Digital marketing method and system based on payment two-dimensional code and mobile terminal

Abstract

The invention relates to the technical field of electronic commerce, in particular to a digital marketing method and system based on a payment two-dimensional code and a mobile terminal.The method comprises the following steps that based on user behavior data, the two-dimensional code scanning frequency and the user retention time are calculated, and a primary user behavior analysis result is obtained; and two-dimensional code content parameters including discount strength, the type of promotion information and timeliness are adjusted, and optimized two-dimensional code parameter configuration is generated. According to the invention, through refining user behavior data such as two-dimensional code scanning frequency and user retention time, a marketing strategy is adjusted in real time, market demands are accurately reflected, rapid response of the strategy to market changes is enhanced, discount strength and sales promotion timeliness are optimized, and user participation degree is improved. The optimal position and time of the two-dimensional code are determined, the advertisement exposure rate and the marketing effect are improved, the cost and the effect are effectively balanced through real-time data-driven Bayesian optimization model adjustment and the use of a multi-objective optimization algorithm, activity scheduling is optimized, and the marketing return on investment is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to a digital marketing method, system and mobile terminal based on payment QR code. Background Art

[0002] The field of e-commerce technology covers various technologies and methods for buying and selling goods or services using the Internet and digital platforms, ranging from online payment processing, automatic inventory management to customer relationship management (CRM) systems. With the popularity of mobile devices and social media, e-commerce has also expanded to mobile commerce and social commerce. E-commerce technology also includes the use of big data and artificial intelligence to analyze consumer behavior, optimize marketing strategies and enhance user experience. E-commerce is not limited to the B2C model, but also includes a variety of transaction models such as B2B and C2C, covering a wide range of industries and markets, enabling companies to cross geographical boundaries and achieve global business expansion.

[0003] Among them, digital marketing methods are a series of strategies and techniques to promote products or services through digital channels, including search engine optimization (SEO), content marketing, social media marketing, email marketing and online advertising. The main purpose of digital marketing is to attract potential customers, build brand awareness and promote sales. Through precise positioning and personalized marketing messages, digital marketing enables companies to interact with target audiences more effectively, improve conversion rates and customer loyalty. The data-driven nature of digital marketing allows companies to track and evaluate the effectiveness of marketing activities in real time, thereby achieving higher marketing efficiency and return on investment.

[0004] Existing digital marketing methods focus on using fixed marketing strategies and lack the flexibility to quickly adapt to dynamic changes in the market. For example, traditional marketing strategies rely too much on historical data and delayed market feedback, resulting in marketing decisions that cannot be updated in real time, thus missing market opportunities or continuing to implement ineffective marketing activities. Data analysis in existing technologies is not sufficient to process and utilize large amounts of data from real-time user interactions, such as QR code scanning data, which limits the optimization of marketing strategies and the precise delivery of personalized marketing information. This static strategy configuration and slow response speed lead to a waste of marketing resources and a reduction in user experience, ultimately affecting the market competitiveness and profitability of enterprises. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a digital marketing method system and a mobile terminal based on payment QR code.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a digital marketing method based on payment QR code, comprising the following steps:

[0007] S1: Based on user behavior data, calculate the QR code scanning frequency and user retention time, obtain primary user behavior analysis results, and adjust the QR code content parameters including discount strength, type and timeliness of promotional information to generate optimized QR code parameter configuration;

[0008] S2: Based on the optimized QR code parameter configuration, perform parameter combination operation, determine the optimal QR code placement position and time, generate a position time optimization strategy, adjust the position time optimization strategy in real time, and generate a dynamically adjusted marketing strategy based on market dynamics and historical transaction data;

[0009] S3: Based on the dynamically adjusted marketing strategy, capture QR code performance data, including scanning frequency and user feedback, generate real-time performance feedback data, use the real-time performance feedback data to update the Bayesian optimization model, adjust the strategy and content of the promotional activities, and generate a Bayesian optimized promotional strategy;

[0010] S4: Based on the promotional strategy after Bayesian optimization, a multi-objective optimization algorithm is integrated to balance cost and effect, optimize the selection of advertising content and the scheduling of promotion activities, generate a balanced optimization result, implement marketing activities according to the balanced optimization result, monitor the performance of the marketing activities, and generate a marketing activity performance monitoring result.

[0011] As a further solution of the present invention, the steps of obtaining the optimized QR code parameter configuration are specifically as follows:

[0012] S111: Based on the user behavior data, count the number of times each user scans the QR code and the retention time, calculate the total scanning frequency and average retention time, using the formula:

[0013]

[0014] and

[0015]

[0016] Get the user behavior data set, where F a represents the total scanning frequency, f a,i represents the number of scans by the i-th user, T a represents the average retention time, t a,i represents the retention time of the i-th user, and n represents the total number of users;

[0017] S112: Calculate a weighted user behavior score based on the user behavior data set, using the formula:

[0018]

[0019] Get the primary user behavior analysis results, where Sa represents the user behavior analysis score, α a is the weight of the scanning frequency, β a is the weight of retention time, γ a is the nonlinear coefficient;

[0020] S113: According to the primary user behavior analysis result, the formula:

[0021]

[0022] Adjust the QR code content parameters to obtain the optimized QR code parameter configuration, where P a represents the optimized QR code parameter configuration, δ a is the exponential adjustment coefficient, κ a is the slope of the logistic function, λ a is the offset of the logistic function.

