Digital marketing method and system based on intelligent algorithm
By analyzing sales and advertising data and adjusting prices and advertising strategies in real time, the problem of lagging response to market changes in the existing technology is solved, market competitiveness and marketing efficiency are improved, and personalized marketing and profit maximization is achieved.
Patent Information
- Application Number
- CN202411548681.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-01
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing technology relies on static market analysis and one-time pricing strategies, and cannot adjust the market environment and consumer demand in a timely manner, resulting in product pricing not meeting market trends, affecting sales volume and profits, and failing to make full use of user behavior data, resulting in lack of personality in marketing decisions. to reduce conversion rate and market competitiveness.
By obtaining and analyzing the current and historical data of each sold product, calculate the adjustment price value, the number of advertisement push adjustment value, and the ad dwell time adjustment value, and adjust the price and advertising strategy in real time to adapt to market changes and consumer needs.
It has achieved rapid response to market changes, improved market competitiveness and resource allocation efficiency, enhanced the goal and personalization of marketing activities, improved conversion rate and return on investment, optimized price strategies to maximize profits, and reduce market forecast error losses.
Smart Images

Figure CN119067701A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of digital marketing technology, and specifically to a digital marketing method and system based on intelligent algorithms. Background Art
[0002] In the modern business environment, digital marketing has become one of the core strategies for companies to promote their products and services. With the rapid development of Internet technology and the increase in consumer online activities, the importance of digital marketing has become increasingly prominent. Although traditional marketing methods such as TV advertising, print media and outdoor advertising still have certain effects, they cannot provide the accuracy and interactivity that digital marketing can achieve.
[0003] In traditional digital marketing practices, companies often face several major challenges: Companies may collect a large amount of consumer data from multiple channels, but this data is often scattered and difficult to integrate and analyze effectively. Many marketing activities lack timely performance feedback, resulting in marketing decisions that cannot quickly adapt to market changes. Untargeted advertising may lead to high advertising costs and low conversion rates. With the advancement of artificial intelligence and machine learning technologies, intelligent algorithms are increasingly being used in the field of digital marketing to improve the efficiency and effectiveness of marketing activities.
[0004] Based on the above solutions, it is found that the limitations of the existing technology include at least the following problems. First, the existing technology usually relies on static market analysis and one-time pricing strategies, ignoring the rapid changes in the market environment and consumer demand, making it difficult to adjust the marketing strategy in time even when market conditions change, which can easily lead to product pricing not meeting the latest market trends, and then easily lead to products being overpriced or underpriced in the market, affecting sales and profits, causing waste of resources and loss of revenue. Secondly, traditional marketing methods fail to make full use of the large amount of user behavior data and historical sales data collected, and data analysis is often limited to the surface, which makes it difficult for marketing decisions to accurately target the target user group, which in turn makes marketing activities lack personalization and targeting, making it difficult to effectively attract potential customers, reducing conversion rates and market competitiveness. Summary of the invention
[0005] In view of the deficiencies of the prior art, the present invention provides a digital marketing method and system based on intelligent algorithms, which solves the problem that the prior art usually relies on static market analysis and one-time pricing strategies, ignores the rapid changes in the market environment and consumer demand, and makes it difficult to adjust the marketing strategy in time even when market conditions change, which easily leads to product pricing not meeting the latest market trends, and further easily leads to products being priced too high or too low in the market, affecting sales and profits, causing waste of resources and loss of revenue. Secondly, traditional marketing methods fail to make full use of the large amount of user behavior data and historical sales data collected, and data analysis is often limited to the surface, which makes it difficult for marketing decisions to accurately target the target user group, and thus makes marketing activities lack personalization and targeting, making it difficult to effectively attract potential customers, reducing conversion rates and market competitiveness.
[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a digital marketing method based on an intelligent algorithm, comprising the following steps: obtaining current sales data and historical sales data of each sales product, wherein the current sales data includes a current price value, a current number of advertising pushes, and a current advertising dwell time, and the historical sales data includes historical price increase data, historical price reduction data, and historical advertising data; comprehensively analyzing the current price value, historical price increase data, and historical price reduction data of each sales product to obtain an adjusted price value for each sales product; analyzing the current number of advertising pushes, the current advertising dwell time, and historical advertising data of each sales product to obtain an adjusted value for the number of advertising pushes and an adjusted value for the advertising dwell time for each sales product; for each sales product, making real-time adjustments to the current sales data based on the adjusted price value, the adjusted value for the number of advertising pushes, and the adjusted value for the advertising dwell time.
