An advertisement data management system based on market trend analysis

Abstract

The application relates to the technical field of network advertising, in particular to an advertisement data management system based on market trend analysis, which comprises a data acquisition module, an analysis module, a prediction module, a conversion rate calculation module and an adjustment module. The application reflects the advertising effect by acquiring the click and purchase data after the advertisement is put, accurately identifies the change trend of user behavior through the analysis module, calculates the user change rate, thereby providing data support for the advertisement putting strategy, predicts the future purchase trend through the analysis of historical data, accurately evaluates the conversion rate change of the advertisement through the comparison between real-time and prediction data, provides the basis for optimizing the advertising effect, judges whether the advertisement putting duration needs to be adjusted according to the comprehensive analysis of the user change rate and the conversion rate change rate, ensures the efficient use of the advertising resources, significantly improves the accuracy and flexibility of the advertisement putting, is beneficial to the conversion rate and the return on investment of the advertisement, and realizes the continuous optimization and improvement of the advertising effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of network advertising, and in particular to an advertising data management system based on market trend analysis. BACKGROUND

[0002] In today's rapidly developing digital marketing, accurate evaluation and optimization of advertising effectiveness have become the key to improving market competitiveness for enterprises. Traditional advertising data management methods are often limited to static data analysis, which cannot capture real-time user behavior trends and market dynamics, resulting in a lack of flexibility and relevance in advertising strategies. Advertisers often rely on experience and limited historical data to develop advertising strategies, making it difficult to accurately predict advertising conversion effectiveness and user response trends, and investment returns are uncertain.

[0003] The patent document with publication number CN112801712A discloses an advertising optimization method and device, which includes: obtaining attribute information of each advertising position, and multiple historical traffic data collected by each advertising position in multiple consecutive predetermined sampling time periods, respectively quantizing the attribute information of each advertising position and the multiple historical traffic data, generating an advertising position information sequence, inputting the advertising position information sequence into a trained traffic prediction model, obtaining high-dimensional features of the advertising position information sequence through a multi-level residual convolutional network, and determining the predicted traffic characteristics of each advertising position according to the high-dimensional features and the traffic prediction function. By dimensionality reduction processing of the predicted traffic characteristics, the predicted traffic data of each advertising position in the predicted time range is obtained, and the advertising placement strategy of each advertising position is optimized according to the predicted traffic data of each advertising position.

[0004] From this, the following problems are seen: in the prior art, the market trend of advertising cannot be predicted to adjust the strategy of advertising placement, resulting in poor advertising investment and return conversion rate. SUMMARY

[0005] To this end, the present application provides an advertising data management system based on market trend analysis to overcome the problem that the market trend of advertising cannot be predicted in the prior art to adjust the strategy of advertising placement, resulting in poor advertising investment and return conversion rate, by comprehensively analyzing user market changes.

[0006] To achieve the above-mentioned purpose, the present application provides an advertising data management system based on market trend analysis, comprising:

[0007] The data acquisition module is used to obtain the real-time click count and real-time purchase count of the advertising after reaching the advertising placement duration to obtain real-time advertising data, and to obtain historical advertising data corresponding to the real-time advertising data, including historical click count and historical purchase count.

[0008] an analysis module connected with the data acquisition module, configured to analyze user change trend and calculate user change rate according to the historical click times and the real-time click times;

[0009] a prediction module connected with the data acquisition module, configured to predict purchase times according to the historical click times and the historical purchase times to obtain a prediction result;

[0010] a conversion rate calculation module connected with the data acquisition module and the prediction module respectively, configured to obtain a comparison result by comparing the prediction result with the real-time purchase times, and determine a conversion rate change rate based on the comparison result;

[0011] an adjustment module connected with the data acquisition module, the analysis module and the conversion rate evaluation module respectively, configured to determine whether to adjust the advertisement launching duration according to the user change rate, and calculate an adjustment rate according to the conversion rate change rate and the user change rate, and adjust the advertisement launching duration according to the adjustment rate.

[0012] Further, the analysis module comprises:

[0013] a trend analysis unit, configured to divide the historical click times into periods, and determine user change trend according to comparison results of historical click totals of adjacent periods;

[0014] a change rate calculation unit connected with the trend analysis unit, configured to calculate the user change rate according to the historical click times and the real-time click times when determining that the user is in a growth or decrease trend.

