataset that conforms to business rules.

[0024] In one embodiment, all advertising data from different sources collected in real time within a preset time period are acquired, and the advertising data from different sources are converted according to a preset unified data format to obtain first target advertising data of the same format. Duplicate data in the first target advertising data is removed, missing data in the first target advertising data is supplemented according to the changing trend of historical advertising data, and invalid data in the first target advertising data is filtered out, etc., to obtain cleaned second target advertising data.

[0025] Step S102: Extract indicators from the target advertising data to obtain multiple target key indicators, and determine abnormal indicators based on the fluctuation data of each target key indicator within a preset time period.

[0026] Among these, key performance indicators (KPIs) are the core metrics for measuring campaign effectiveness and guiding strategy optimization. Different industries and campaign objectives have different metric emphases; therefore, KPIs will vary depending on the scenario or campaign purpose. Fluctuation data refers to the numerical changes, trends, and abnormal fluctuations in key advertising metrics.

[0027] In one embodiment, one or more indicator keywords corresponding to the current campaign objective are determined based on the pre-set correlation between the campaign objective and keyword indicators. Key performance indicators (KPIs) are then extracted based on these KPIs to obtain one or more target KPIs. For example, if the campaign objective is "brand exposure," the corresponding target KPIs would be "exposure," "reach," and "frequency," etc. If the campaign objective is "user conversion," the corresponding target KPIs would be "conversion rate," "ROI (Return on Investment)," and "CVR (Conversion Rate)," etc. If the campaign objective is "user retention," the corresponding target KPIs would be "7-day retention rate" or "30-day retention rate," etc. After obtaining multiple target KPIs, abnormal indicators are determined based on the fluctuation trend of each target KPI within a preset time period. For example, it is determined whether the fluctuation trend of each target KPI is consistent over 7 days. If it continuously rises or continuously falls over 7 days, the target KPIs with consistent fluctuation trends are identified as abnormal indicators.

[0028] Step S103: Perform geographic segmentation, creative segmentation, and time segmentation on the abnormal indicators, and adjust the advertising delivery strategy corresponding to the abnormal indicators based on the segmentation results of the abnormal indicators and the target advertising data.

[0029] Geographic segmentation refers to breaking down abnormal metrics according to the user's geographical region, enabling regional metric analysis. This involves segmenting metrics by geographical dimension to uncover behavioral differences, campaign performance variations, or market characteristics across different regions, providing data support for adjusting advertising strategies. Creative segmentation involves breaking down creative materials corresponding to abnormal metrics, such as images, videos, and copy, according to different dimensions. By comparing the performance metrics of each segmented creative, the advertising strategy can be optimized. Time segmentation is a method for segmenting and analyzing abnormal metric data along a time dimension. By dividing the overall time period into smaller time units, it allows for more detailed observation of the data's performance, trends, and patterns across different time intervals. Advertising strategy refers to the overall plan for systematically planning, allocating resources, and optimizing the execution of each stage of advertising campaigns to achieve specific marketing objectives.

[0030] In one embodiment, abnormal indicators are segmented by region to obtain regional dimension indicators, by creative segmentation to obtain creative dimension indicators, and by time segmentation to obtain time dimension indicators. The main indicators causing the abnormality are determined to be one or more of the regional dimension indicators, creative dimension indicators, and time dimension indicators. If the indicator causing the abnormality is a regional dimension indicator, the corresponding overall trend, historical data, or deviation from the expected target is determined based on the target advertising data corresponding to the regional indicator. The advertising placement strategy corresponding to the abnormal indicator is then adjusted based on the overall trend, historical data, or deviation from the expected target, such as adjusting the placement ratio and placement time in each region.

[0031] This application embodiment acquires real-time collected advertising data, cleans the data to obtain target advertising data, extracts indicators from the target advertising data to obtain multiple target key indicators, and identifies abnormal indicators based on the fluctuation data of each target key indicator within a preset time period. The abnormal indicators are then segmented by region, creative content, and time. Based on the segmentation results of the abnormal indicators and the target advertising data, the advertising placement strategy corresponding to the abnormal indicators is adjusted. In the above solution, abnormal indicators can be identified by analyzing the fluctuation of data within a preset time period, and the accuracy of abnormal indicator analysis is improved by analyzing the abnormal indicators from dimensions such as region, creative content, and time. Adjusting the advertising placement strategy based on the abnormal indicators improves the effectiveness of advertising placement.

