A multi-platform advertising data integration and analysis system

Abstract

The present invention discloses a multi-platform advertising data integration and analysis system, which relates to the technical field of data integration and analysis and includes: a data layer, which includes a plurality of data collection modules and a plurality of data processing modules; each of the data collection modules is respectively matched with a group of platforms; the plurality of data processing modules are respectively used to receive the raw data of the corresponding data collection module and process it to obtain processed data with feature points; a processing layer, which includes: a screening network module, corresponding to the data processing modules of a group of platforms, and pre-classifying the feature points to establish a multi-layer screening network. The present invention ensures data consistency and standardization by performing duplicate removal and format standardization processing on the received raw data, extracts feature points through a feature library, and establishes a global substitute feature point library to ensure the unity of feature point standards among platforms, realizing the standardized storage and management of feature points on different platforms.

Description

Technical Field

[0001] The present invention relates to the technical field of data integration and analysis, and particularly to a multi-platform advertising data integration and analysis system. Background Art

[0002] With the rapid development of the Internet and the digital transformation of advertising, more and more advertisers have started to place advertisements on multiple platforms to maximize their coverage and accuracy. In multi-platform advertising, data integration and analysis have become the key for advertisers to optimize the advertising effect and improve the user conversion rate. However, due to the differences in data formats, collection methods, and user feature points among various platforms, traditional advertising data analysis systems have significant limitations in cross-platform data integration.

[0003] After retrieval, the Chinese patent (Publication No.: CN116805255B) discloses an automatic advertising optimization and placement system based on user portrait analysis, including an intelligent push module, a user portrait module, a placement optimization module, and an effect analysis module. The user portrait module is used to label users based on shopping information to obtain a user portrait model of the users. The intelligent push module is used to automatically place advertisements for users based on the user portrait model. The effect analysis module is used to analyze the traffic effect of the products after the advertisements are placed, and generate signals of poor benefits, slow benefits, or normal benefits. The placement optimization module is used to receive a placement optimization instruction to optimize the placement of the advertisements corresponding to the products.

[0004] In the prior art, due to the differences in user data among various platforms, the distribution of user portrait feature points is inconsistent, making it difficult to achieve cross-platform unified analysis. Moreover, the existing technologies usually rely on fixed screening rules and lack the ability to dynamically adjust according to data distribution or target portraits, making it difficult to quickly adapt to the differences of different platforms. Therefore, the present invention proposes a multi-platform advertising data integration and analysis system. Summary of the Invention

[0005] The purpose of the present invention is to provide a multi-platform advertising data integration and analysis system to solve the problems mentioned in the above background art.

[0006] The present invention can be realized by the following technical solutions: A multi-platform advertising data integration and analysis system includes a data layer, a processing layer, and a storage layer;

[0007] The data layer includes a plurality of data collection modules and a plurality of data processing modules;

[0008] Each of the data collection modules is respectively matched with a group of platforms, and obtains raw data from the corresponding platform API or platform database according to a predetermined rule;

[0009] Multiple of the data processing modules respectively correspond to a group of data acquisition modules, and are used to receive the raw data from the corresponding data acquisition modules. They include a data cleaning unit, a feature library, and a feature extraction unit;

[0010] The cleaning unit is used to clean the received raw data, including duplicate removal and format standardization;

[0011] Based on the feature library, the feature extraction unit generates feature points from the cleaned raw data to obtain processed data;

[0012] The processing layer is used to receive and dynamically screen the processed data corresponding to each platform. It includes multiple screening network modules, a statistics module, and an analysis module;

[0013] Each screening network module respectively corresponds to a group of data processing modules of a platform, and the screening network module pre-classifies the feature points and establishes a multi-layer screening network to screen the processed data of the corresponding platform. Among them, different levels correspond to different degrees of importance of the feature points. When screening, the importance of the feature points is gradually screened from high to low, and the successfully screened processed data is integrated to obtain a screening data set for subsequent statistics and analysis;

[0014] The statistics module receives the cleaned raw data from each cleaning unit and receives the screening data set from the corresponding screening network module;

[0015] After receiving the cleaned raw data and the screening data set, the statistics module performs an association process on them to obtain the screening rate of the corresponding screening network;

[0016] The analysis module integrates and analyzes the screening data set that meets the screening rate requirements to obtain analysis data, including the behavior patterns, interest trends, and user portraits of the corresponding platform;

[0017] The storage layer is used to store the raw data and analysis data of each platform. By storing the raw data of each platform, it ensures that there is a complete record of the data before it is processed.