[0015] Further, the trend analysis unit comprises:

[0016] a period division sub-unit, configured to set a calculation period;

[0017] a period calculation sub-unit connected with the period division sub-unit, configured to calculate each of the historical click totals corresponding to each of the calculation periods;

[0018] a trend analysis sub-unit connected with the period calculation sub-unit, configured to calculate a difference value of the historical click totals of a later period minus a former period of each of adjacent periods, and calculate a difference total sum of all difference values, and determine user change trend based on the difference total sum.

[0019] Further, the change rate calculation unit comprises:

[0020] a graph drawing sub-unit, configured to draw a scatter plot of the historical click times in a coordinate axis according to the historical click times when the user is in a growth or decrease trend, and fit a straight line representing the change trend;

[0021] a change rate calculation subunit connected with the image drawing subunit, configured to calculate a mean value of a slope of the straight line and an abscissa axis divided by a total number of historical clicks, to obtain the user change rate.

[0022] Further, the prediction module comprises:

[0023] a model training unit configured to train the prediction model according to a part of data of the historical click number and the historical purchase number, to obtain a training model;

[0024] a model verification unit connected with the model training subunit, configured to verify the training model according to another part of data of the historical data, to obtain a verification model;

[0025] a model optimization unit connected with the model verification subunit, configured to optimize the verification model to predict the prediction result.

[0026] Further, the conversion rate calculation module comprises:

[0027] a comparison unit configured to compare the prediction result and the real-time purchase number, to obtain a comparison result;

[0028] a calculation unit connected with the comparison unit, configured to determine a conversion rate change according to the comparison result, and calculate a conversion rate change rate based on a determination result.

[0029] Further, the calculation unit comprises:

[0030] a receiving subunit configured to receive the comparison result;

[0031] a determination subunit connected with the receiving subunit, configured to determine a conversion rate change according to the comparison result, wherein,

[0032] if the prediction result is less than the real-time purchase number, it is determined that the conversion rate increases;

[0033] if the prediction result is equal to the real-time purchase number, it is determined that the conversion rate is unchanged;

[0034] if the prediction result is greater than the real-time purchase number, it is determined that the conversion rate decreases;

[0035] a calculation subunit connected with the determination subunit, configured to calculate the conversion rate change rate when it is determined that the conversion rate increases or the conversion rate decreases.

[0036] Further, the adjustment module comprises:

[0037] An adjustment determination unit is configured to compare the user change rate with a preset user change rate threshold, and determine whether to adjust the advertisement delivery time length based on the comparison result.

[0038] An adjustment unit is connected with the adjustment determination unit, and configured to calculate an adjustment rate according to the conversion rate change rate and the user change rate when it is determined to adjust the advertisement delivery time length, and adjust the advertisement delivery time length according to a preset adjustment coefficient.

[0039] Further, the adjustment unit comprises:

[0040] An adjustment rate calculation sub-unit is configured to assign weights to the conversion rate change rate and the user change rate, and calculate an adjustment rate.

[0041] An adjustment value calculation sub-unit is connected with the adjustment rate calculation sub-unit, and configured to determine an adjustment value according to the adjustment rate and the adjustment coefficient, so as to adjust the advertisement delivery time length.

[0042] Further, the data acquisition module comprises:

[0043] A first acquisition unit is configured to acquire the real-time click times and the real-time purchase times of the advertisement after the advertisement delivery time length is reached.

[0044] A second acquisition unit is configured to acquire the historical click times and the historical purchase times.

[0045] Compared with the prior art, the present application has the beneficial effects that through the deep combination of real-time data and historical data, the intelligent management and optimization of the advertisement delivery effect are realized, the click and purchase data after the advertisement delivery are acquired in real time, the advertisement effect is reflected in time, the change trend of the user behavior is accurately identified through the analysis module, the user change rate is calculated, data support is provided for the advertisement delivery strategy, the prediction module can efficiently predict the future purchase trend through the analysis of the historical data, the conversion rate calculation module accurately evaluates the conversion rate change of the advertisement through the comparison of real-time and prediction data, provides an important basis for optimizing the advertisement effect, the adjustment module intelligently judges whether the advertisement delivery time length needs to be adjusted according to the comprehensive analysis of the user change rate and the conversion rate change rate, ensures the efficient use of advertisement resources, significantly improves the precision and flexibility of the advertisement delivery, improves the conversion rate and the return on investment of the advertisement, and realizes the continuous optimization and improvement of the advertisement effect.