[0032] Figure 2 This is a flowchart of an abnormal indicator determination method provided in an embodiment of this application, such as... Figure 2 As shown, it includes: Step S201: Determine whether the fluctuation frequency is less than the preset fluctuation frequency threshold and whether the changing trends of the target key indicators are consistent, and obtain the first judgment result.

[0033] Step S202: Determine whether the fluctuation range is within the corresponding preset indicator range. If the fluctuation range is not within the preset indicator range, calculate the abnormal ratio between the target key indicator and the preset indicator range, and determine whether the abnormal ratio is less than the preset abnormal ratio threshold to obtain the second judgment result.

[0034] Step S203: Identify the target key indicators whose first and second judgment results are both abnormal as abnormal indicators.

[0035] Optionally, the fluctuation data includes fluctuation frequency and fluctuation range. Fluctuation frequency refers to the number of times data changes or its periodicity within a certain time range, reflecting how frequently data values ​​fluctuate around the mean or trend line. Fluctuation range refers to the difference between the maximum and minimum values ​​of a set of data during its change, directly reflecting the dispersion and magnitude of the data. In one embodiment, it is determined whether the fluctuation frequency is less than a preset fluctuation frequency threshold and whether the overall trend within a preset time is consistent. If the fluctuation frequency is less than the preset fluctuation frequency threshold and the overall trend within the preset time is consistent, it can be considered that the target key indicator is continuously rising or falling within the preset time. This may indicate malicious interference from competitors, leading to inflated key indicators, or a discrepancy between the landing page and the advertisement, causing a continuous decline in key indicators. Based on historical data, different normal fluctuation ranges are pre-defined for different indicators. It is then determined whether the fluctuation range of each key indicator within a preset time period falls within the corresponding preset range. For example, if the preset range for "daily search volume" is 1000-5000 times, and the currently collected daily search volumes for the past 7 days are 1500, 6521, 2889, 4124, 2500, 3842, and 4200 times respectively, then the daily search volume of 6521 times is outside the preset range. Therefore, the abnormal daily search volume is calculated based on its deviation from the preset range. For example, the ratio is determined by identifying the boundary value of the index range similar to the daily search volume of the abnormality, which is 5000 times, and the abnormal ratio is calculated as: (6521-5000) / 5000×100%=30.42%. It is then determined whether the abnormal ratio is less than the preset abnormal ratio threshold. If it is less than or equal to, the target key index can be considered to be fluctuating within a controllable range and the target key index can be determined to be a normal index. If it is greater than, the target key index can be considered to be fluctuating abnormally within an uncontrollable range and the target key index with abnormal fluctuation frequency and fluctuation range can be determined to be an abnormal index.

[0036] This application embodiment obtains a first judgment result by determining whether the fluctuation frequency is less than a preset fluctuation frequency threshold and whether the changing trends of the target key indicators are consistent; it then determines whether the fluctuation range is within the corresponding preset indicator range. If the fluctuation range is not within the preset indicator range, it calculates the abnormal ratio between the target key indicator and the preset indicator range, and determines whether the abnormal ratio is less than a preset abnormal ratio threshold to obtain a second judgment result; the target key indicator for which both the first and second judgment results are abnormal is identified as an abnormal indicator. In the above scheme, each target key indicator can be analyzed from the perspectives of fluctuation frequency and fluctuation range within a preset time period, and abnormal indicators can be identified, thus improving the accuracy of identifying abnormal indicators.

[0037] In one embodiment, after extracting metrics from the target advertising data to obtain multiple target key metrics, the method further includes: generating an advertising metric line chart based on each target key metric, and determining the inflection points of each target key metric on the advertising metric line chart; correspondingly, determining whether the fluctuation data of each target key metric within a preset time period meets preset abnormal conditions, and determining abnormal indicators based on the determination results, including: determining whether the number of indicator inflection points of each target key metric within a preset time period meets preset fluctuation conditions, and determining abnormal indicators based on the determination results.