[0018] A further technical improvement of the present invention lies in that: the screening network adopts a dynamic adjustment mechanism, and its adjustment method includes the following steps:

[0019] S1. The screening network sets weights for each feature point based on the importance of each feature point and sets multiple screening layers;

[0020] S2. After each screening layer screens the data, it counts the actual screening rate and the screening quantity of each feature point, and uses the statistical results as feedback signals for subsequent dynamic adjustment of the screening criteria;

[0021] S3. Dynamically adjust the screening conditions of the subsequent layer according to the feedback signal of the statistical result to ensure that the final screening network meets the target screening rate and maintain the balanced distribution of each feature point.

[0022] A further technical improvement of the present invention lies in that: Step S3 includes:

[0023] A1. Calculating the screening rate deviation;

[0024] Calculate the difference between the actual screening rate and the target screening rate;

[0025] A2. Adjust the weights of the feature points of the subsequent levels based on the number of screened feature points in the feedback to ensure that the key feature points are retained;

[0026] It is obtained through the formula Obtained;

[0027] w k,i+1 Is the weight of the feature point k in the i + 1 layer;

[0028] N k,g Is the expected data volume of the target feature point k;

[0029] N k,i Is the actual data volume of the feature point k in the i layer;

[0030] γ is the weight adjustment rate, and η is a constant;

[0031] A3. Identify the screening rate of the corresponding feature point. After the deviation of the corresponding screening rate exceeds the preset threshold, introduce feature points with the same weight for substitution to maintain the stability of screening.

[0032] A further technical improvement of the present invention lies in that: The storage layer includes a global substitution feature point library, and its generation method includes:

[0033] Q1. Global statistics;

[0034] Extract the feature point distribution from the historical data of each platform, analyze the common values of each feature point on the corresponding platform, and then determine the range and standard of the global feature points;

[0035] Q2. Cluster analysis;

[0036] Classify similar feature points through the clustering algorithm to generate the standard categories or intervals of each feature point. The value range and average weight of the center of each category of feature points constitute the substitution feature points;

[0037] Q3. Manual optimization;

[0038] Manually correct the globally substituted feature points processed by Q2, integrate the corrected substituted feature points to obtain a global substituted feature point library, and ensure that the global substituted feature point library is consistent with the actual business requirements.

[0039] A further technical improvement of the present invention lies in that: the analysis module judges whether the screening network of each platform meets the output screening data set by pre-inputting the user portrait and the screening rate;

[0040] If the corresponding platform cannot meet the pre-input user portrait and screening rate, the corresponding screening network generates substituted feature points to replace the feature points of the pre-input user portrait and screening rate, and adjusts the screening network to assist the user in performing integrated analysis between different platforms.

[0041] A further technical improvement of the present invention lies in that: the method for the analysis module to judge the screening network of each platform includes the following steps:

[0042] Z1. Judge the platform adaptability. According to the actual data volume and feature point distribution of each platform, judge whether it meets the pre-input user portrait P in and the screening rate R in , including the adaptation rate ratio and the portrait similarity;

[0043] The adaptation rate ratio judges whether the screening rate target is met by calculating the ratio of the actual data volume of the platform to the required data volume. If the ratio of the actual data volume to the required data volume is less than 1, the platform cannot meet the screening rate requirement;

[0044] Z2. When the corresponding platform cannot meet the screening rate requirement, its corresponding screening network module adjusts the user portrait feature points of the corresponding platform by generating substituted feature points similar to the feature points of the pre-input user portrait, so that it is close to or meets the pre-input screening rate and user portrait;

[0045] It judges the similarity of the substituted feature points through the formula ;