[0007] Furthermore, the historical price increase data specifically include the product increase sales volume, product price increase value, and product increase return volume in each historical price increase cycle; the historical price reduction data specifically include the product reduction sales volume, product price reduction value, and product reduction return volume in each historical price reduction cycle; the historical advertising data specifically include the historical conversion rate in each historical sales cycle and the historical page browsing time of each user each time they purchase a product.
[0008] Furthermore, the specific steps to obtain the adjusted price value of each sales product are as follows: obtain the product sales reference volume of each sales product, and conduct comprehensive analysis based on the product increasing sales volume and product price increase value in each historical price increase cycle, and the product reducing sales volume and product price reduction value in each historical price reduction cycle to obtain the price variation coefficient of each sales product; conduct comprehensive analysis based on the price variation coefficient of each sales product with the current price value of each sales product, the product increasing sales volume and product increasing return volume in each historical price increase cycle, and the product reducing sales volume and product reducing return volume in each historical price reduction cycle to obtain the adjusted price value of each sales product.
[0009] Furthermore, the specific formula for calculating the adjusted price value of each sales product is as follows: ;in, For the The adjusted price value of the sales product, For the The current price value of the product being sold, For the The price variation coefficient of the product sold. For the The history of sales products The sales volume of products increased during the price increase cycle, For the The history of sales products The number of product returns during the price increase cycle, For the The history of sales products The sales volume of products in the price reduction cycle is reduced. For the The history of sales products The number of product returns during a price reduction cycle, , is the number of products sold, , is the number of historical price increase cycles, , The number of cycles by which the historical price is adjusted downward.
[0010] Furthermore, the specific steps for obtaining the price change coefficient of each sales product are as follows: perform difference analysis on the product sales reference quantity of each sales product and the product increase sales quantity in each historical price increase cycle, and obtain the product increase sales change in each historical price increase cycle of each sales product; perform difference analysis on the product sales reference quantity of each sales product and the product reduction sales quantity in each historical price reduction cycle, and obtain the product reduction sales change in each historical price reduction cycle of each sales product; perform comprehensive analysis on the product sales reference quantity of each sales product, the product increase sales change in each historical price increase cycle, the product price increase value, the product reduction sales change in each historical price reduction cycle, and the product price reduction value, and obtain the price change coefficient of each sales product; wherein, the specific formulas for calculating the product increase sales change in each historical price increase cycle, the product reduction sales change in each historical price reduction cycle, and the price change coefficient of each sales product are as follows: ;in, For the The history of sales products The change in product sales during a price increase cycle, For the The history of sales products The sales volume of products increased during the price increase cycle, For the The product sales reference volume of the product sold. For the The history of sales products The sales change of products in a price reduction cycle, For the The history of sales products The sales volume of products in the price reduction cycle is reduced. For the The price variation coefficient of the product sold. For the The history of sales products The product price increase value within a price increase cycle, For the The history of sales products The product price reduction value within a price reduction cycle, , is the number of products sold, , is the number of historical price increase cycles, , The number of cycles by which the historical price is adjusted downward.
[0011] Furthermore, the specific steps for obtaining the adjustment value of the number of advertising pushes for each sales product are as follows: perform mean analysis on the historical conversion rates of each sales product in each historical sales cycle to obtain the historical average conversion rate of each sales product; obtain the marginal revenue and current total advertising revenue of each sales product, and perform a comprehensive analysis based on the historical average conversion rate, the current number of advertising pushes, and the current conversion rate to obtain the adjustment value of the number of advertising pushes for each sales product.
[0012] Furthermore, the specific formula for calculating the historical average conversion rate and the adjustment value of the number of ad pushes for each sales product is as follows: ;in, For the The historical average conversion rate of the products sold, For the The history of sales products Historical conversion rate within sales cycles, For the The adjustment value of the number of advertisement pushes for the sales product. For the The current number of ad pushes for the product being sold. For the Current conversion rate of products sold, For the The marginal revenue from selling a product, For the The current total advertising revenue of the products sold, , is the number of products sold, , is the number of historical sales cycles.
[0013] Furthermore, the specific steps for obtaining the adjustment value of the advertising dwell time for each sales product are as follows: perform a mean analysis on the historical page browsing time of each user each time they purchase a product in each historical sales cycle of each sales product to obtain the average historical page browsing time of each sales product; conduct a comprehensive analysis on the average historical page browsing time of each sales product in combination with the current advertising dwell time to obtain the adjustment value of the advertising dwell time for each sales product.