[0038] Figure 3 This is a line chart of advertising metrics provided in an embodiment of this application, such as... Figure 3 As shown, line charts of advertising metrics are generated based on the changes of each key objective indicator within a preset time period. For example, line charts of advertising metrics are generated based on the changes of CTR and CPC over the past week. The inflection points of the metrics on the line charts and the number of inflection points are determined. Figure 3 As shown, the turning points for the indicators are points B and D, meaning the target key indicator fluctuates 3 times within a preset time period. A reasonable fluctuation range is calculated based on the number of times each target key indicator is collected within the preset time period and the preset fluctuation range value. If the fluctuation number of a target key indicator is outside this reasonable range, it is considered an abnormal indicator. For example, if the CTR indicator was collected 7 times in the past week, and the preset fluctuation range value is 30%-60%, then the reasonable fluctuation range can be calculated to be 2.1-4.2 times. Figure 3 The CTR fluctuated twice between June 1st and June 7th, which is outside the reasonable range of fluctuations. Therefore, the CTR indicator is determined to be an abnormal indicator.

[0039] This application embodiment generates an advertising metric line chart based on each of the target key indicators, determines the inflection points of each target key indicator on the advertising metric line chart, judges whether the number of inflection points of each target key indicator within a preset time period meets preset fluctuation conditions, and identifies abnormal indicators based on the judgment results. In the above scheme, abnormal indicators can be identified intuitively and quickly based on the advertising metric line chart, improving the efficiency of abnormal indicator identification while ensuring accuracy.

[0040] Figure 4 This is a flowchart of an abnormal indicator splitting method provided in an embodiment of this application, such as... Figure 4 As shown, it includes: Step S301: Determine the fine-grained regional splitting corresponding to the indicator type of the abnormal indicator, and perform regional splitting on the abnormal indicator based on the fine-grained regional splitting.

[0041] Step S302: Determine the creative segmentation dimension corresponding to the creative type of the abnormal indicator, and perform creative segmentation on the abnormal indicator based on the creative segmentation dimension. The creative type includes any one or more of copywriting creativity, visual creativity, form creativity and action command creativity.

[0042] Step S303: Determine the time segmentation dimension based on the advertising scenario corresponding to the abnormal indicator, and perform time segmentation on the abnormal indicator based on the time segmentation dimension.

[0043] Among these, "regional segmentation granularity" refers to the level of detail or granularity used when dividing or analyzing geographical regions. It reflects the level of detail in the regional division; higher granularity means a more detailed and smaller regional division, while lower granularity means a coarser and larger division. "Creative segmentation dimensions" refer to different angles or standards for decomposing and classifying creative content in fields such as advertising, marketing, and content creation. By using segmentation dimensions, complex creative systems can be broken down into multiple quantifiable and analyzable elements, facilitating the optimization of creative effects, problem identification, or the uncovering of potential needs. "Time-related segmentation dimensions" refer to standards or frameworks for decomposing and classifying data, activities, processes, etc., from a time-related perspective.

[0044] In one embodiment, a mapping relationship between different indicator types and fine-grained regional segmentation is pre-defined. Based on this mapping relationship, the fine-grained regional segmentation corresponding to the current abnormal indicator is determined, and the abnormal indicator is then segmented regionally based on this fine-grained regional segmentation. For example, if the abnormal indicator is "overall CTR (Click-Through Rate) decline," it is segmented by province or city level to quickly locate problems in large regions. If the abnormal indicator is "conversion cost soaring," it is segmented by business district or county level to eliminate local competition or audience matching issues. The creative types of advertisements can include copywriting, visual design, format design, and CTA design, etc. Different creative types can have corresponding creative segmentation dimensions pre-defined, and the abnormal indicator is then segmented creatively based on these dimensions. For example, if the creative type is "copywriting," the corresponding creative segmentation dimension is any one of the following: title / subtitle, keywords, sentiment keywords, or action instructions. If the creative type is "visual design," the corresponding creative segmentation dimension is any one of the following: image, video style, color scheme, or main element. If the creative type is "Form Creativity," the corresponding creative breakdown dimensions are: any one of the following: static image, animated GIF, short video, carousel, and interactive H5. If the creative type is "Action Command Creativity," the corresponding creative breakdown dimensions are: button text, color, position, and animation. A mapping relationship between advertising scenarios and time-based breakdown dimensions is pre-defined to determine the corresponding time-based breakdown dimension for the current advertising scenario. Abnormal metrics are then broken down by time based on this time-based breakdown dimension. For example, if the current advertising scenario is an e-commerce promotion, abnormal metrics are broken down daily; if the current advertising scenario is a game, abnormal metrics are broken down weekly; and if it is a daily sales scenario, abnormal metrics are broken down monthly.