[0046] wherein, T k is the feature point in the pre-input portrait, T' k is the substituted feature point generated by the platform, M is the number of feature point samples, and is used to calculate the distribution similarity of T k and T'; k ;

[0047] Z3. Based on the substituted feature points, adjust the feature point weights of the screening network, redefine the screening conditions of each feature point, and ensure that the screening process conforms to the pre-input user portrait;

[0048] It resets the weight w k,new, adjust the influence of the substitute feature points in the screening network, and its formula is: w k,new = w k ×(1 - γ×(1 - S' k ));

[0049] Where S' k represents the similarity between the substitute technical feature point T' k and the target feature point;

[0050] γ is the adjustment coefficient for controlling the substitute feature point T' k ;

[0051] Z4. After readjusting the weights of the feature points and the screening conditions, screen the processed data of the platform, and calculate the adjusted screening rate R new , and determine whether it meets the pre-input screening rate R in ;

[0052] Where,

[0053] N p,new is the amount of data passed through the adjusted screening network;

[0054] N t is the total amount of processed data input;

[0055] δ is a constant;

[0056] If R new ≥ R in , then the corresponding platform meets the pre-input screening rate requirement after adjustment;

[0057] Otherwise, the platform is still marked as mismatched, and its data weight is reduced or marked as a secondary reference during analysis;

[0058] Z5. If the screening rate of the platform still cannot be met after adjustment, regenerate different substitute feature points, and continue to adjust the weights of the feature points and the screening conditions until the screening rate is the same as the pre-input screening rate;

[0059] If the screening rate standard still cannot be achieved finally, record it as "incompatible platform", make corresponding markings, and reduce its influence in subsequent analysis.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] Through deduplication and format standardization processing of the received original data, the present invention ensures data consistency and standardization, extracts feature points through a feature library, and establishes a global substitute feature point library to ensure the unity of feature point standards among platforms, realizing the standardized storage and management of feature points on different platforms. Even when the feature points are not completely consistent, the system can automatically select similar feature points for substitution, maintaining the consistency of cross-platform portrait analysis and improving the adaptability and accuracy of the system;

[0062] Moreover, the present invention adopts a multi-level dynamic screening network, which supports hierarchical screening based on the importance of feature points and realizes fast screening through layer-by-layer screening and feedback mechanisms. At the same time, the screening network is dynamically adjusted through feedback signals, enabling the system to adapt to platform data in real time and meet the requirements of preset screening rates and user portraits. Even if the data of a certain platform does not meet the initial conditions, the system can ensure the adaptability of the screening network by automatically adjusting the screening conditions, providing efficient and flexible cross-platform data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings.

[0064] Figure 1 It is the system block diagram of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0065] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will, in conjunction with the accompanying drawings and preferred embodiments, describe in detail the specific embodiments, structures, features and effects according to the present invention.

[0066] Embodiment 1

[0067] Please refer to Figure 1 As shown, the present invention provides a multi-platform advertising placement data integration and analysis system, including a data layer, a processing layer and a storage layer;

[0068] The data layer includes a plurality of data acquisition modules and a plurality of data processing modules;

[0069] Each data acquisition module is respectively matched with a group of platforms and obtains original data from the corresponding platform database according to a predetermined rule;

[0070] A plurality of data processing modules respectively correspond to a group of data acquisition modules, which are used to receive the original data of the corresponding data acquisition module, and include a data cleaning unit, a feature library and a feature extraction unit;

[0071] The cleaning unit is used to clean the received original data, including deduplication and format standardization;

[0072] The deduplication of the original data includes unique identifier detection, field matching detection, similarity algorithm detection, and time window deduplication;

[0073] The format standardization of the original data includes:

[0074] Field name standardization: uniformly map the data field names from different sources;

[0075] Data type normalization: standardize the data types of the fields. In this embodiment, the date fields are unified into "XXXX-YY-RR", and the currency is unified into decimal format to ensure the consistency of the precision of the numerical fields;

[0076] Format unification: unify the text format and numerical format into a unified standard;

[0077] Null value and outlier handling: set the filling value for the missing data, and the filling value is filled with a fixed field or the average value;