[0023] As a further solution of the present invention, the steps of obtaining the location time optimization strategy are specifically as follows:

[0024] S211: Using the optimized QR code parameter configuration, calculate the average flow of people in each time period using the formula:

[0025]

[0026] Introduce the attenuation factor, calculate and obtain the potential scanning frequency data, where P a Represents the optimized QR code parameter configuration, x b represents the flow of people, y b Indicates the time period, e b is the time decay factor, Z b is the potential scanning frequency data;

[0027] S212: Based on the potential scanning frequency data and in combination with the location influence coefficient, a nonlinear attenuation formula is used:

[0028]

[0029] Calculate the QR code placement effect at each location and obtain the QR code placement effect evaluation result, where W b Indicates the evaluation result of QR code placement effect, Z b is the potential scanning frequency data, g b is the location influence coefficient;

[0030] S213: Select the maximum value from the two-dimensional code placement effect evaluation results and apply the formula:

[0031] V b =max(W b)

[0032] Determine the optimal QR code placement location and time, and generate a location and time optimization strategy, where V b represents the location time optimization strategy, W b Indicates the evaluation result of the QR code placement effect.

[0033] As a further solution of the present invention, the step of obtaining the dynamically adjusted marketing strategy is specifically:

[0034] S221: Based on the position time optimization strategy, the current market dynamic data and historical transaction data are integrated, and the compound growth rate formula is used:

[0035]

[0036] Adjust the historical weights and calculate the market performance evaluation results, where P c is the benchmark adjustment factor, β c is the historical data impact factor, α c and γ c is the tuning parameter, D c represents the market performance evaluation result, M c Indicates market dynamics data, H c Represents historical transaction data;

[0037] S222: Using the market performance evaluation results, adopting the index adjustment model, through the formula:

[0038]

[0039] Evaluate the market's reaction sensitivity and generate a market response index, where κ c , η c and c is the nonlinear adjustment parameter, R c represents the market response index, D c Evaluate results for market performance;

[0040] S223: Based on the market response indicator, through the strategy decision model, the formula is adopted:

[0041]

[0042] Adjust the marketing strategy and generate a dynamically adjusted marketing strategy, where τ c is the strategy adjustment coefficient, μ c is the decision threshold, S c Represents a dynamically adjusted marketing strategy, R c It is a market response indicator.

[0043] As a further solution of the present invention, the steps of obtaining the promotion strategy after Bayesian optimization are specifically as follows:

[0044] S311: In combination with the dynamically adjusted marketing strategy, the scanning frequency of the QR code and user feedback are collected, and a data aggregation formula is used:

[0045]

[0046] Get real-time performance feedback data, where f d represents the scanning frequency, u d represents user feedback, ρ d is the weight of user feedback, is the data smoothing parameter, F d It is real-time performance feedback data;

[0047] S312: Using the real-time performance feedback data to update the Bayesian optimization model, by formula:

[0048]

[0049] Adjust the model to reflect current market dynamics and user behavior and generate an updated Bayesian model, where B d is the updated Bayesian model, F d is the real-time performance feedback data, τ d is the model sensitivity threshold;

[0050] S313: Using the updated Bayesian model, adjust the strategy and content of the promotional activity, using the strategy optimization formula:

[0051]

[0052] Generate a Bayesian optimized promotion strategy, where P d represents the promotion strategy after Bayesian optimization, B d is the updated Bayesian model, λ d is the influence coefficient, σ d and ψ d To adjust the parameters.

[0053] As a further solution of the present invention, the steps of obtaining the marketing activity performance monitoring results are specifically as follows:

[0054] S411: Based on the Bayesian optimized promotion strategy, a multi-objective optimization algorithm is integrated to balance cost and effect, and a cost-benefit analysis formula is adopted:

[0055]

[0056] The equilibrium optimization result is obtained, where ωg represents the benefit weight of the advertising content, v g represents the expected visual appeal of the advertisement, D g is the cost of advertising content, C g It is the result of balanced optimization;

[0057] S412: Implement marketing activities according to the balance optimization results, monitor marketing performance, and use an effect tracking model through the formula:

[0058] E g =γ g ·(η g ·C g )

[0059] Generate real-time marketing effect monitoring results, where γ g is the market reaction coefficient, η g is the adjustment factor, E g Represents real-time marketing effect monitoring results;

[0060] S413: Using the real-time marketing effect monitoring results, perform data analysis and evaluate the overall success rate of the activity, and apply the performance evaluation formula:

[0061]

[0062] Generate marketing campaign performance monitoring results, where P g represents the marketing activity performance monitoring results, κ g is the sensitivity parameter, θ g is the success threshold, E g Represents real-time marketing effect monitoring results.