[0014] Furthermore, the specific formula for calculating the historical average page browsing time and the ad dwell time adjustment value for each sales product is as follows: ;in, For the Average browsing time of historical pages of sales products, For the The history of sales products sales cycle History of users The historical page browsing time when purchasing products, For the The ad dwell time adjustment value of the product being sold. For the The current ad dwell time of the product being sold, For the The stay adjustment factor of the sales product, , is the number of products sold, , is the number of historical sales cycles, , is the number of users, , The number of historical product purchases.
[0015] A digital marketing system based on intelligent algorithms includes: a data acquisition module, a price adjustment analysis module, an advertising adjustment analysis module, and a real-time adjustment module; the data acquisition module is used to acquire the current sales data and historical sales data of each sales product, the current sales data includes the current price value, the current number of advertising pushes, and the current advertising residence time, and the historical sales data includes historical price increase data, historical price reduction data, and historical advertising data; the price adjustment analysis module is used to conduct a comprehensive analysis of the current price value, historical price increase data, and historical price reduction data of each sales product to obtain an adjusted price value for each sales product; the advertising adjustment analysis module is used to analyze the current number of advertising pushes, the current advertising residence time, and the historical advertising data of each sales product to obtain an adjusted value for the number of advertising pushes and an adjusted value for the advertising residence time for each sales product; the real-time adjustment module is used to make real-time adjustments to the current sales data for each sales product based on the adjusted price value, the adjusted value for the number of advertising pushes, and the adjusted value for the advertising residence time.
[0016] The present invention has the following beneficial effects:
[0017] (1) This digital marketing method based on intelligent algorithms can quickly respond to market changes by acquiring and analyzing sales data and market dynamics in real time. For example, by analyzing historical and current data, it can instantly adjust prices and advertising strategies to adapt to changes in consumer demand and competitive conditions. This rapid response not only improves market competitiveness, but also optimizes resource allocation and reduces losses caused by market forecast errors.
[0018] (2) This digital marketing method based on intelligent algorithms makes marketing activities more targeted and personalized by comprehensively analyzing historical advertising data and user behavior. By calculating the number of advertising pushes and the adjustment value of the dwell time, the marketing strategy can reach the target users more accurately, improve the advertising conversion rate and return on investment. For example, historical data analysis helps determine the most effective advertising display duration, thereby reducing invalid pushes and enhancing user engagement.
[0019] (3) This digital marketing method based on intelligent algorithms uses historical price data and sales performance analysis. The intelligent algorithms help companies formulate pricing strategies scientifically and effectively balance market demand and maximize profits. Through detailed analysis of each price increase or decrease cycle, this method can predict the impact of price adjustments on sales volume and return rate, thereby maximizing profits while ensuring competitiveness. The implementation of this strategy helps to improve the company's market adaptability and financial performance and achieve long-term economic growth.
[0020] (4) This digital marketing system based on intelligent algorithms integrates data analysis, price adjustment, advertising adjustment and real-time adjustment modules. This integrated system architecture greatly improves the efficiency of marketing operations and the speed of decision-making. The system has a high degree of automation and can quickly extract useful information from massive data, conduct in-depth analysis, and automatically implement optimization strategies. For example, the system can analyze market data in a few minutes and quickly adjust product pricing and advertising strategies, while traditional methods may take days or even weeks to manually analyze and adjust. This rapid response capability enables companies to immediately take advantage of market opportunities and respond to sudden market changes, thereby maintaining market competitiveness and maximizing marketing effectiveness. In addition, automated data processing and decision-making processes reduce human resource requirements and related costs, while reducing the risks that may be caused by human errors, ensuring the accuracy and reliability of marketing strategies.
[0021] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 This is a flow chart of the digital marketing method based on intelligent algorithm of the present invention.
[0023] Figure 2 The present invention is a flowchart of the specific steps for obtaining the adjusted price value of each sales product in the digital marketing method based on the intelligent algorithm.
[0024] Figure 3 The present invention is a flowchart of the specific steps for obtaining the price variation coefficient of each sales product in the digital marketing method based on the intelligent algorithm.
[0025] Figure 4 This is a block diagram of the digital marketing system based on intelligent algorithms of the present invention. DETAILED DESCRIPTION
[0026] The embodiments of the present application solve the problem that the prior art usually relies on static market analysis and one-time pricing strategies through a digital marketing method and system based on intelligent algorithms, and ignores the rapid changes in the market environment and consumer demand, making it difficult to adjust the marketing strategy in a timely manner even when market conditions change, which can easily lead to product pricing not meeting the latest market trends, and in turn, can easily lead to products being priced too high or too low in the market, affecting sales and profits, causing waste of resources and loss of revenue. Secondly, traditional marketing methods fail to make full use of the large amount of user behavior data and historical sales data collected, and data analysis is often limited to the surface, which makes it difficult for marketing decisions to accurately target the target user group, and thus makes marketing activities lack personalization and targeting, making it difficult to effectively attract potential customers, reducing conversion rates and market competitiveness.