[0045] This application embodiment determines the fine-grained regional segmentation corresponding to the indicator type of the abnormal indicator, and performs regional segmentation on the abnormal indicator based on the fine-grained regional segmentation; it determines the creative segmentation dimension corresponding to the creative type of the abnormal indicator, and performs creative segmentation on the abnormal indicator based on the creative segmentation dimension. The creative type includes any one or more of copywriting creative, visual creative, formal creative, and action command creative; and it determines the time segmentation dimension according to the advertising placement scenario corresponding to the abnormal indicator, and performs time segmentation on the abnormal indicator based on the time segmentation dimension. In the above scheme, the corresponding segmentation dimensions are determined based on the indicator type, creative type, and corresponding advertising placement scenario of the abnormal indicator, which improves the segmentation accuracy of different dimensions, thereby ensuring the accuracy of subsequent advertising placement strategy adjustment analysis based on the segmentation results.

[0046] In one embodiment, determining the time segmentation dimension based on the advertising scenario corresponding to the abnormal indicator includes: determining the target time period associated with the advertising scenario corresponding to the abnormal indicator; matching the target time period with the current time period corresponding to the abnormal indicator; if the match is consistent, determining the time segmentation dimension as the first time dimension; if the match is inconsistent, determining the time segmentation dimension as the second time dimension, wherein the first time dimension is smaller than the second time dimension.

[0047] For example, since different advertising scenarios correspond to different discounts and different user traffic, different advertising scenarios can be pre-set with different discount periods or target periods with high popularity. For example, if the advertising scenario is the Double Eleven e-commerce promotion, the target period can be from October 20 to November 20. If the advertising scenario is the New Year's Day promotion, the target period can be from December 20 to January 5. The current period corresponding to the abnormal indicator is matched with each of the pre-set target periods. If a matching target period exists, the time is broken down by day, which is the first time dimension. If no matching target period exists, the time is broken down by month, which is the second time dimension.

[0048] This application embodiment determines the target time period associated with the advertising scenario corresponding to the abnormal indicator, and matches the target time period with the current time period corresponding to the abnormal indicator. If the match is consistent, the time segmentation dimension is determined as the first time dimension; if the match is inconsistent, the time segmentation dimension is determined as the second time dimension, where the first time dimension is smaller than the second time dimension. In the above scheme, the method of matching the current time corresponding to the abnormal indicator with each preset time period quickly and accurately determines the corresponding time dimension.

[0049] Figure 5 This is a flowchart of an advertising placement strategy adjustment method provided in an embodiment of this application, such as... Figure 5 As shown, it includes: Step S401: Perform abnormal regional analysis on the first abnormal indicator, inefficient creative analysis on the second abnormal indicator, and sudden abnormal period analysis on the third abnormal indicator to obtain the analysis results.

[0050] Step S402: Adjust the advertising strategy corresponding to the abnormal indicators based on the analysis results and the target advertising data.