[0063] A digital marketing system based on a payment QR code, the digital marketing system based on a payment QR code is used to execute the above-mentioned digital marketing method based on a payment QR code, the system comprising:

[0064] The user behavior analysis module calculates the QR code scanning frequency and user retention time based on user behavior data, sorts data and identifies usage frequency, and generates user behavior analysis results;

[0065] The QR code parameter optimization module evaluates the attractiveness of the QR code according to the user behavior analysis results, adjusts the type and timeliness of discount and promotion information, and obtains optimized parameter configuration;

[0066] The location time strategy module uses the above optimization parameter configuration, geographic location and time distribution data to analyze the optimal placement location and time point, and generates a location time optimization strategy;

[0067] The real-time performance feedback module monitors QR code scanning and user feedback based on the location time optimization strategy, updates the marketing model, makes key adjustments to the strategy, and obtains the Bayesian optimization strategy;

[0068] The multi-objective marketing optimization module applies the Bayesian optimization strategy, compares and analyzes costs and effects, adjusts advertising content and activity parameters, tracks real-time activity performance, and obtains marketing activity performance monitoring results.

[0069] A digital marketing mobile terminal based on payment QR code includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the digital marketing method based on payment QR code when executing the computer program.

[0070] Compared with the prior art, the advantages and positive effects of the present invention are:

[0071] In the present invention, by refining the analysis of user behavior data, such as detailed measurements of QR code scanning frequency and user retention time, marketing strategies can be adjusted in real time to more accurately reflect the actual needs of the market and consumers. The ability to adjust in real time allows marketing strategies to quickly respond to market changes and optimize QR code content parameters, such as discount strength and the timeliness of promotional information, thereby improving user participation and satisfaction. By performing parameter combination operations to determine the optimal placement position and time of the QR code, not only the exposure rate of the advertising content is increased, but also the overall effect of the marketing campaign is improved. Using real-time performance feedback data to update the Bayesian optimization model, adjust strategies and content, allow marketing decisions to be more data-driven, reduce decision errors based on assumptions, integrate multi-objective optimization algorithms to balance costs and effects, optimize advertising content selection and promotion activity scheduling, and thus significantly improve marketing ROI. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0073] Figure 2 A flowchart of the optimized QR code parameter configuration in the present invention;

[0074] Figure 3 It is a flow chart of the location time optimization strategy in the present invention;

[0075] Figure 4 A flowchart of a marketing strategy dynamically adjusted in the present invention;

[0076] Figure 5 A flow chart of the promotion strategy after Bayesian optimization in the present invention;

[0077] Figure 6 The flowchart of the marketing activity performance monitoring results in the present invention. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0079] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0080] Embodiment 1

[0081] See also Figure 1 The present invention provides a technical solution: a digital marketing method based on payment QR code, comprising the following steps:

[0082] S1: Based on user behavior data, calculate the QR code scanning frequency and user retention time, obtain primary user behavior analysis results, and adjust the QR code content parameters including discount strength, type and timeliness of promotional information to generate optimized QR code parameter configuration;

[0083] S2: Based on the optimized QR code parameter configuration, perform parameter combination operations, determine the optimal QR code placement location and time, generate a location and time optimization strategy, make real-time adjustments to the location and time optimization strategy, and generate a dynamically adjusted marketing strategy based on market dynamics and historical transaction data;

[0084] S3: Based on the dynamically adjusted marketing strategy, capture QR code performance data, including scanning frequency and user feedback, generate real-time performance feedback data, use the real-time performance feedback data to update the Bayesian optimization model, adjust the strategy and content of the promotion activities, and generate the Bayesian optimized promotion strategy;

[0085] S4: Based on the promotion strategy after Bayesian optimization, integrate the multi-objective optimization algorithm, balance the cost and effect, optimize the advertising content selection and promotion activity scheduling, generate balanced optimization results, implement marketing activities according to the balanced optimization results, monitor the performance of marketing activities, and generate marketing activity performance monitoring results.

[0086] The optimized QR code parameter configuration includes discount strategy, information update frequency, and response time setting. The location time optimization strategy includes promotion area positioning, event time arrangement, and location selection logic. The dynamically adjusted marketing strategy includes market response speed, data-driven adjustment, and strategy iteration cycle. Real-time performance feedback data includes user interaction indicators, performance evaluation index, and feedback immediacy. The promotion strategy after Bayesian optimization includes parameter optimization depth, content accuracy, and prediction accuracy. The balanced optimization results include resource allocation efficiency, content achievement rate, and scheduling execution. The marketing activity performance monitoring results include participation rate statistics, effect conversion analysis, and customer satisfaction evaluation.