[0046] Further, by dividing the historical click count into cycles, the user's interaction pattern in different time periods can be analyzed in depth, and potential trend changes can be identified. This periodic comparative analysis not only reveals the dynamic changes in user interest and behavior, but also helps advertisers understand the fluctuations in user demand in different market environments and time backgrounds, thereby providing more accurate basis for advertising placement strategies. The change rate calculation unit accurately calculates the user change rate by comparing the real-time click count with the historical click count, quickly identifies changes in user engagement, and adjusts the advertising content and placement strategy in a timely manner to adapt to the rapid changes in user demand, effectively improving the accuracy and effectiveness of advertising placement, and further promoting the return on investment of advertising investment.

[0047] Further, by aggregating the historical click total in each calculation period, a reliable data foundation is provided for subsequent trend analysis. By calculating the difference in historical click total between adjacent periods, the fluctuations in user behavior can be identified in depth, and the user change trend can be accurately determined through comprehensive evaluation of the difference. This method not only improves the accuracy of user change trend determination, but also timely captures potential market changes and quickly responds to market demand changes, providing a scientific basis for adjusting advertising placement strategies, thereby improving the effectiveness of advertising placement and market competitiveness.

[0048] Further, by converting the historical click count into a scatter plot on the coordinate axis, not only is the distribution of data visually displayed, but also complex data changes are converted into a simple and clear linear expression by fitting a straight line representing the change trend. The slope of the trend line and the horizontal axis is used as a quantitative indicator of the user change rate, achieving accurate quantitative analysis of user behavior changes, visually presenting the overall change trend of user behavior, enhancing the readability of data analysis, and significantly improving the scientificity and accuracy of user behavior trend analysis, providing more accurate decision support for advertising placement strategy optimization.

[0049] Further, by using a part of the historical click and purchase data to build an initial prediction model, a foundation is laid for subsequent analysis. The model verification unit uses another part of the data set to strictly verify the trained model, effectively testing the model's generalization ability and prediction performance, avoiding overfitting problems. The model optimization unit continuously optimizes the model based on the verification results, constantly adjusting model parameters and learning strategies, so that the prediction model can more accurately capture the complex change rules of user behavior. Through this multi-level, iterative model building method, the accuracy of advertising purchase frequency prediction can be significantly improved, providing more reliable and forward-looking decision support, accurately controlling advertising placement effectiveness, and improving the efficiency of advertising resources and the return on investment.

[0050] Further, by directly comparing the prediction result with the real-time purchase times, the deviation between the actual effect of the advertisement and the expectation can be quickly obtained, providing key data basis for subsequent analysis. Based on the comparison result, the computing unit can intelligently judge the change trend of the conversion rate and accurately calculate the conversion rate change rate, providing data support for real-time adjustment of the advertisement placement strategy, helping to quickly identify problems in advertisement placement and timely adjust the strategy, not only improving the accuracy of advertisement placement, but also significantly improving the utilization efficiency of advertisement resources.

[0051] Further, by quickly obtaining real-time comparison results, the timeliness and accuracy of data processing are ensured, and the change of the conversion rate is flexibly judged based on the comparison results, so that the change of the advertisement effect can be mastered in real time, and the advertisement strategy can be adjusted in time, which not only improves the flexibility and accuracy of advertisement placement, but also optimizes resource allocation, and finally improves the overall benefit and return on investment of the advertisement.

[0052] Further, by comparing the real-time calculated user change rate with the preset threshold, subtle changes in user behavior can be sensitively captured, providing a scientific basis for dynamic adjustment of the advertisement placement strategy. Through the conversion rate change rate and the user change rate, and in combination with the preset adjustment coefficient, the adjustment range of the advertisement placement duration can be comprehensively and accurately calculated, which not only can quickly respond to market changes, but also can effectively balance the efficiency and cost of advertisement placement, significantly improving the targeting and conversion rate of advertisement placement.

[0053] Further, by comprehensively evaluating according to the weights of the conversion rate change rate and the user change rate, it can be ensured that the actual change of the advertisement placement effect can be accurately reflected in different situations, and the advertisement placement strategy can be automatically adjusted, improving the adaptability and reaction speed of the system. Based on the adjustment rate calculated and the preset adjustment coefficient, the adjustment range of the advertisement placement duration is accurately determined, the advertisement placement opportunity is optimized, the waste of resources is effectively avoided, the competitive advantage can be maintained in real-time market changes, and the effect and efficiency of advertisement placement are significantly improved.