[0051] In one embodiment, the breakdown of abnormal indicators includes a first abnormal indicator, a second abnormal indicator, and a third abnormal indicator. The first abnormal indicator can be a regional abnormal indicator, the second abnormal indicator can be a creative abnormal indicator, and the third abnormal indicator can be a time-related abnormal indicator. Correspondingly, the regional abnormal indicators obtained from the regional breakdown are analyzed to determine whether the indicator anomaly is caused by the advertising's geographic location or the specific region causing the anomaly. For example, if the abnormal indicator is a CTR indicator, the mean of the CTR indicators for each region is calculated, the target region with the largest deviation from the mean is identified, and it is determined whether the CTR of this target region is proportional to its actual conversion rate. That is, whether the actual conversion rate of the target region increases with increasing CTR or decreases with decreasing CTR. If so, the target region is considered not the cause of the CTR indicator anomaly; otherwise, the target region is considered the cause or part of the cause of the CTR indicator anomaly. For the creative abnormal indicators, inefficient creative analysis is performed to determine whether the poor creative effect or the existence of better creatives is impacting the advertising performance. For example, if the second anomaly indicator is a creative anomaly indicator obtained by breaking down the copywriting creative type, then it is determined whether the keyword matching degree in the copywriting has decreased or whether the click-through rate of the ad title has dropped sharply. If the matching degree has decreased or the click-through rate of the title has dropped sharply, then the current text creative can be considered as an inefficient creative, and the anomaly indicator is caused by the copywriting of the inefficient creative. The effectiveness of ad placement can be reflected by the ad conversion rate; the higher the ad conversion rate, the better the placement effect. If the anomaly indicator is a CTR indicator, after breaking down the anomaly indicator into a time dimension to obtain a time anomaly indicator, the average CTR within each time period is calculated, the target time period with the largest deviation from the average is determined, and it is determined whether the CTR of the target time period is proportional to the actual conversion rate of the target time period. If not, then the anomaly of the CTR indicator is considered to be caused by an abnormal placement time. Based on the above analysis results, the cause of the indicator anomaly is determined to be one or more of the following: placement region, ad creative, or placement time. If the placement region is abnormal, then the relationship between the number of ads placed in the abnormal region and the ad conversion rate is determined based on the target ad data, and the number of ads placed in the target region is increased or decreased based on this relationship. For example, the system analyzes the increase in ad conversion rate for each ad campaign and compares this value with a preset conversion rate threshold. If the conversion rate is greater than the threshold, the number of ads placed in the affected region is increased; if it is less, the number is decreased. If the analysis indicates the anomaly is due to low ad creative quality, specifically a decrease in keyword match rate, the title text is extracted from the target ad data and updated.If the analysis results indicate that the abnormality in the metrics is caused by the timing of the ad placement, the ad placement volume during the abnormal period is determined based on the target ad data. The number of ad placements to be reduced is calculated based on the preset adjustment ratio, and the number of ad placements corresponding to the abnormal placement time in the ad placement strategy is adjusted based on the number of ad placements to be reduced.

[0052] This application embodiment analyzes the first abnormal indicator by performing abnormal regional analysis, the second abnormal indicator by performing inefficient creative analysis, and the third abnormal indicator by performing sudden abnormal time period analysis to obtain analysis results. Based on the analysis results and target advertising data, the advertising placement strategy corresponding to the abnormal indicators is adjusted. In the above solution, by analyzing the first, second, and third abnormal indicators separately, the causes of the indicator anomalies can be accurately determined. Based on the causes of the anomalies, the number of advertisements can be adjusted in a targeted manner, improving the rationality and accuracy of the advertising placement strategy, and consequently, improving the advertising effectiveness.

[0053] Optionally, adjusting the advertising strategy corresponding to the abnormal indicator based on the analysis results and the target advertising data includes: if the analysis result indicates an abnormal advertising region, determining an adjustment ratio based on the current and expected return rates in the target advertising data, and reducing the number of ads placed in the region corresponding to the abnormal indicator according to the adjustment ratio; if the analysis result indicates an abnormal creative, determining the version update frequency associated with the advertising scenario in the target advertising data, and updating the creative version corresponding to the abnormal indicator according to the version update frequency; if the analysis result indicates an abnormal sudden time period, determining the target time period associated with the advertising scenario in the target advertising data, and adjusting the advertising time period corresponding to the abnormal indicator to the target time period.

[0054] In one embodiment, if the analysis result indicates an anomaly in the target advertising region, the current rate of return in the target advertising data is calculated as a percentage of the expected rate of return under the current advertising scenario. For example, if it's 80%, the current number of placements cannot meet the expected results, so the number of placements needs to be reduced accordingly. The reduction percentage could be 20%, meaning a 20% reduction in the current number of placements. If the analysis result indicates anomalies in copywriting, visual design, or format design, the version update frequency associated with the advertising scenario in the target advertising data is determined, and the copywriting, visual design, or format design corresponding to the anomaly is updated based on the version update frequency. If the analysis result indicates an anomaly in a sudden time period, the target time period associated with the advertising scenario in the target advertising data is determined, and the placement time period corresponding to the anomaly is adjusted to the target time period. For example, the target period for the Double Eleven e-commerce promotion is from October 20 to November 20. The abnormal indicator obtained from the analysis corresponds to the advertising period on October 19. Since this advertising period is not within the target period, the advertising on October 19 can be canceled and the corresponding amount of advertising can be increased to the target period on an average basis, or the advertising on October 19 can be canceled directly to adjust the advertising period.