[0087] See also Figure 2 , the specific steps for obtaining the optimized QR code parameter configuration are:

[0088] S111: Based on the user behavior data, count the number of times each user scans the QR code and the retention time, calculate the total scanning frequency and average retention time, using the formula:

[0089]

[0090] and

[0091]

[0092] Get the user behavior data set, where F a represents the total scanning frequency, f a,i represents the number of scans by the i-th user, T a represents the average retention time, t a,i represents the retention time of the i-th user, and n represents the total number of users;

[0093] S112: Calculate the weighted user behavior score based on the user behavior data set, using the formula:

[0094]

[0095] Get the primary user behavior analysis results, where S a represents the user behavior analysis score, α a is the weight of the scanning frequency, β a is the weight of retention time, γ a is the nonlinear coefficient;

[0096] S113: Based on the primary user behavior analysis results, the formula:

[0097]

[0098] Adjust the QR code content parameters to obtain the optimized QR code parameter configuration, where P arepresents the optimized QR code parameter configuration, δ a is the exponential adjustment coefficient, κ a is the slope of the logistic function, λ a is the offset of the logistic function.

[0099] Calculation formula for user behavior dataset:

[0100]

[0101] and

[0102]

[0103] F a : The total scanning frequency of the user;

[0104] f a,i : The number of scans by the i-th user;

[0105] T a : Average retention time of all users;

[0106] t a,i : The retention time of the i-th user;

[0107] n: total number of users;

[0108] Assume there are 3 users, the scan times are 10, 15, and 5, and the retention times are 30 seconds, 45 seconds, and 15 seconds, respectively;

[0109] Calculate the total scanning frequency: F a =10+15+5=30;

[0110] Calculate the average retention time:

[0111] A total scanning frequency of 30 means that all users have scanned the QR code 30 times cumulatively;

[0112] An average retention time of 30 seconds means that users stay on the page for 30 seconds on average.

[0113] User behavior analysis score formula:

[0114]

[0115] S a : User behavior analysis score;

[0116] α a , β a : Weights adjusted based on historical data;

[0117] γ a : Adjust the nonlinear coefficient to increase the flexibility of the model;

[0118] Setting α a =0.5,β a =1.5,γ a =2, using the result from the previous step, F a =30, T a =30;

[0119] Calculate behavioral scores:

[0120]

[0121] A behavior score of 1 means that according to the set weight, the user behavior scores 1 in the evaluation model, and this score will be used for further parameter optimization.

[0122] Optimized QR code parameter configuration formula:

[0123]

[0124] P a : Optimized QR code parameter configuration;

[0125] δ a : Index adjustment coefficient;

[0126] κ a , a : The slope and offset of the logistic function;

[0127] Assume that δ a =1,κ a =1,λ a = 0.5, using the score S from the previous step a =1;

[0128] Calculate QR code parameter configuration P a :

[0129]

[0130] The value of the QR code parameter configuration is about 0.62, which means that the optimized QR code configuration is moderately adjusted under the given model and parameters.

[0131] See also Figure 3 , the steps for obtaining the location time optimization strategy are as follows:

[0132] S211: Use the optimized QR code parameter configuration to calculate the average flow of people in each time period using the formula:

[0133]

[0134] Introduce the attenuation factor, calculate and obtain the potential scanning frequency data, where P a Represents the optimized QR code parameter configuration, x b represents the flow of people, y b Indicates the time period, e b is the time decay factor, Z b is the potential scanning frequency data;

[0135] S212: Based on the potential scanning frequency data, combined with the location influence coefficient, use the nonlinear attenuation formula:

[0136]

[0137] Calculate the QR code placement effect at each location and obtain the QR code placement effect evaluation result, where W b Indicates the evaluation result of QR code placement effect, Z b is the potential scanning frequency data, g b is the location influence coefficient;

[0138] S213: Select the maximum value from the QR code placement effect evaluation results and apply the formula:

[0139] V b =max(W b )

[0140] Determine the optimal QR code placement location and time, and generate a location and time optimization strategy, where V b represents the location time optimization strategy, W b Indicates the evaluation result of the QR code placement effect.

[0141] Potential scan frequency data formula:

[0142]

[0143] P a : Optimized QR code parameter configuration, obtained from the previous analysis steps;

[0144] x b : Traffic flow, assumed to be obtained through traffic counting tools or historical data;

[0145] y b : time period, such as hours or days;

[0146] e b : Time attenuation factor, which indicates the nonlinear effect of time on the scanning effect;

[0147] Assumption: P a =0.8 (optimized QR code parameter configuration value), x b =100(people flow), yb =3 (time period, such as 3 pm), e b =0.05 (time decay factor);

[0148] Calculate potential scan frequency:

[0149]

[0150] The potential scanning frequency of 8.35 indicates that under certain time periods and traffic conditions, the scanning potential score of the QR code is 8.35, reflecting the attractiveness of the QR code.