[0054] Further, through the fine data collection mechanism, the real-time and accuracy of advertisement data management are significantly improved, laying a solid data foundation for subsequent user behavior prediction and advertisement strategy optimization, capturing market changes in real time, providing more accurate and efficient data analysis and decision support, and helping to improve the targeting of advertisement placement. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 The system framework diagram of the advertisement data management system based on market trend analysis provided by the embodiment of the application is provided.

[0056] Figure 2 The structural schematic diagram of the analysis module of the embodiment of the application is provided.

[0057] Figure 3 A structure diagram of a prediction module of an embodiment of the present application is shown in the figure;

[0058] Figure 4 A structure diagram of an adjustment module of an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0059] In order to make the objects and advantages of the present application clearer, the present application will be further described in conjunction with embodiments. It should be understood that the specific embodiments described herein merely serve the purpose of explaining the present application and are not intended to limit the present application.

[0060] The preferred embodiments of the present application will be described in detail below with reference to the drawings. It should be understood by those skilled in the art that the embodiments are merely used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.

[0061] It should be noted that, in the description of the present application, the terms of direction or position relationship such as "upper", "lower", "left", "right", "inner", "outer" and the like are based on the direction or position relationship shown in the drawings, which is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0062] In addition, it should also be noted that, in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connection" should be understood in a broad sense, for example, can be fixed connection, can also be detachable connection, or integral connection; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be the communication inside two elements. Those skilled in the art can understand the specific meaning of the above terms in the present application according to the specific circumstances.

[0063] Please refer to Figure 1 As Figure 1 shown, it is a system framework diagram of an advertisement data management system based on market trend analysis provided by an embodiment of the present application;

[0064] Specifically, the present application provides an advertisement data management system based on market trend analysis, comprising:

[0065] The data acquisition module is used to acquire the real-time click times and real-time purchase times of the advertisement after reaching the advertisement delivery time length, so as to obtain real-time advertisement data, and acquire historical advertisement data corresponding to the real-time advertisement data, including historical click times and historical purchase times;

[0066] an analysis module connected with the data acquisition module to analyze user change trends and calculate user change rates based on the historical click counts and the real-time click counts;

[0067] a prediction module connected with the data acquisition module to predict purchase counts based on the historical click counts and the historical purchase counts to obtain prediction results;

[0068] a conversion rate calculation module respectively connected with the data acquisition module and the prediction module to compare the prediction results with the real-time purchase counts to obtain comparison results, and determine conversion rate change rates based on the comparison results;

[0069] an adjustment module respectively connected with the data acquisition module, the analysis module, and the conversion rate evaluation module to determine whether to adjust the advertisement launching duration based on the user change rates, and to calculate adjustment rates based on the conversion rate change rates and the user change rates, and to adjust the advertisement launching duration based on the adjustment rates.

[0070] Specifically, the advertisement launching duration is the specific launching duration of the advertisement in a day on the shopping platform, the click count is the number of users who click the advertisement to enter the product interface after seeing the advertisement, the purchase count is the number of users who purchase products after clicking the advertisement to enter the product interface, the conversion rate is the proportion of the number of users who purchase products after clicking the advertisement to enter the product interface to the total number of users who click the advertisement to enter the product interface, and the intention of users for the advertised products will change over time when market trends change during the advertisement launching. The advertisement launching duration is adjusted based on the user change trends analyzed from historical data and the conversion rate changes, so as to reduce cost consumption.

[0071] Specifically, through the deep combination of real-time data and historical data, intelligent management and optimization of advertisement launching effects are realized. Through real-time acquisition of click and purchase data after advertisement launching, advertisement effects are timely reflected, and through accurate identification of user behavior change trends by the analysis module, user change rates are calculated, thereby providing data support for advertisement launching strategies. Through analysis of historical data, the prediction module can efficiently predict future purchase trends. Through comparison of real-time and prediction data, the conversion rate calculation module accurately evaluates the conversion rate changes of advertisements, thereby providing an important basis for optimizing advertisement effects. The adjustment module intelligently judges whether to adjust the advertisement launching duration based on the comprehensive analysis of user change rates and conversion rate change rates, thereby ensuring efficient use of advertisement resources, significantly improving the precision and flexibility of advertisement launching, improving the conversion rate and return on investment of advertisements, and realizing continuous optimization and improvement of advertisement effects.