[0027] The overall idea of the problem in the embodiment of this application is as follows:
[0028] First, the current and historical sales data of each product sold are collected, including the current price of the product, number of ad pushes, ad dwell time, and historical price change data and advertising-related data. A detailed analysis is conducted on the collected data, including trend analysis of historical price changes and advertising effectiveness analysis. According to the data analysis results, the price, number of ad pushes, and ad dwell time of each product are adjusted. An intelligent algorithm is used to calculate the optimal price change coefficient, ad push adjustment value, and ad dwell time adjustment value. These calculation results are used to formulate specific adjustment strategies for implementation in the next sales cycle. In each sales cycle, real-time adjustments are implemented according to the formulated strategies, including updates to product prices, ad pushes, and ad dwell time. The market reaction and sales effect after the adjustments are monitored to ensure that the adjustments achieve the expected goals, and necessary strategy optimization is performed based on market feedback.
[0029] See also Figure 1, the embodiment of the present invention provides a technical solution: a digital marketing method based on an intelligent algorithm, comprising the following steps: obtaining current sales data (obtained in real time through an e-commerce platform or an advertising management platform) and historical sales data (extracted from a sales record database) of each sales product, the current sales data including the current price value, the current number of advertising pushes, and the current advertising stay time, and the historical sales data including the historical price increase data, the historical price reduction data, and the historical advertising data; comprehensively analyzing the current price value, the historical price increase data, and the historical price reduction data of each sales product to obtain an adjusted price value of each sales product; analyzing the current number of advertising pushes, the current advertising stay time, and the historical advertising data of each sales product to obtain an adjusted value of the number of advertising pushes and an adjusted value of the advertising stay time of each sales product; for each sales product, adjusting the current sales data in real time (real-time adjustment according to the sales cycle) based on the adjusted price value, the adjusted value of the number of advertising pushes, and the adjusted value of the advertising stay time, respectively, and the specific adjustment steps are: after the end of the current sales cycle, using the calculated adjusted price value, the adjusted value of the number of advertising pushes, and the adjusted value of the advertising stay time of each sales product as the initial price value, the initial number of advertising pushes, and the initial advertising stay time of each sales product at the beginning of the next cycle.
[0030] The historical price increase data specifically include the product increase sales volume, product price increase value, and product increase return volume in each historical price increase cycle. The historical price reduction data specifically include the product reduction sales volume, product price reduction value, and product reduction return volume in each historical price reduction cycle. The historical advertising data specifically include the historical conversion rate in each historical sales cycle and the historical page browsing time of each user each time they purchase a product.
[0031] Specifically, Figure 2 As shown, the specific steps for obtaining the adjusted price value of each sales product are as follows: obtain the product sales reference volume of each sales product, and conduct comprehensive analysis on the product increase sales volume and product price increase value in each historical price increase cycle, and the product reduction sales volume and product price reduction value in each historical price reduction cycle to obtain the price change coefficient of each sales product; conduct comprehensive analysis on the price change coefficient of each sales product with the current price value of each sales product, the product increase sales volume and product increase return volume in each historical price increase cycle, and the product reduction sales volume and product reduction return volume in each historical price reduction cycle to obtain the adjusted price value of each sales product.
[0032] The specific formula for calculating the adjusted price value for each sales product is as follows: ;in, For the The adjusted price value of the sales product, For the The current price value of the product being sold, For the The price variation coefficient of the product sold. For the The history of sales products The sales volume of products increased during the price increase cycle, For the The history of sales products The number of product returns during the price increase cycle, For the The history of sales products The sales volume of products in the price reduction cycle is reduced. For the The history of sales products The number of product returns during a price reduction cycle, , is the number of products sold, , is the number of historical price increase cycles, , The number of cycles by which the historical price is adjusted downward.
[0033] In this implementation scheme, by combining historical price increase and decrease data and related sales and return volumes, this method enables companies to understand the specific impact of different price points on consumer behavior. This not only helps companies grasp market price sensitivity, but also allows them to dynamically adjust prices to maximize sales and revenue. For example, if historical data shows that sales increase significantly and returns do not increase when prices are reduced, companies may tend to lower prices when demand is high to promote more sales. By calculating the price change coefficient and combining it with current market conditions, companies can adjust their pricing strategies more finely, rather than simply setting them based on cost-plus or market average prices. This method takes into account market reactions and internal sales data, making price adjustments more scientific. This refined management helps companies avoid over-pricing or low-price sales, thereby maximizing profits. By analyzing the actual impact of price changes on sales and returns, companies can manage inventory more effectively and reduce excess or shortages caused by inappropriate price setting. Reasonable price adjustments can help companies quickly transfer slow-selling products and improve capital liquidity, thereby supporting new product development and market expansion activities. Comprehensive consideration of historical sales and return data for price adjustments can help companies better meet consumer expectations and market demands and improve customer satisfaction. At the same time, timely and appropriate price adjustments reflect the company's sensitivity and responsiveness to market dynamics, and enhance its brand image and market competitiveness in the minds of consumers.