[0151] QR code placement effect evaluation result formula:

[0152]

[0153] Z b : Potential scanning frequency, obtained from the previous step;

[0154] g b : Location influence coefficient, assumed to be obtained based on specific attributes or historical data of the location;

[0155] y b : Time period, continue to use the time period in the previous step;

[0156] Assumption: Z b =8.35 (result of step 1), g b =0.2 (location influence coefficient), y b =3(time period);

[0157] Calculate the QR code placement effect:

[0158]

[0159] The QR code placement effect score is 1.25, which reflects the optimization effect of QR code placement at a given time and place.

[0160] Position time optimization strategy formula:

[0161] V b =max(W b )

[0162] W b : QR code placement effect evaluation, obtained from the previous step;

[0163] Assume that in different combinations of place and time, W b The values ​​of are 1.25, 1.1, and 0.9 respectively;

[0164] Choose the optimal value:

[0165] V b =max(1.25, 1.1, 0.9) = 1.25

[0166] The optimal value of the location-time optimization strategy is 1.25, which means that after considering all time and location combinations, the combination that provides the highest score of 1.25 is selected as the best QR code placement strategy.

[0167] See also Figure 4 , the specific steps for obtaining the dynamically adjusted marketing strategy are:

[0168] S221: Based on the position time optimization strategy, the current market dynamics data and historical transaction data are integrated, and the compound growth rate formula is used:

[0169]

[0170] Adjust the historical weights and calculate the market performance evaluation results, where P c is the benchmark adjustment factor, β c is the historical data impact factor, α c and γ c is the tuning parameter, D c represents the market performance evaluation result, M c Indicates market dynamics data, H c Represents historical transaction data;

[0171] S222: Using the market performance evaluation results, adopt the index adjustment model, through the formula:

[0172]

[0173] Evaluate the market's reaction sensitivity and generate a market response index, where κ c , η c and c is the nonlinear adjustment parameter, R c represents the market response index, D c Evaluate results for market performance;

[0174] S223: Based on the market response index, through the strategic decision model, the formula is adopted:

[0175]

[0176] Adjust the marketing strategy and generate a dynamically adjusted marketing strategy, where τ c is the strategy adjustment coefficient, μ c is the decision threshold, S c Represents a dynamically adjusted marketing strategy, R c It is a market response indicator.

[0177] The formula for market performance evaluation results is:

[0178]

[0179] M c : Current market dynamics data, assumed to be collected through real-time market monitoring tools;

[0180] H c : Historical transaction data, obtained by querying historical records in the database;

[0181] P c : Benchmark adjustment factor, which may be set based on previous market analysis;

[0182] β c : Historical data impact factor, set according to the importance of historical data to current decision-making;

[0183] α c and γ c : Adjustment parameters to balance the impact of historical and current data, determined through historical data analysis;

[0184] Assumption: M c =200 (current market dynamic data points), H c =150 (historical transaction data points), P c =1.5 (benchmark adjustment coefficient), β c =0.4 (historical data impact factor), α c =2,γ c =0.05;

[0185] Calculate D c

[0186]

[0187] The comprehensive market data of 132.11 indicates that under the weighted influence of current market dynamics and historical data, the obtained market index is 132.11, which reflects the overall activity of the market.

[0188] The formula for the Market Response Index is:

[0189]

[0190] D c : The market performance evaluation result calculated from the previous step;

[0191] κ c , η c , c : Non-linear adjustment parameters, adjusted according to market sensitivity and response requirements;

[0192] Assumed value: D c =132.11,κ c =0.1,η c =5,ξ c =2;

[0193] Calculate R c :

[0194]

[0195] The market response index is 0.018, which is a low value, indicating that the market is slow to respond to the current marketing strategy and needs further adjustment.

[0196] The formula for a dynamically adjusted marketing strategy:

[0197]

[0198] R c : The market response indicator calculated from the previous step

[0199] τ c , μ c :Strategy adjustment coefficient and decision threshold are set according to market reaction speed and strategy sensitivity.

[0200] Assumed value: R c =0.018, τ c =10,μ c =0.02;

[0201] Calculate S c :

[0202]

[0203] The dynamically adjusted marketing strategy scored 0.495, which indicates that the strategy is in a neutral state and does not require extreme adjustments, but it should be kept under observation and prepared to make small adjustments to respond to market changes.

[0204] See also Figure 5 , the specific steps for obtaining the promotion strategy after Bayesian optimization are:

[0205] S311: Combined with the dynamically adjusted marketing strategy, the scanning frequency of the QR code and user feedback are collected, and the data aggregation formula is adopted:

[0206]

[0207] Get real-time performance feedback data, where f d represents the scanning frequency, u d represents user feedback, ρ dis the weight of user feedback, is the data smoothing parameter, F d It is real-time performance feedback data;

[0208] S312: Use the real-time performance feedback data to update the Bayesian optimization model, using the formula:

[0209]

[0210] Adjust the model to reflect current market dynamics and user behavior and generate an updated Bayesian model, where B d is the updated Bayesian model, F d is the real-time performance feedback data, τ d is the model sensitivity threshold;

[0211] S313: Use the updated Bayesian model to adjust the strategy and content of the promotional activities, using the strategy optimization formula:

[0212]

[0213] Generate a Bayesian optimized promotion strategy, where P d represents the promotion strategy after Bayesian optimization, B d is the updated Bayesian model, λ d is the influence coefficient, σ d and ψ d To adjust the parameters.