[0078] Encoding conversion: unify the encoding formats of each original data into the same encoding;

[0079] Based on the feature library, the feature extraction unit generates feature points for the cleaned original data to obtain the processed data;

[0080] The processing layer is used to receive and dynamically screen the processed data corresponding to each platform, and it includes multiple screening network modules, a statistics module, and an analysis module;

[0081] Each screening network module corresponds to a data processing module of a group of platforms, and the screening network module pre-classifies the feature points, establishes a multi-layer screening network to screen the processed data corresponding to the platform. Among them, different levels correspond to the importance of different feature points. When screening, the importance of the feature points is gradually screened from high to low. The successfully screened processed data is integrated to obtain a screening data set for subsequent statistics and analysis;

[0082] When the missing data uses a fixed field, the corresponding processed data is not screened when passing through the feature points corresponding to the screening network, and is screened out;

[0083] When the missing data uses the average value, the corresponding processed data is randomly assigned in the hierarchical layer of the feature points corresponding to the screening network. And in the distribution of one cycle, the already assigned feature points are removed until all the feature points of the same level have been assigned, and then the next cycle of distribution starts;

[0084] The statistics module receives the cleaned original data from each cleaning unit and receives the screening data set from the corresponding screening network module;

[0085] After receiving the cleaned original data and the screening data set, the statistical module associates them to obtain the screening rate of the corresponding screening network;

[0086] The analysis module integrates and analyzes the screening data set that meets the screening rate requirements to obtain analysis data, including the behavior patterns, interest trends, and user portraits of the corresponding platforms;

[0087] The storage layer is used to store the original data and analysis data of each platform. By storing the original data of each platform, it ensures that there are complete records before the data is processed;

[0088] The screening network adopts a dynamic adjustment mechanism, and its adjustment method includes the following steps:

[0089] S1. The screening network sets weights for each feature point based on the importance of each feature point and sets multiple screening layers;

[0090] S2. After each screening layer screens the data, it counts the actual screening rate and the screening quantity of each feature point, and uses the statistical results as feedback signals for the subsequent dynamic adjustment screening criteria;

[0091] The actual screening rate is obtained through the formula obtained;

[0092] where, R i is the actual screening rate of the i-th layer, N p,i is the amount of data screened and passed through the i-th layer, N t,i is the total amount of data entering the i-th layer, and ∈ is a constant used to prevent the denominator from being 0;

[0093] The screening quantity of each feature point is obtained through the formula obtained;

[0094] where, N k,i is the amount of data containing feature point k in the i-th layer, d j is the j-th piece of data;

[0095] Ⅱ(·) is an indicator function used to determine whether the corresponding processed data contains feature point k;

[0096] S3. According to the feedback signal of the statistical results, dynamically adjust the screening conditions of the subsequent layers to ensure that the final screening network meets the target screening rate and maintains an even distribution of each feature point;

[0097] Step S3 includes:

[0098] A1. Calculate the screening rate deviation ΔR i Calculate;

[0099] Calculate the difference between the actual screening rate and the target screening rate, and the formula used is: ΔRi = R g,i - R i ;

[0100] R g,i is the target screening rate of the i-th layer, and R i is the actual screening rate of the i-th layer;

[0101] A2. Adjust the weights of feature points in subsequent levels based on the number of feature points screened in the feedback to ensure that key feature points are retained. Key feature points include user information (age, gender, geographical location), interest tags (interest fields on the corresponding platform, including sports, fashion, technology, learning, life), purchase behavior (consumption frequency, consumption amount, shopping preferences), interaction behavior (click-through rate, browsing duration, feedback actions), response behavior (conversion rate, exit rate, repeat visit behavior), channel characteristics (device type, device system), and time characteristics (access time period, seasonal preferences);

[0102] It is obtained through the formula ;

[0103] w k,i+1 is the weight of feature point k in the (i + 1)-th layer;

[0104] N k,g is the expected data volume of target feature point k;

[0105] N k,i is the actual data volume of feature point k in the i-th layer;