[0072] Please continue to refer to Figure 2 For example, Figure 2As shown, it is a structural schematic diagram of the analysis module of the embodiment of the present application;

[0073] Specifically, the analysis module comprises:

[0074] A trend analysis unit is configured to divide the historical click counts into periods and determine the user trend according to the comparison result of the historical click totals of adjacent periods.

[0075] A change rate calculation unit is connected with the trend analysis unit and configured to calculate the user change rate according to the historical click counts and the real-time click counts when the user is determined to be in a growth or decrease trend.

[0076] Specifically, the historical click counts are the click counts of the user on the advertisement in the past days, which reflect the number of users with the intention to purchase the advertisement commodity. The historical click counts of the past history are divided into periods, and the change trend of the historical click counts is determined according to the historical click totals of each period to reflect the user trend.

[0077] Specifically, by dividing the historical click counts into periods, the interactive mode of the user in different time periods can be deeply analyzed, and potential trend changes can be identified. Such periodic comparison and analysis not only reveals the dynamic changes of user interest and behavior, but also helps the advertiser to understand the fluctuation of user demand in different market environments and time backgrounds, thereby providing a more accurate basis for the advertisement delivery strategy. The change rate calculation unit accurately calculates the user change rate by comparing the real-time click counts with the historical click counts, quickly identifies the change of user participation, and timely adjusts the advertisement content and delivery strategy to adapt to the rapid changes of user demand, thereby effectively improving the accuracy and effect of advertisement delivery and further promoting the return on investment of advertisement investment.

[0078] Specifically, the trend analysis unit comprises:

[0079] A period division subunit is configured to set a calculation period.

[0080] A period calculation subunit is connected with the period division subunit and configured to calculate the corresponding historical click totals in each calculation period.

[0081] A trend analysis subunit is connected with the period calculation subunit and configured to calculate the difference between the historical click totals of the next period and the previous period of each adjacent period, calculate the total sum of all differences, and determine the user trend based on the total sum of differences.

[0082] Specifically, when the total sum of differences is greater than 0, it is determined to be an increasing trend, or when it is less than 0, it is determined to be a decreasing trend.

[0083] In the embodiment, the historical number of clicks of the advertisement in the past 40 days is obtained, and a calculation period of 10 days is set, the historical total number of clicks in each period is calculated as 140 clicks, 130 clicks, 120 clicks and 110 clicks, the difference between the historical total number of clicks in each adjacent period is calculated as -10, -10, -10, the sum of the differences is -40, which is less than 0, and it is determined as a decreasing trend.

[0084] Specifically, by aggregating the historical total number of clicks in each calculation period, a reliable data basis is provided for subsequent trend analysis, by calculating the difference between the historical total number of clicks in adjacent periods, the fluctuation of user behavior can be deeply identified, and by comprehensive evaluation of the difference, the user change trend can be accurately judged, this method not only improves the accuracy of user change trend determination, but also can timely capture potential market changes, quickly respond to market demand changes, provides a scientific basis for the adjustment of advertisement placement strategy, thereby improving the placement effect and market competitiveness of the advertisement.

[0085] Specifically, the change rate calculation unit comprises:

[0086] The graph drawing subunit is used to draw a scatter plot of the historical number of clicks in the coordinate axis according to the historical number of clicks when the user is in a growth or decreasing trend, and fit a straight line representing the change trend;

[0087] The change rate calculation subunit is connected with the image drawing subunit, and is used to calculate the slope of the straight line and the horizontal coordinate axis divided by the average of the historical total number of clicks to obtain the user change rate.

[0088] In the specific implementation process, the historical total number of clicks is 140 clicks, 130 clicks, 120 clicks and 110 clicks, the slope of the fitted curve is -13, and then the change rate is -10% which is the slope 13 divided by the average of the historical total number of clicks 125.

[0089] Specifically, by converting the historical number of clicks into a scatter plot on the coordinate axis, not only the distribution characteristics of the data are intuitively displayed, but also the complex data change is converted into a simple and clear linear expression by fitting a straight line representing the change trend, and the slope of the trend line and the horizontal coordinate axis is used as a quantitative index of the user change rate, realizing the accurate quantitative analysis of the user behavior change, intuitively presenting the overall change trend of the user behavior, enhancing the readability of the data analysis, and significantly improving the scientificity and accuracy of the user behavior trend analysis, providing more accurate decision support for the optimization of advertisement placement strategy.