[0214] Real-time performance feedback data formula:

[0215]

[0216] f d : Scanning frequency, the number of scans of each user is collected through the real-time monitoring system;

[0217] u d : User feedback is the user satisfaction rating, collected through surveys or online feedback systems;

[0218] ρ d : The weight of user feedback, which is an adjustment parameter that determines its impact on performance feedback data based on historical data analysis;

[0219] Data smoothing parameters are used to prevent extreme values ​​from affecting the overall data analysis;

[0220] Assumption: Scanning frequency f d The total is 500 times, user feedback u d The total is 250 points, and the weight is ρ d Set to 0.5, smoothing parameter Set to 10;

[0221] Calculate F d :

[0222]

[0223] The real-time performance feedback data is 4.04, which indicates the smoothed performance score under the current user feedback and scanning frequency.

[0224] Updated Bayesian model formula:

[0225]

[0226] F d : Real-time performance feedback data calculated in the previous step;

[0227] τ d : Model sensitivity threshold, which is set based on historical data and market reactions to adjust the model’s response threshold;

[0228] Assume the parameter value is: F d =4.04, τ d =4;

[0229] Calculate B d :

[0230]

[0231] The updated Bayesian model value is 0.51, indicating that under the given threshold and real-time feedback, the model moderately adjusts the response strategy.

[0232] Promotion strategy formula after Bayesian optimization:

[0233]

[0234] B d : The Bayesian model value calculated in the previous step;

[0235] λ d , σ d , d : Adjustment parameters, namely the influence coefficient and adjustment factor, are used to fine-tune the flexibility and sensitivity of the promotion strategy;

[0236] Assumption: B d =0.51,λ d =2,σ d =1,ψ d =0.5;

[0237] Calculate P d :

[0238]

[0239] The promotion strategy value after Bayesian optimization is 0.207, which is low, indicating that the current strategy needs further adjustment to improve the effect.

[0240] See also Figure 6 , the specific steps for obtaining the marketing activity performance monitoring results are:

[0241] S411: Based on the promotion strategy after Bayesian optimization, by integrating multi-objective optimization algorithm, balancing cost and effect, the cost-benefit analysis formula is adopted:

[0242]

[0243] The equilibrium optimization result is obtained, where ω g represents the benefit weight of the advertising content, v g represents the expected visual appeal of the advertisement, D g is the cost of advertising content, C g It is the result of balanced optimization;

[0244] S412: Implement marketing activities based on the balance optimization results and monitor marketing performance using an effect tracking model using the formula:

[0245] E g =γ g ·(η g ·C g )

[0246] Generate real-time marketing effect monitoring results, where γ g is the market reaction coefficient, η g is the adjustment factor, E g Represents real-time marketing effect monitoring results;

[0247] S413: Use real-time marketing effectiveness monitoring results to conduct data analysis and evaluate the overall success rate of the campaign, applying the performance evaluation formula:

[0248]

[0249] Generate marketing campaign performance monitoring results, where P g represents the marketing activity performance monitoring results, κ g is the sensitivity parameter, θ g is the success threshold, E g Represents real-time marketing effect monitoring results.

[0250] Balance optimization result formula:

[0251]

[0252] ω g : The benefit weight of advertising content is determined based on historical data and expert analysis;

[0253] v g : The expected visual appeal of the ad, based on the design team’s assessment or consumer research data;

[0254] D g : The cost of advertising content, which comes from the finance department or market research;

[0255] Assumption: There are three types of advertising content, weight ω g They are 0.5, 0.3, and 0.2 respectively, and the visual appeal v g 80, 60, 90 respectively, cost D g They are 1000, 500 and 300 respectively;

[0256] Calculate C g :

[0257]

[0258] The resulting equilibrium optimization result is 0.042, indicating a weighted benefit of visual appeal per unit cost.

[0259] Real-time marketing effect monitoring result formula:

[0260] E g =γ g ·(η g ·C g )

[0261] γ g : Market response coefficient, determined based on market analysis;

[0262] η g : Adjustment coefficient, adjust the impact of market changes on advertising effectiveness;

[0263] C g : Balance optimization result obtained from the previous step;

[0264] Actual example: C g = 0.042 (calculated from step 1), γ g =5,η g =2;

[0265] Calculate E g :

[0266] E g =5·(2·0.042)=5·0.084=0.42

[0267] The performance monitoring result of the marketing campaign is 0.42, which reflects the effectiveness of the campaign relative to the expected execution.