[0106] γ is the weight adjustment rate, and η is a constant;

[0107] A3. Identify the screening rate of the corresponding feature point. After the deviation of the corresponding screening rate exceeds the preset threshold, introduce feature points with the same weight for replacement to maintain the stability of screening. The adjustment formula used is:

[0108] θ k,i+1 = θ k′,i+1 + α × ΔR i × w k,i+1 ;

[0109] θ k,i+1 is the screening threshold of feature point k in the (i + 1)-th layer;

[0110] θ k′,i+1 is the threshold of the replacement feature point k' in the i-th layer;

[0111] α is the threshold adjustment rate;

[0112] After screening each layer, count the actual screening rate and the number of feature points screened for each feature point, form a feedback signal, and dynamically adjust the weights and importance thresholds of subsequent layers;

[0113] And through the feedback and dynamic adjustment mechanism of each layer, the screening network gradually generates a screening data set that meets the target screening rate and user profile.

[0114] Embodiment 2

[0115] A multi-platform advertising data integration and analysis system includes a data layer, a processing layer, and a storage layer;

[0116] The data layer includes multiple data collection modules and multiple data processing modules;

[0117] Each data collection module is respectively matched with a group of platforms, and obtains raw data from the corresponding platform API according to a predetermined rule;

[0118] Multiple data processing modules respectively correspond to a group of data collection modules, which are used to receive the raw data of the corresponding data collection module, and include a data cleaning unit, a feature library, and a feature extraction unit;

[0119] The cleaning unit is used to clean the received raw data, including duplicate removal and format standardization;

[0120] The duplicate removal of the raw data includes: unique identifier detection, field matching detection, similarity algorithm detection, and time window duplicate removal;

[0121] The format standardization of the raw data includes: field name standardization, data type normalization, format unification, null value and outlier processing, and encoding conversion;

[0122] The feature extraction unit generates feature points for the cleaned raw data based on the feature library to obtain processed data;

[0123] The processing layer is used to receive and dynamically screen the processed data corresponding to each platform, and includes multiple screening network modules, a statistics module, and an analysis module;

[0124] Each screening network module respectively corresponds to a group of data processing modules of the platform, and the screening network module pre-classifies the feature points, establishes a multi-layer screening network to screen the processed data of the corresponding platform. Among them, different levels correspond to the importance of different feature points. When screening, the importance of the feature points is gradually screened from high to low, and the successfully screened processed data is integrated to obtain a screening data set for subsequent statistics and analysis;

[0125] The statistics module receives the cleaned raw data from each cleaning unit and receives the screening data set from the corresponding screening network module;

[0126] After receiving the cleaned raw data and the screening data set, the statistics module performs an association process on them to obtain the screening rate of the corresponding screening network;

[0127] The analysis module integrates and analyzes the screening data sets that meet the screening rate requirements to obtain analysis data, including the behavior patterns, interest trends, and user portraits of the corresponding platforms;

[0128] The storage layer is used to store the original data and analysis data of each platform. By storing the original data of each platform, it ensures that there are complete records before the data is processed;

[0129] The storage layer includes a global substitute feature point library, and its generation method includes:

[0130] Q1. Global statistics;

[0131] Extract the feature point distribution from the historical data of each platform, analyze the general values of each feature point on the corresponding platform, and then determine the range and standard of the global feature points;

[0132] Q2. Cluster analysis;

[0133] Classify similar feature points through a clustering algorithm to generate the standard categories or intervals of each feature point. The value range and average weight of the center of each class of feature points constitute the substitute feature points;

[0134] Q3. Manual optimization;

[0135] Manually correct the global substitute feature points processed by Q2, integrate the corrected substitute feature points to obtain the global substitute feature point library, and ensure that the global substitute feature point library is consistent with the actual business requirements.

[0136] In this embodiment, the analysis module judges whether the screening network of each platform meets the output screening data set by pre-inputting the user portrait and the screening rate;

[0137] If the corresponding platform cannot meet the pre-input user portrait and screening rate, its corresponding screening network generates substitute feature points to replace the feature points of the pre-input user portrait and screening rate, and adjusts the screening network to assist the user in performing integrated analysis between different platforms.