[0055] This application's embodiments, when the analysis result indicates an abnormal targeting region, determine an adjustment ratio based on the current and expected return rates in the target advertising data, and reduce the number of ads targeting the region corresponding to the abnormal indicator according to the adjustment ratio; when the analysis result indicates an abnormal creative, determine the version update frequency associated with the advertising scenario in the target advertising data, and update the creative version corresponding to the abnormal indicator according to the version update frequency; when the analysis result indicates an abnormal time period, determine the target time period associated with the advertising scenario in the target advertising data, and adjust the targeting time period corresponding to the abnormal indicator to the target time period. The above solutions can adaptively adjust the corresponding advertising targeting strategies for different abnormal situations, improving the rationality and accuracy of advertising targeting strategy adjustments.

[0056] Figure 6 This is a schematic diagram of the structure of an advertising placement strategy adjustment device provided in an embodiment of this application, such as... Figure 6 The above includes: Data cleaning module 21 is used to acquire real-time collected advertising data, clean the advertising data, and obtain target advertising data; The indicator extraction module 22 is used to extract indicators from the target advertising data to obtain multiple target key indicators; The abnormal indicator determination module 23 is used to determine abnormal indicators based on the fluctuation data of each target key indicator within a preset time period. The abnormal indicator splitting module 24 is used to split the abnormal indicators by region, creativity, and time respectively. The advertising strategy adjustment module 25 is used to adjust the advertising strategy corresponding to the abnormal indicator based on the breakdown results of the abnormal indicator and the target advertising data.

[0057] This application embodiment acquires real-time collected advertising data, cleans the data to obtain target advertising data, extracts indicators from the target advertising data to obtain multiple target key indicators, and identifies abnormal indicators based on the fluctuation data of each target key indicator within a preset time period. The abnormal indicators are then segmented by region, creative content, and time. Based on the segmentation results of the abnormal indicators and the target advertising data, the advertising placement strategy corresponding to the abnormal indicators is adjusted. In the above solution, abnormal indicators can be identified by analyzing the fluctuation of data within a preset time period, and the accuracy of abnormal indicator analysis is improved by analyzing the abnormal indicators from dimensions such as region, creative content, and time. Adjusting the advertising placement strategy based on the abnormal indicators improves the effectiveness of advertising placement.

[0058] In one possible embodiment, the fluctuation data includes fluctuation frequency and fluctuation range, and the anomaly indicator determination module 23 is used for: Determine whether the fluctuation frequency is less than a preset fluctuation frequency threshold and whether the changing trends of the target key indicators are consistent to obtain a first judgment result; Determine whether the fluctuation range is within the corresponding preset indicator range. If the fluctuation range is not within the preset indicator range, calculate the abnormal ratio of the target key indicator to the preset indicator range, determine whether the abnormal ratio is less than a preset abnormal ratio threshold, and obtain a second determination result. The target key indicator whose first judgment result and the second judgment result are both abnormal is identified as an abnormal indicator.

[0059] In one possible embodiment, the anomaly indicator splitting module 24 is used for: Determine the fine-grained regional segmentation corresponding to the index type of the abnormal index, and perform regional segmentation on the abnormal index based on the fine-grained regional segmentation. Determine the creative segmentation dimension corresponding to the creative type of the abnormal indicator, and perform creative segmentation on the abnormal indicator based on the creative segmentation dimension. The creative type includes any one or more of copywriting creativity, visual creativity, formal creativity and action command creativity. The time segmentation dimension is determined based on the advertising scenario corresponding to the abnormal indicator, and the abnormal indicator is then segmented over time based on the time segmentation dimension.

[0060] In one possible embodiment, the anomaly indicator splitting module 24 is used for: Determine the target time period associated with the advertising scenario corresponding to the abnormal indicator, match the target time period with the current time period corresponding to the abnormal indicator, and if the match is consistent, determine the time segmentation dimension as the first time dimension. In the event of a mismatch, the time split dimension is determined to be the second time dimension, where the first time dimension is smaller than the second time dimension.

[0061] In one possible embodiment, the breakdown of the abnormal indicators includes a first abnormal indicator, a second abnormal indicator, and a third abnormal indicator, and the advertising delivery strategy adjustment module 25 is used for: The analysis results are obtained by performing abnormal regional analysis on the first abnormal indicator, inefficient creative analysis on the second abnormal indicator, and sudden abnormal period analysis on the third abnormal indicator. Based on the analysis results and the target advertising data, the advertising strategy corresponding to the abnormal indicators is adjusted.