[0268] Marketing campaign performance monitoring results formula:

[0269]

[0270] E g : The marketing campaign performance monitoring results calculated in the previous step;

[0271] κ g : Sensitivity parameter, reflecting the sensitivity of the change to the strategy;

[0272] θ g : Success threshold, set based on business goals and past experience;

[0273] Assume the parameter value is: E g =0.42,κ g =3,θ g =0.4;

[0274] Calculate P g :

[0275]

[0276] The marketing campaign performance monitoring result obtained was evaluated as 0.396, indicating that the campaign was close to the success threshold and the execution effect was good but there was room for further improvement.

[0277] A digital marketing system based on a payment QR code, the digital marketing system based on a payment QR code is used to execute the above-mentioned digital marketing method based on a payment QR code, the system comprising:

[0278] The user behavior analysis module calculates the frequency of QR code scanning and user retention time based on user behavior data, sorts and counts the data, identifies the frequency of use and user preferences, organizes information and analyzes user behavior, and generates user behavior analysis results;

[0279] The QR code parameter optimization module evaluates the attractiveness of the current QR code content based on the results of user behavior analysis, adjusts the discount intensity for differentiated user groups, modifies the time sensitivity and type of promotional information, determines the QR code content strategy, and generates optimized parameter configuration;

[0280] The location-time strategy module optimizes parameter configuration, uses geographic location data and time distribution data, performs data matching analysis, captures the optimal QR code placement location and time point, establishes a data optimization strategy model, and outputs the model as an executable marketing deployment plan to generate a location-time optimization strategy;

[0281] The real-time performance feedback module monitors QR code scanning data and user feedback based on the location-time optimization strategy, collects real-time data and conducts preliminary analysis, updates the marketing model based on the analysis results, makes key adjustments to the promotion strategy, and repositions the strategy focus to obtain the Bayesian optimization strategy;

[0282] The multi-objective marketing optimization module applies the Bayesian optimization strategy to conduct comparative analysis of costs and effects, adjust the parameters of advertising content and promotion activities, adjust and monitor the real-time performance of marketing activities in real time, continuously track the effectiveness of activities, and refine strategies based on market feedback to obtain marketing activity performance monitoring results.

[0283] A digital marketing mobile terminal based on payment QR code includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of the digital marketing method based on payment QR code are implemented.

[0284] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A digital marketing method based on payment QR code, characterized in that: The following steps are involved: Based on user behavior data, calculate the QR code scanning frequency and user retention time, obtain primary user behavior analysis results, and adjust the QR code content parameters including discount strength, type and timeliness of promotional information to generate optimized QR code parameter configuration; Based on the optimized QR code parameter configuration, perform parameter combination operations, determine the optimal QR code placement location and time, generate a location time optimization strategy, make real-time adjustments to the location time optimization strategy, and generate a dynamically adjusted marketing strategy based on market dynamics and historical transaction data; Based on the dynamically adjusted marketing strategy, capture QR code performance data, including scanning frequency and user feedback, generate real-time performance feedback data, use the real-time performance feedback data to update the Bayesian optimization model, adjust the strategy and content of the promotional activities, and generate a Bayesian optimized promotional strategy; Based on the promotional strategy after Bayesian optimization, a multi-objective optimization algorithm is integrated to balance cost and effect, optimize advertising content selection and promotion activity scheduling, generate balanced optimization results, implement marketing activities according to the balanced optimization results, monitor the performance of marketing activities, and generate marketing activity performance monitoring results.

2. The digital marketing method based on payment QR code according to claim 1, characterized in that: The steps for obtaining the optimized QR code parameter configuration are specifically as follows: Based on user behavior data, count the number of times each user scans the QR code and the retention time, calculate the total scanning frequency and average retention time, and use the formula: and Get the user behavior data set, where F a represents the total scanning frequency, f a,i represents the number of scans by the i-th user, T a represents the average retention time, t a,i represents the retention time of the i-th user, and n represents the total number of users; According to the user behavior data set, a weighted user behavior score is calculated by the formula: Get the primary user behavior analysis results, where S a represents the user behavior analysis score, α a is the weight of the scanning frequency, β a is the weight of retention time, γ a is the nonlinear coefficient; According to the primary user behavior analysis results, through the formula: Adjust the QR code content parameters to obtain the optimized QR code parameter configuration, where P a represents the optimized QR code parameter configuration, δ a is the exponential adjustment coefficient, κ a is the slope of the logistic function, λ a is the offset of the logistic function.

3. The digital marketing method based on payment QR code according to claim 2, characterized in that: The steps for obtaining the location time optimization strategy are specifically as follows: Using the optimized QR code parameter configuration, the average flow of people in each time period is calculated using the formula: Introduce the attenuation factor, calculate and obtain the potential scanning frequency data, where P a Represents the optimized QR code parameter configuration, x b represents the flow of people, y b Indicates the time period, e b is the time decay factor, Z b is the potential scanning frequency data; Based on the potential scanning frequency data, combined with the location influence coefficient, a nonlinear attenuation formula is used: Calculate the QR code placement effect at each location and obtain the QR code placement effect evaluation result, where W b Indicates the evaluation result of QR code placement effect, Z b is the potential scanning frequency data, g b is the location influence coefficient; Select the maximum value from the QR code placement effect evaluation results and apply the formula: V b =max(W b ) Determine the optimal QR code placement location and time, and generate a location and time optimization strategy, where V b represents the location time optimization strategy, W b Indicates the evaluation result of the QR code placement effect.