[0090] Please continue to refer to Figure 3 As Figure 3 shown, it is a structure schematic diagram of the prediction module of the embodiment of the application.

[0091] In particular, the prediction module comprises:

[0092] a model training unit configured to train the prediction model according to a part of historical click times and historical purchase times to obtain a training model;

[0093] a model verification unit connected with the model training unit and configured to verify the training model according to another part of the historical data to obtain a verification model;

[0094] a model optimization unit connected with the model verification unit and configured to optimize the verification model to predict the prediction result.

[0095] In particular, a suitable machine learning algorithm is selected to construct the prediction model, such as support vector machine, random forest, neural network, etc., a part of historical click times and historical purchase times is used for model training, and another part is used for model verification.

[0096] In particular, an initial prediction model is constructed by using a part of historical click and purchase data, which lays a foundation for subsequent analysis. The model verification unit uses another part of the data set to strictly verify the training model, effectively tests the generalization ability and prediction performance of the model, avoids overfitting problem, the model optimization unit continuously optimizes the model based on the verification result, and continuously adjusts the model parameters and learning strategy, so that the prediction model can more accurately capture the complex change rule of user behavior. Through this multi-level and iterative model construction method, the prediction accuracy of the advertisement purchase times can be significantly improved, more reliable and forward-looking decision support can be provided, the advertisement delivery effect can be accurately controlled, and the use efficiency and investment return rate of the advertisement resources can be improved.

[0097] In particular, the conversion rate calculation module comprises:

[0098] a comparison unit configured to compare the prediction result with the real-time purchase times to obtain a comparison result;

[0099] a calculation unit connected with the comparison unit and configured to determine a conversion rate change according to the comparison result, and calculate a conversion rate change rate based on the determination result.

[0100] Specifically, by directly comparing the predicted results with the real-time purchase count, the deviation between the actual advertising effect and the expectation can be quickly obtained, providing a key data foundation for subsequent analysis. Based on the comparison results, the calculation unit can intelligently judge the trend of conversion rate changes and accurately calculate the conversion rate change rate, providing data support for real-time adjustment of advertising strategies. This helps to quickly identify problems in advertising and adjust strategies in a timely manner, which not only improves the accuracy of advertising but also significantly improves the utilization efficiency of advertising resources.

[0101] Specifically, the computing unit includes:

[0102] A receiving subunit is used to receive the comparison result;

[0103] A determination subunit, connected to the receiving subunit, is used to determine the conversion rate change based on the comparison result, wherein...

[0104] If the predicted result is less than the number of real-time purchases, the conversion rate is determined to have increased.

[0105] If the predicted result is equal to the number of real-time purchases, then the conversion rate is determined to remain unchanged;

[0106] If the predicted result is greater than the number of real-time purchases, the conversion rate is determined to have decreased.

[0107] A calculation subunit, connected to the determination subunit, is used to calculate the rate of change of conversion rate when the conversion rate is determined to increase or decrease.

[0108] In the specific implementation process, the predicted number of purchases for a total of 100 clicks is 40, while the actual number of real-time purchases is 30. Since the predicted number is greater than the actual number of real-time purchases, the conversion rate is determined to be reduced. The conversion rate change rate is calculated as the ratio of real-time purchases to total clicks minus the ratio of the predicted number to total clicks, which is a decrease of 10%.

[0109] Specifically, by quickly obtaining real-time comparison results, ensuring the timeliness and accuracy of data processing, and flexibly judging changes in conversion rates based on the comparison results, it is possible to grasp changes in advertising effectiveness in real time and adjust advertising strategies in a timely manner. This not only improves the flexibility and accuracy of advertising placement but also optimizes resource allocation, ultimately improving the overall effectiveness and return on investment of advertising.

[0110] Please continue reading. Figure 4 ,like Figure 4 As shown, it is a structural schematic diagram of the adjustment module in an embodiment of the present invention;

[0111] Specifically, the adjustment module includes:

[0112] an adjustment determination unit configured to compare the user change rate with a preset user change rate threshold, and determine whether to adjust the advertisement delivery time length based on a comparison result;

[0113] an adjustment unit connected with the adjustment determination unit, configured to calculate an adjustment rate according to the conversion rate change rate and the user change rate when it is determined to adjust the advertisement delivery time length, and adjust the advertisement delivery time length according to a preset adjustment coefficient.