[0034] Specifically, Figure 3 As shown, the specific steps for obtaining the price variation coefficient of each sales product are as follows: perform difference analysis on the product sales reference quantity of each sales product and the product increase sales quantity in each historical price increase cycle, and obtain the product increase sales variation of each sales product in each historical price increase cycle; perform difference analysis on the product sales reference quantity of each sales product and the product reduction sales quantity in each historical price reduction cycle, and obtain the product reduction sales variation of each sales product in each historical price reduction cycle; perform comprehensive analysis on the product sales reference quantity of each sales product, the product increase sales variation in each historical price increase cycle, the product price increase value, the product reduction sales variation in each historical price reduction cycle, and the product price reduction value, and obtain the price variation coefficient of each sales product.
[0035] The specific formulas for calculating the product sales increase change in each historical price increase cycle, the product sales decrease change in each historical price decrease cycle, and the price change coefficient for each sales product are as follows: ;in, For the The history of sales products The change in product sales during a price increase cycle, For the The history of sales products The sales volume of products increased during the price increase cycle, For the The product sales reference volume of the product sold. For the The history of sales products The sales change of products in a price reduction cycle, For the The history of sales products The sales volume of products in the price reduction cycle is reduced. For the The price variation coefficient of the product sold. For the The history of sales products The product price increase value within a price increase cycle, For the The history of sales products The product price reduction value within a price reduction cycle, , is the number of products sold, , is the number of historical price increase cycles, , The number of cycles by which the historical price is adjusted downward.
[0036] It should be explained that the product sales reference volume is the average of the total sales volume of the product over several sales cycles at the time of initial pricing (extracted from the sales record database).
[0037] The specific implementation example of calculating the adjusted price value of a certain sales product is as follows, with the following data:
[0038] The product sales reference quantity of a certain sales product is 7,000 units and the current price value is 300 yuan.
[0039] There are two historical price increase cycles, and the product sales changes in the two historical price increase cycles are -100 units and -200 units respectively, the product price increase values in the two historical price increase cycles are 5 yuan and 3 yuan respectively, and the product return volumes in the two historical price increase cycles are 300 units and 350 units respectively.
[0040] There are two historical price reduction cycles, and the product sales reduction changes in the two historical price reduction cycles are +100 units and +150 units respectively, the product price reduction values in the two historical price reduction cycles are 3 yuan and 4 yuan respectively, and the product return reduction volumes in the two historical price reduction cycles are 200 units and 400 units respectively.
[0041] Inputting the above parameters into the calculation formula of the adjusted price value of the sales product, it can be calculated that the adjusted price value of the sales product is JgT=300+(1 / 7000)*((-100*5-200*6)-(100*3+150*4))*(1-((300+350)+(200+400)) / ((6900+6800)+(7100+7150))≈300.273 yuan.
[0042] In this implementation scheme, by comprehensively analyzing the reference sales volume of the product with the sales volume and return volume of the historical price change cycle, the method enables enterprises to accurately understand the actual impact of price changes on consumer purchasing behavior. This analysis helps enterprises gain insight into the specific impact of different price changes on sales and returns, thereby judging the consumer's sensitivity to price changes and which price adjustment strategies have been effective or ineffective in the past, providing a basis for future pricing decisions. Combining historical sales data and return data, this method allows enterprises to adjust prices more accurately to maximize profits. By considering the sales changes and returns in different cycles, enterprises can: prevent the reduction of sales and loss of market share caused by overpricing, avoid setting too low prices through scientific calculations, and protect profit margins from being damaged. Through systematic data analysis, enterprises can formulate pricing strategies more objectively and accurately, rather than relying on empirical judgment or market speculation. This data-driven approach provides: pricing decisions based on actual data analysis, reducing uncertainty and risk due to intuition, and the ability to quickly integrate and analyze the latest market data, adjusting prices in real time to adapt to market fluctuations. Through this approach, not only are price adjustments optimized, but the overall market strategy—including advertising push, product promotions, and customer relationship management—can be better coordinated with the pricing strategy to form a unified market entry and expansion strategy.