4. The digital marketing method based on payment QR code according to claim 3, characterized in that: The steps for obtaining the dynamically adjusted marketing strategy are specifically as follows: Based on the position time optimization strategy, the current market dynamics data and historical transaction data are integrated, and the compound growth rate formula is used: Adjust the historical weights and calculate the market performance evaluation results, where P c is the benchmark adjustment factor, β c is the historical data impact factor, α c and γ c is the tuning parameter, D c represents the market performance evaluation result, M c Indicates market dynamics data, H c Represents historical transaction data; Using the market performance evaluation results, an index adjustment model is adopted, through the formula: Evaluate the market's reaction sensitivity and generate a market response index, where κ c , η c and c is the nonlinear adjustment parameter, R c represents the market response index, D c Evaluate results for market performance; Based on the market response index, through the strategic decision model, the formula is adopted: Adjust the marketing strategy and generate a dynamically adjusted marketing strategy, where τ c is the strategy adjustment coefficient, μ c is the decision threshold, S c Represents a dynamically adjusted marketing strategy, R c It is a market response indicator.

5. The digital marketing method based on payment QR code according to claim 4, characterized in that: The steps for obtaining the promotion strategy after Bayesian optimization are specifically as follows: Combined with the above dynamically adjusted marketing strategy, the scanning frequency of the QR code and user feedback are collected, and the data aggregation formula is adopted: Get real-time performance feedback data, where f d represents the scanning frequency, u d represents user feedback, ρ d is the weight of user feedback, is the data smoothing parameter, F d It is real-time performance feedback data; The real-time performance feedback data is used to update the Bayesian optimization model, through the formula: Adjust the model to reflect current market dynamics and user behavior and generate an updated Bayesian model, where B d is the updated Bayesian model, F d is the real-time performance feedback data, τ d is the model sensitivity threshold; Using the updated Bayesian model, adjust the strategy and content of the promotional activities, using the strategy optimization formula: Generate a Bayesian optimized promotion strategy, where P d represents the promotion strategy after Bayesian optimization, B d is the updated Bayesian model, λ d is the influence coefficient, σ d and ψ d To adjust the parameters.

6. The digital marketing method based on payment QR code according to claim 5, characterized in that: The steps for obtaining the marketing activity performance monitoring results are specifically as follows: Based on the Bayesian optimized promotion strategy, a cost-benefit analysis formula is adopted by integrating a multi-objective optimization algorithm to balance cost and effect: The equilibrium optimization result is obtained, where ω g represents the benefit weight of the advertising content, v g represents the expected visual appeal of the advertisement, D g is the cost of advertising content, C g It is the result of balanced optimization; According to the above balance optimization results, marketing activities are implemented and marketing performance is monitored using an effect tracking model through the formula: E g =c g ·(or g ·C g ) Generate real-time marketing effect monitoring results, where γ g is the market reaction coefficient, η g is the adjustment factor, E g Represents real-time marketing effect monitoring results; Use the real-time marketing effectiveness monitoring results to conduct data analysis and evaluate the overall success rate of the campaign, applying the performance evaluation formula: Generate marketing campaign performance monitoring results, where P g represents the marketing activity performance monitoring results, κ g is the sensitivity parameter, θ g is the success threshold, E g Represents real-time marketing effect monitoring results.

7. A digital marketing system based on payment QR code, characterized in that: According to the digital marketing method based on payment QR code according to any one of claims 1 to 6, the system comprises: The user behavior analysis module calculates the QR code scanning frequency and user retention time based on user behavior data, sorts data and identifies usage frequency, and generates user behavior analysis results; The QR code parameter optimization module evaluates the attractiveness of the QR code according to the user behavior analysis results, adjusts the type and timeliness of discount and promotion information, and obtains optimized parameter configuration; The location time strategy module uses the above optimization parameter configuration, geographic location and time distribution data to analyze the optimal placement location and time point, and generates a location time optimization strategy; The real-time performance feedback module monitors QR code scanning and user feedback based on the location time optimization strategy, updates the marketing model, makes key adjustments to the strategy, and obtains the Bayesian optimization strategy; The multi-objective marketing optimization module applies the Bayesian optimization strategy, compares and analyzes costs and effects, adjusts advertising content and activity parameters, tracks real-time activity performance, and obtains marketing activity performance monitoring results.

8. A digital marketing mobile terminal based on payment QR code, comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the processor executes the computer program, the steps of the digital marketing method based on payment QR code described in any one of claims 1 to 6 are implemented.

Images