[0138] The method for the analysis module to judge the screening network of each platform includes the following steps:

[0139] Z1. Judge the platform adaptability. According to the actual data volume and feature point distribution of each platform, judge whether it meets the pre-input user portrait P in and the screening rate R in , including the adaptation rate ratio and the portrait similarity;

[0140] The adaptation rate ratio calculates the ratio of the actual data volume of the platform to the required data volume to determine whether the screening rate target is met. If the ratio of the actual data volume to the required data volume is less than 1, the platform cannot meet the screening rate requirement;

[0141] The portrait similarity is obtained through the formula If S exceeds the set threshold, the user portrait of the platform is quite different from the pre-input platform portrait and needs to be adjusted;

[0142] where K is the total number of feature points of the user portrait, that is, the number of key feature points included in the pre-input user portrait;

[0143] w k is the weight of feature point k, indicating the importance of this feature point in the portrait;

[0144] T k is the ideal value of the k-th feature point of the target portrait;

[0145] P k is the actual value of the k-th feature point of the platform user portrait;

[0146] Z2. When the corresponding platform cannot meet the screening rate requirement, its corresponding screening network module adjusts the user portrait feature points of the corresponding platform by generating substitute feature points similar to the feature points of the pre-input user portrait, so that they are close to or meet the pre-input screening rate and user portrait;

[0147] It judges the similarity of the substitute feature points through the formula ;

[0148] where, T k is the feature point in the pre-input portrait, T′ k is the substitute feature point generated by the platform, and M is the number of feature point samples, which is used to calculate the distribution similarity of T k and T′ k ;

[0149] Z3. Based on the substitute feature points, adjust the feature point weights of the screening network, redefine the screening conditions for each feature point, and ensure that the screening process conforms to the pre-input user portrait;

[0150] It adjusts the influence of the substitute feature points in the screening network by resetting the weight w k,new on the basis of the substitute feature points. The formula is: w k,new = w k ×(1 - γ×(1 - S′ k ));

[0151] where S′ k represents the substitute technical feature point T′ kSimilarity with the target feature points;

[0152] γ is the adjustment coefficient for controlling the substitute feature point T′ k ;

[0153] Z4. After readjusting the weights of the feature points and the screening conditions, screen the processed data of the platform, and calculate the adjusted screening rate R new , and determine whether it meets the pre-input screening rate R in ;

[0154] Among them,

[0155] N p,new is the amount of data passed through the adjusted screening network;

[0156] N t is the total amount of input processed data;

[0157] δ is a constant;

[0158] If R new ≥R in , then the corresponding platform meets the pre-input screening rate requirements after adjustment;

[0159] Otherwise, the platform is still marked as mismatched, and its data weight is reduced or marked as a secondary reference during analysis;

[0160] Z5. If the screening rate of the platform still cannot be met after adjustment, regenerate different substitute feature points, and continue to adjust the weights of the feature points and the screening conditions until the screening rate is the same as the pre-input screening rate;

[0161] In this embodiment, a preset adjustment times threshold is set. After the number of adjustments exceeds the adjustment times threshold, the platform is recorded as an "incompatible platform" to reduce resource consumption and computational overhead.