[0043] Specifically, the specific steps to obtain the adjustment value of the number of advertising pushes for each sales product are as follows: perform mean analysis on the historical conversion rates of each sales product in each historical sales cycle to obtain the historical average conversion rate of each sales product; obtain the marginal revenue and current total advertising revenue of each sales product, and perform a comprehensive analysis based on the historical average conversion rate, the current number of advertising pushes, and the current conversion rate to obtain the adjustment value of the number of advertising pushes for each sales product.
[0044] The specific formula for calculating the historical average conversion rate and the adjustment value of the number of ad pushes for each sales product is as follows: ;in, For the The historical average conversion rate of the products sold, For the The history of sales products Historical conversion rate within sales cycles, For the The adjustment value of the number of advertisement pushes for the sales product. For the The current number of ad pushes for the product being sold. For the Current conversion rate of products sold, For the The marginal revenue from selling a product, For the The current total advertising revenue of the products sold, , is the number of products sold, , is the number of historical sales cycles.
[0045] It should be explained that the current number of ad pushes refers specifically to the number of ongoing ad pushes.
[0046] The conversion rate is calculated by dividing the total number of product visits by the total number of product purchases.
[0047] Marginal revenue (obtained through data analysis in the sales record database) is the additional revenue that can be brought about by each unit increase in conversion rate (for example, the conversion rate increases from 4% to 5%). The specific calculation process is: collect advertising revenue and corresponding conversion rate data within a certain period of time, for example, record the conversion rates of different advertising campaigns in the past few months (such as 4%, 5%, 6%, etc.) and their corresponding revenues, use linear regression or multiple regression analysis to determine the relationship between conversion rate and revenue, establish a model with conversion rate as the independent variable and revenue as the dependent variable, and analyze it to obtain marginal revenue. If the regression result shows that marginal revenue = 1000, this means that for every 1% increase in conversion rate, the revenue increases by an average of 1,000 yuan.
[0048] The current total revenue (obtained through data analysis in the sales record database) refers to the total revenue achieved in the current advertising campaign. The specific calculation process is: use the tools provided by the advertising platform (such as Google AdWords, Facebook Ads Manager, etc.) to track the revenue of the advertising campaign, ensure that the tracking settings are correct, and be able to capture all relevant revenue data, including direct sales, potential customer conversions, etc. Within the specified advertising cycle, summarize all relevant revenue data, calculate the total, deduct the advertising cost from the total revenue, and obtain the net revenue.
[0049] In this implementation scheme, by combining historical average conversion rates with current advertising campaign data for analysis, companies can more accurately determine which advertising strategies are most effective and adjust advertising investment accordingly. For example, if historical data shows that the conversion rate of a product increases significantly after increasing the number of advertisements, then increasing advertising investment for this product can directly increase sales, thereby improving the overall ROI (return on investment) of advertising. This method can ensure that advertising budgets are allocated to activities that are most likely to generate the highest returns. By analyzing marginal revenue and current total revenue, companies can make more informed decisions about the allocation of advertising budgets. This strategy can help companies avoid wasting resources on inefficient advertising while increasing investment in efficient advertising. For example, if a product has low marginal revenue, the company may choose to reduce its number of advertisements and reallocate resources to other products with higher marginal revenues. This data-based resource allocation not only improves the profitability of each product, but also improves the company's profitability. The effect of unit advertising expenditure also enhances the cost-effectiveness of the overall marketing activities. The current adjustment of the number of advertising pushes is not only based on historical data, but also combined with real-time market feedback, enabling companies to flexibly respond to market changes. In a highly competitive market environment, the ability to quickly adjust advertising strategies is crucial to seizing market opportunities. For example, if the initial effect of a certain advertising campaign exceeds expectations, the company can quickly increase the number of advertising pushes for the campaign to maximize market response. Similarly, if an advertisement is not effective, timely reducing its exposure can reduce unnecessary expenses. By systematically analyzing and adjusting the number of advertising pushes, companies can continuously optimize the performance of their advertising campaigns. This continuous optimization process not only improves the effectiveness of a single advertising campaign, but also plays a positive role in the success of the entire marketing strategy. In the long run, this strategy can help companies establish more effective brand promotion and customer interaction, thereby enhancing brand influence and market share.
[0050] Specifically, the specific steps for obtaining the advertising dwell time adjustment value for each sales product are as follows: perform mean analysis on the historical page browsing time of each user each time they purchase a product in each historical sales cycle of each sales product to obtain the historical average page browsing time of each sales product; conduct a comprehensive analysis of the historical average page browsing time of each sales product in combination with the current advertising dwell time to obtain the advertising dwell time adjustment value for each sales product.