[0114] Specifically, if the user change rate is greater than the preset user change rate threshold, it is determined to adjust the advertisement delivery time length, and if the user change rate is less than or equal to the preset user change rate threshold, it is determined not to adjust the advertisement delivery time length. In a specific implementation process, the user change rate threshold is 5%, the user change rate of the advertisement is reduced by 10%, and the user change rate is greater than the preset user change rate threshold, so it is determined to adjust the advertisement delivery time length.

[0115] Specifically, by comparing the real-time calculated user change rate with the preset threshold, subtle changes in user behavior can be sensitively captured, providing a scientific basis for dynamic adjustment of advertisement delivery strategy. By conversion rate change rate and user change rate, and combining a preset adjustment coefficient, the adjustment range of the advertisement delivery time length can be comprehensively and accurately calculated, which not only can quickly respond to market changes, but also can effectively balance the efficiency and cost of advertisement delivery, significantly improving the pertinence and conversion rate of advertisement delivery.

[0116] Specifically, the adjustment unit comprises:

[0117] an adjustment rate calculation sub-unit configured to assign weights to the conversion rate change rate and the user change rate, and calculate an adjustment rate;

[0118] an adjustment value calculation sub-unit connected with the adjustment rate calculation sub-unit, configured to determine an adjustment value according to the adjustment rate and the adjustment coefficient, and adjust the advertisement delivery time length.

[0119] In a specific implementation process, the adjustment coefficient is the degree of adjustment of the advertisement delivery time length, which is 100 in this embodiment. The user change rate weight is 40%, the conversion rate weight is 60%, the advertisement delivery time length is 200 minutes, the user change rate is -10%, and the conversion rate is -10%. Then the product of the user change rate and the user change rate weight plus the product of the conversion rate and the conversion rate weight is calculated to obtain an adjustment rate of -10%. The product of the sum and the adjustment coefficient is calculated to obtain an adjusted advertisement time length of 190 minutes.

[0120] Specifically, by comprehensively evaluating according to the weight of the conversion rate change rate and the user change rate, it is ensured that the actual change of the advertising effect can be accurately reflected in different situations, the advertising strategy is automatically adjusted, the adaptability and reaction speed of the system are improved, the adjustment range of the advertising duration is accurately determined based on the calculated adjustment rate and the preset adjustment coefficient, the advertising opportunity is optimized, the waste of resources is effectively avoided, the competitive advantage can be maintained in real-time market changes, and the effect and efficiency of the advertising are significantly improved.

[0121] Specifically, the data acquisition module comprises:

[0122] The first acquisition unit is configured to acquire the real-time click number and the real-time purchase number of the advertisement after the advertising duration is reached.

[0123] The second acquisition unit is configured to acquire the historical click number and the historical purchase number.

[0124] Specifically, the data acquisition module acquires the historical click number of advertisement clicks and the historical purchase number of purchases of goods in the commodity interface in each day of the past time of the advertisement on the advertising platform, and acquires the real-time click number and the real-time purchase number of the advertisement reaching the advertising duration on the same day.

[0125] Specifically, by using the refined data collection mechanism, the real-time and accuracy of the advertisement data management are significantly improved, a solid data foundation is laid for subsequent user behavior prediction and advertising strategy optimization, market changes are captured in real time, more accurate and efficient data analysis and decision support are provided, and the pertinence of the advertising is improved.

[0126] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements will fall within the protection scope of the present application.