[0062] In one possible embodiment, the advertising delivery strategy adjustment module 25 is used for: If the analysis results indicate that the target region is abnormal, an adjustment ratio is determined based on the current and expected rates of return in the target advertising data, and the number of ads placed in the region corresponding to the abnormal indicator is reduced according to the adjustment ratio. If the analysis result indicates creative anomaly, determine the version update frequency associated with the advertising scenario in the target advertising data, and update the creative version corresponding to the anomaly indicator according to the version update frequency. If the analysis results indicate an abnormal period, a target time period associated with the advertising scenario in the target advertising data is determined, and the advertising time period corresponding to the abnormal indicator is adjusted to the target time period.

[0063] In one possible embodiment, a line chart generation module is also included, which is used to: Based on each of the aforementioned target key indicators, an advertising indicator line chart is generated, and the indicator inflection points of each of the aforementioned target key indicators on the advertising indicator line chart are determined. The abnormal indicator determination module is used to: determine whether the number of indicator inflection points of each target key indicator within a preset time period meets the preset fluctuation conditions, and determine the abnormal indicators based on the judgment results.

[0064] This application also provides an electronic device that can integrate an advertising strategy adjustment device provided in this application. Figure 7This is a schematic diagram of the structure of an advertising placement strategy adjustment device provided in an embodiment of this application, with reference to... Figure 7 The advertising strategy adjustment device includes: an input device 33, an output device 34, a memory 32, and one or more processors 31; the memory 32 is used to store one or more programs; when one or more programs are executed by one or more processors 31, the one or more processors 31 implement the advertising strategy adjustment method provided in the above embodiments. The input device 33, output device 34, memory 32, and processors 31 can be connected via a bus or other means. Figure 7 Taking the example of a connection between China and Israel via a bus.

[0065] The memory 32, as a computing device readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the advertising placement strategy adjustment method provided in any embodiment of this application. The memory 32 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the device. Furthermore, the memory 32 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 32 may further include memory remotely located relative to the processor 31, and these remote memories can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0066] Input device 33 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Output device 34 may include display devices such as a display screen.

[0067] The processor 31 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 32, thereby realizing the above-mentioned advertising placement strategy adjustment method.

[0068] The advertising strategy adjustment device, equipment, and computer provided above can be used to execute the advertising strategy adjustment method provided in any of the above embodiments, and have corresponding functions and beneficial effects.

[0069] This application embodiment also provides a storage medium for storing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to execute the advertising placement strategy adjustment method provided in the above embodiment. The advertising placement strategy adjustment method includes: acquiring real-time collected advertising data; cleaning the advertising data to obtain target advertising data; extracting indicators from the target advertising data to obtain multiple target key indicators; determining abnormal indicators based on the fluctuation data of each target key indicator within a preset time period; performing regional segmentation, creative segmentation, and time segmentation on the abnormal indicators respectively; and adjusting the advertising placement strategy corresponding to the abnormal indicators based on the segmentation results of the abnormal indicators and the target advertising data.

[0070] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disks or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. Furthermore, storage media may reside in a first computer system in which a program is executed, or may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). Storage media may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0071] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the advertising placement strategy adjustment method described above, but can also perform related operations in the advertising placement strategy adjustment method provided in any embodiment of this application.

[0072] The advertising strategy adjustment device, equipment, and storage medium provided in the above embodiments can execute the advertising strategy adjustment method provided in any embodiment of this application. For technical details not described in detail in the above embodiments, please refer to the advertising strategy adjustment method provided in any embodiment of this application.

[0073] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A method for adjusting an advertising placement strategy, characterized in that, include: Acquire real-time collected advertising data, perform data cleaning on the advertising data, and obtain target advertising data; The target advertising data is subjected to indicator extraction to obtain multiple target key indicators, and abnormal indicators are determined based on the fluctuation data of each target key indicator within a preset time period. The abnormal indicators are segmented by region, creative content, and time. Based on the segmentation results of the abnormal indicators and the target advertising data, the advertising delivery strategy corresponding to the abnormal indicators is adjusted.

2. The advertising placement strategy adjustment method according to claim 1, characterized in that, The fluctuation data includes fluctuation frequency and fluctuation range. The step of determining abnormal indicators based on the fluctuation data of each target key indicator within a preset time period includes: Determine whether the fluctuation frequency is less than a preset fluctuation frequency threshold and whether the changing trends of the target key indicators are consistent to obtain a first judgment result; Determine whether the fluctuation range is within the corresponding preset indicator range. If the fluctuation range is not within the preset indicator range, calculate the abnormal ratio of the target key indicator to the preset indicator range, determine whether the abnormal ratio is less than a preset abnormal ratio threshold, and obtain a second determination result. The target key indicator whose first judgment result and the second judgment result are both abnormal is identified as an abnormal indicator.