[0051] The specific formula for calculating the historical average page browsing time and ad dwell time adjustment value for each sales product is as follows: ;in, For the Average browsing time of historical pages of sales products, For the The history of sales products sales cycle History of users The historical page browsing time when purchasing products, For the The ad dwell time adjustment value of the product being sold. For the The current ad dwell time of the product being sold, For the The stay adjustment factor of the sales product, , is the number of products sold, , is the number of historical sales cycles, , is the number of users, , The number of historical product purchases.
[0052] It should be explained that the current advertisement dwell time specifically refers to the dwell time of the current advertisement on the sales software page.
[0053] The current page browsing time is specifically the average browsing time of users when purchasing products on the sales software page where the current advertisement is located (for example, the first browsing time is 30 seconds, but no purchase is made, the second browsing time is 20 seconds, but a purchase is made, so the average time is 25 seconds).
[0054] The specific calculation process is as follows: for a certain sales product of an online retail store, by analyzing advertising data, we hope to adjust the advertising dwell time to maximize revenue, collect historical advertising data, including the page browsing time (seconds) and the corresponding advertising revenue (US dollars) of each advertising exposure of a certain sales product.
[0055] Example data:
[0056] Ad 1: Viewing time 30 seconds, sales of a product earning $0.10.
[0057] Ad 2: Viewing time 45 seconds, sales of a product with a profit of $0.20.
[0058] Ad 3: Viewing time 50 seconds, profit of $0.25 from selling a certain product.
[0059] Linear regression was used to analyze the relationship between page view time (independent variable) and advertising revenue (dependent variable).
[0060] For example, if the regression analysis result is: Revenue = 0.05 + 0.005 × browsing time, here, the stay adjustment coefficient = 0.005, which means that for every additional second of page browsing time, the advertising revenue of a certain sales product increases by an average of US$0.005.
[0061] In this implementation scheme, historical data is used to analyze the relationship between page browsing time and advertising revenue, and the advertising dwell time is adjusted accordingly, which can significantly increase the revenue potential of each advertising exposure. For example, the dwell adjustment coefficient determined by linear regression analysis can accurately indicate the increase in revenue brought about by increasing the advertising dwell time. If the analysis shows that each additional second of browsing time can significantly increase revenue, the adjustment strategy can make the advertisement more effective and improve the overall ROI (return on investment) of advertising. This data-based adjustment method enables advertising budgets to be used more effectively, thereby maximizing advertising revenue. By adjusting the advertising dwell time to adapt to the user's browsing habits, the user's engagement and satisfaction can be improved. If historical data shows that users tend to make purchase decisions after a longer browsing time, then increasing the advertising dwell time can provide users with more This not only improves the user experience, but may also indirectly increase revenue by increasing conversion rates. In-depth analysis of the relationship between browsing time and revenue can also help companies optimize the advertising content itself. For example, if an advertisement can achieve a high conversion rate in a short period of time, it may indicate that the advertising content directly hits user needs and is very effective. On the contrary, if a longer browsing time is required for conversion, it may indicate that the attractiveness of the advertising content or the efficiency of information communication needs to be improved. Therefore, this analysis not only focuses on time adjustment, but also goes deep into the optimization of advertising content and design. Market conditions and consumer behavior are constantly changing. By continuously analyzing advertising data and adjusting advertising strategies accordingly, companies can respond to these changes more flexibly. This dynamic adjustment can ensure that advertising strategies are always kept up to date and keep pace with the current needs of the market and consumers.
[0062] See also Figure 4The embodiment of the present invention provides a technical solution: a digital marketing system based on an intelligent algorithm, comprising: a data acquisition module, a price adjustment analysis module, an advertising adjustment analysis module, and a real-time adjustment module; the data acquisition module is used to acquire the current sales data (acquired in real time through an e-commerce platform or an advertising management platform) and historical sales data (extracted from a sales record database) of each sales product, the current sales data includes the current price value, the current number of advertising pushes, and the current advertising stay time, and the historical sales data includes the historical price increase data, the historical price reduction data, and the historical advertising data; the price adjustment analysis module is used to perform a comprehensive analysis on the current price value, the historical price increase data, and the historical price reduction data of each sales product, respectively, to obtain the adjusted price value of each sales product; the advertising adjustment analysis module is used to analyze the current number of advertising pushes, the current advertising stay time, and the historical advertising data of each sales product, respectively, to obtain the advertising push number adjustment value and the advertising stay time adjustment value of each sales product; the real-time adjustment module is used to adjust the current sales data in real time (real-time adjustment according to the sales cycle) for each sales product based on the adjusted price value, the advertising push number adjustment value, and the advertising stay time adjustment value.