[0162] The above is only a preferred embodiment of the present invention, and does not impose any form of limitation on the present invention. Although the present invention has been disclosed above with preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the above-disclosed technical content to make equivalent embodiments with equivalent changes, but as long as it does not depart from the technical content of the present invention, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A multi-platform advertising data integration and analysis system, characterized in that: include: The data layer includes a plurality of data acquisition modules and a plurality of data processing modules; Each of the data acquisition modules is matched with a group of platforms respectively, and obtains raw data from the corresponding platform API or platform database according to predetermined rules; The plurality of data processing modules respectively correspond to a group of data acquisition modules, which are used to receive the original data of the corresponding data acquisition modules and process the original data to obtain processed data with characteristic points; The processing layer receives and dynamically screens the processing data corresponding to each platform, including: The screening network module corresponds to a data processing module of a group of platforms, and the screening network module pre-classifies the feature points, establishes a multi-layer screening network, and screens the processing data of the corresponding platform, and obtains the screening data set through integration; The statistical module receives the cleaned raw data from each cleaning unit, receives the screening data set from the corresponding screening network module, and performs correlation processing to obtain the screening rate of the corresponding screening network; Different levels of the screening network correspond to the importance of different feature points. During screening, the importance of feature points is gradually screened from high to low; The screening network adopts a dynamic adjustment mechanism, and its adjustment method includes the following steps: S1. The screening network sets weights for each feature point based on its importance, and sets multiple screening layers; S2. After screening the data, each screening layer counts the actual screening rate and the number of screenings at each characteristic point, and uses the statistical results as feedback signals for subsequent dynamic adjustment of the screening standard; S3. Dynamically adjust the screening conditions of subsequent layers according to the feedback signal of the statistical results, including: A1. Calculation of screening rate deviation; A2. Based on the number of feature point screenings fed back, adjust the weights of feature points at subsequent levels to ensure that key feature points are retained; A3. Identify the screening rate of the corresponding feature point. When the corresponding screening rate deviation exceeds the preset threshold, introduce a feature point with the same weight to replace it to maintain the stability of screening; The analysis module integrates and analyzes the screening data sets that meet the screening rate requirements to obtain analytical data, including the behavior patterns, interest trends, and user portraits of the corresponding platforms; The analysis module determines whether the screening network of each platform satisfies the output screening data set by pre-inputting user portraits and screening rates; If the corresponding platform cannot satisfy the pre-input user portrait and screening rate, the corresponding screening network generates replacement feature points to replace the pre-input user portrait and screening rate feature points, and adjusts the screening network; The storage layer stores the raw data and analysis data of each platform.

2. A multi-platform advertising data integration and analysis system according to claim 1, characterized in that: The data processing module includes a data cleaning unit, a feature library and a feature extraction unit; The cleaning unit cleans the received raw data, including deduplication and format standardization; The feature extraction unit generates feature points for the cleaned original data based on the feature library to obtain processed data.

3. The multi-platform advertising data integration and analysis system according to claim 1, characterized in that: The formula used in step A2 is: ; in, is the weight of feature point k in the i+1th layer; is the expected data volume of the target feature point k; is the actual data volume of feature point k in the i-th layer; is the weight adjustment rate, is a constant.

4. The multi-platform advertising data integration and analysis system according to claim 1, characterized in that: The storage layer includes a global replacement feature point library, and the generation method thereof includes: Q1. Global statistics; Extract the distribution of feature points from the historical data of each platform, analyze the common values ​​of each feature point on the corresponding platform, and then determine the scope and standard of global feature points; Q2, cluster analysis; Similar feature points are classified by clustering algorithm to generate standard categories or intervals for each feature point. The value range and average weight of the center of each type of feature point constitute the replacement feature point; Q3, manual tuning; The global replacement feature points processed by Q2 are manually corrected, and the corrected replacement feature points are integrated to obtain a global replacement feature point library.

5. The multi-platform advertising data integration and analysis system according to claim 1, characterized in that: The analysis module determines the screening network of each platform, including the following steps: Z1. Determine the platform adaptability and whether it meets the pre-input user profile and screening rate based on the actual data volume and feature point distribution of each platform; Z2. When the corresponding platform cannot meet the screening rate requirement, the corresponding screening network module generates replacement feature points similar to the pre-input user portrait feature points, and adjusts the user portrait feature points of the corresponding platform to make them close to or meet the pre-input screening rate and user portrait; Z3. Based on the replacement feature points, adjust the feature point weights of the screening network and redefine the screening conditions for each feature point to ensure that the screening process conforms to the pre-input user portrait; Z4. After re-adjusting the feature point weights and screening conditions, the platform's processed data is screened, the adjusted screening rate is calculated, and it is determined whether it meets the pre-input screening rate; Z5. If the screening rate of the platform still cannot be met after adjustment, different replacement feature points are regenerated, and the feature point weights and screening conditions are continued to be adjusted.

Images