3. The advertising placement strategy adjustment method according to claim 1, characterized in that, The process of segmenting the abnormal indicators by region, creativity, and time includes: Determine the fine-grained regional segmentation corresponding to the index type of the abnormal index, and perform regional segmentation on the abnormal index based on the fine-grained regional segmentation. Determine the creative segmentation dimension corresponding to the creative type of the abnormal indicator, and perform creative segmentation on the abnormal indicator based on the creative segmentation dimension. The creative type includes any one or more of copywriting creativity, visual creativity, formal creativity and action command creativity. The time segmentation dimension is determined based on the advertising scenario corresponding to the abnormal indicator, and the abnormal indicator is then segmented over time based on the time segmentation dimension.

4. The advertising placement strategy adjustment method according to claim 3, characterized in that, The step of determining the time segmentation dimension based on the advertising scenario corresponding to the abnormal indicator includes: Determine the target time period associated with the advertising scenario corresponding to the abnormal indicator, match the target time period with the current time period corresponding to the abnormal indicator, and if the match is consistent, determine the time segmentation dimension as the first time dimension. In the event of a mismatch, the time split dimension is determined to be the second time dimension, where the first time dimension is smaller than the second time dimension.

5. The advertising placement strategy adjustment method according to claim 1, characterized in that, The breakdown of the abnormal indicators includes a first abnormal indicator, a second abnormal indicator, and a third abnormal indicator. Adjusting the advertising strategy corresponding to the abnormal indicators based on the breakdown results and the target advertising data includes: The analysis results are obtained by performing abnormal regional analysis on the first abnormal indicator, inefficient creative analysis on the second abnormal indicator, and sudden abnormal period analysis on the third abnormal indicator. Based on the analysis results and the target advertising data, the advertising strategy corresponding to the abnormal indicators is adjusted.

6. The advertising placement strategy adjustment method according to claim 5, characterized in that, The adjustment of the advertising delivery strategy corresponding to the abnormal indicators based on the analysis results and the target advertising data includes: If the analysis results indicate that the target region is abnormal, an adjustment ratio is determined based on the current and expected rates of return in the target advertising data, and the number of ads placed in the region corresponding to the abnormal indicator is reduced according to the adjustment ratio. If the analysis result indicates creative anomaly, determine the version update frequency associated with the advertising scenario in the target advertising data, and update the creative version corresponding to the anomaly indicator according to the version update frequency. If the analysis results indicate an abnormal period, a target time period associated with the advertising scenario in the target advertising data is determined, and the advertising time period corresponding to the abnormal indicator is adjusted to the target time period.

7. The advertising placement strategy adjustment method according to claim 2, characterized in that, After extracting metrics from the target advertising data to obtain multiple target key metrics, the process further includes: Based on each of the aforementioned target key indicators, an advertising indicator line chart is generated, and the indicator inflection points of each of the aforementioned target key indicators on the advertising indicator line chart are determined. Accordingly, the step of determining whether the fluctuation data of each target key indicator within a preset time period meets preset abnormal conditions, and determining abnormal indicators based on the determination results, includes: Determine whether the number of indicator inflection points of each target key indicator within a preset time period meets the preset fluctuation conditions, and determine abnormal indicators based on the determination results.

8. An advertising placement strategy adjustment device, characterized in that, include: The data cleaning module is used to acquire real-time collected advertising data, clean the advertising data, and obtain target advertising data. The indicator extraction module is used to extract indicators from the target advertising data to obtain multiple target key indicators; An abnormal indicator determination module is used to determine abnormal indicators based on the fluctuation data of each target key indicator within a preset time period. The abnormal indicator splitting module is used to split the abnormal indicators by region, creativity, and time, respectively. The advertising strategy adjustment module is used to adjust the advertising strategy corresponding to the abnormal indicator based on the breakdown results of the abnormal indicator and the target advertising data.

9. An electronic device, the device comprising: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the advertising delivery strategy adjustment method as described in any one of claims 1-7.

10. A storage medium storing computer-executable instructions, which, when executed by a computer processor, are used to perform the advertising delivery strategy adjustment method as described in any one of claims 1-7.

Images