[0127] The above description is only the preferred embodiments of the present application and is not used to limit the present application; for those skilled in the art, the present application can have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An advertisement data management system based on market trend analysis, characterized by, The method comprises the following steps: a data acquisition module is configured to acquire real-time click times and real-time purchase times of an advertisement to obtain real-time advertisement data when the advertisement duration reaches a preset value, and acquire historical advertisement data corresponding to the real-time advertisement data, including historical click times and historical purchase times; an analysis module connected with the data acquisition module is configured to analyze user change trends and calculate a user change rate according to the historical click times and the real-time click times; a prediction module connected with the data acquisition module is configured to predict purchase times according to the historical click times and the historical purchase times to obtain a prediction result; a conversion rate calculation module connected with the data acquisition module and the prediction module is configured to compare the prediction result with the real-time purchase times to obtain a comparison result, and determine a conversion rate change rate based on the comparison result; an adjustment module connected with the data acquisition module, the analysis module and the conversion rate calculation module is configured to determine whether to adjust the advertisement duration according to the user change rate, calculate an adjustment rate according to the conversion rate change rate and the user change rate, and adjust the advertisement duration according to the adjustment rate; the analysis module comprises: a trend analysis unit configured to divide the historical click times into periods, and determine user change trends according to comparison results of historical click totals of adjacent periods; a change rate calculation unit connected with the trend analysis unit is configured to calculate the user change rate according to the historical click times and the real-time click times when it is determined that the user is in a growth or decrease trend; the trend analysis unit comprises: a period division sub-unit configured to set a calculation period; a period calculation sub-unit connected with the period division sub-unit is configured to calculate corresponding historical click totals in each calculation period; a trend analysis sub-unit connected with the period calculation sub-unit is configured to calculate a difference value of the historical click totals of a later period minus an earlier period of each adjacent period, calculate a difference total of all difference values, and determine user change trends based on the difference total; when the difference total is greater than 0, it is determined as an increase trend; when the difference total is less than 0, it is determined as a decrease trend; the change rate calculation unit comprises: a graph drawing sub-unit configured to draw a scatter plot of historical click times in a coordinate axis according to the historical click times when the user is in a growth or decrease trend, and fit a straight line representing the change trend; a change rate calculation sub-unit connected with the graph drawing sub-unit is configured to calculate a slope of the straight line and the horizontal coordinate axis divided by a mean value of the historical click totals to obtain the user change rate; the adjustment module comprises: an adjustment determination unit configured to compare the user change rate with a preset user change rate threshold, and determine whether to adjust the advertisement duration based on the comparison result; an adjustment unit connected with the adjustment determination unit is configured to calculate an adjustment rate according to the conversion rate change rate and the user change rate when it is determined to adjust the advertisement duration, and adjust the advertisement duration according to a preset adjustment coefficient. The adjustment unit comprises: an adjustment rate calculation sub-unit configured to calculate an adjustment rate by weighting the conversion rate change rate and the user change rate; an adjustment value calculation sub-unit connected with the adjustment rate calculation sub-unit and configured to determine an adjustment value according to the adjustment rate and the adjustment coefficient, so as to adjust the advertisement delivery time length; the adjustment rate is obtained by adding the product of the user change rate and the user change rate weight to the product of the conversion rate and the conversion rate weight.

2. The advertisement data management system based on market trend analysis according to claim 1, characterized in that, The prediction module comprises: a model training unit configured to train a prediction model according to part of historical click times and historical purchase times to obtain a training model; a model verification unit connected with the model training unit and configured to verify the training model according to another part of historical data to obtain a verification model; a model optimization unit connected with the model verification unit and configured to optimize the verification model to predict the prediction result.

3. The advertisement data management system based on market trend analysis according to claim 1, characterized in that, The conversion rate calculation module comprises: a comparison unit configured to compare the prediction result with the real-time purchase times to obtain a comparison result; a calculation unit connected with the comparison unit and configured to determine a conversion rate change according to the comparison result, and calculate a conversion rate change rate based on the determination result.

4. The advertisement data management system based on market trend analysis according to claim 3, characterized in that, The calculation unit comprises: a receiving sub-unit configured to receive the comparison result; a determination sub-unit connected with the receiving sub-unit and configured to determine a conversion rate change according to the comparison result, wherein, if the prediction result is less than the real-time purchase times, it is determined that the conversion rate increases; if the prediction result is equal to the real-time purchase times, it is determined that the conversion rate is unchanged; if the prediction result is greater than the real-time purchase times, it is determined that the conversion rate decreases; a calculation sub-unit connected with the determination sub-unit and configured to calculate the conversion rate change rate when it is determined that the conversion rate increases or the conversion rate decreases.

5. The advertisement data management system based on market trend analysis according to claim 1, wherein, The data acquisition module comprises: a first acquisition unit configured to acquire the real-time click times and the real-time purchase times of the advertisement after the advertisement delivery time length is reached; a second acquisition unit configured to acquire the historical click times and the historical purchase times.

Images