[0063] In summary, this application has at least the following effects:
[0064] By acquiring and analyzing sales data and market dynamics in real time, this method can respond quickly to market changes. For example, by analyzing historical and current data, prices and advertising strategies can be adjusted instantly to adapt to changes in consumer demand and competitive conditions. This rapid response not only improves market competitiveness, but also optimizes resource allocation and reduces losses caused by market forecast errors.
[0065] By comprehensively analyzing historical advertising data and user behavior, marketing activities can be more targeted and personalized. By calculating the number of ad pushes and the adjustment value of the dwell time, marketing strategies can reach target users more accurately, improve advertising conversion rate and return on investment. For example, historical data analysis helps determine the most effective ad display duration, thereby reducing invalid pushes and enhancing user engagement.
[0066] Using historical price data and sales performance analysis, intelligent algorithms help companies formulate pricing strategies scientifically and effectively balance market demand and maximize profits. Through detailed analysis of each price increase or decrease cycle, this method can predict the impact of price adjustments on sales volume and return rate, thereby maximizing profits while ensuring competitiveness. The implementation of this strategy helps to improve the company's market adaptability and financial performance and achieve long-term economic benefit growth.
[0067] By integrating data analysis, price adjustment, advertising adjustment and real-time adjustment modules, this integrated system architecture greatly improves the efficiency of marketing operations and the speed of decision-making. The system has a high degree of automation and can quickly extract useful information from massive data, conduct in-depth analysis, and automatically implement optimization strategies. For example, the system can analyze market data in a few minutes and quickly adjust product pricing and advertising strategies, while traditional methods may take days or even weeks to manually analyze and adjust. This rapid response capability enables companies to immediately take advantage of market opportunities and respond to sudden market changes, thereby maintaining market competitiveness and maximizing marketing effectiveness. In addition, automated data processing and decision-making processes reduce human resource requirements and related costs, while reducing the risks that may be caused by human errors, ensuring the accuracy and reliability of marketing strategies.
[0068] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0069] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A digital marketing method based on intelligent algorithms, characterized by: The following steps are involved: Obtaining the current sales data and historical sales data of each product for sale, wherein the current sales data includes the current price value, the current number of advertisement pushes, and the current advertisement dwell time, and the historical sales data includes the historical price increase data, the historical price reduction data, and the historical advertisement data; Conduct a comprehensive analysis of the current price value, historical price increase data, and historical price reduction data of each sales product to obtain the adjusted price value of each sales product; Analyze the current number of advertisement pushes, current advertisement dwell time, and historical advertisement data of each sales product to obtain an adjustment value for the number of advertisement pushes and an adjustment value for the advertisement dwell time of each sales product; For each sales product, the current sales data is adjusted in real time based on the adjusted price value, the adjusted number of ad pushes, and the adjusted ad stay time; The historical price increase data specifically include the product increase sales volume, product price increase value, and product increase return volume in each historical price increase cycle; the historical price reduction data specifically include the product reduction sales volume, product price reduction value, and product reduction return volume in each historical price reduction cycle; the historical advertising data specifically include the historical conversion rate in each historical sales cycle, and the historical page browsing time of each user when purchasing a product each time; The specific steps to get the adjusted price value of each sales product are as follows: Obtain the reference sales volume of each product for sale, and conduct a comprehensive analysis based on the product sales volume and price increase value in each historical price increase cycle, and the product sales volume and price decrease value in each historical price decrease cycle, to obtain the price change coefficient of each product for sale; The price change coefficient of each sales product is combined with the current price value of each sales product, the product increase sales volume and product increase return volume in each historical price increase cycle of each sales product, and the product decrease sales volume and product decrease return volume in each historical price decrease cycle of each sales product, and a comprehensive analysis is performed to obtain the adjusted price value of each sales product; The specific formula for calculating the adjusted price value for each sales product is as follows: ; in, For the The adjusted price value of the sales product, For the The current price value of the product being sold, For the The price variation coefficient of the product sold. For the The history of sales products The sales volume of products increased during the price increase cycle, For the The history of sales products The number of product returns during the price increase cycle, For the The history of sales products The sales volume of products in the price reduction cycle is reduced. For the The history of sales products The number of product returns during a price reduction cycle, , is the number of products sold, , is the number of historical price increase cycles, , The number of cycles by which the historical price is adjusted downward.
2. The digital marketing method based on intelligent algorithm according to claim 1, characterized in that: The specific steps to obtain the price variation coefficient of each sales product are as follows: Perform difference analysis on the product sales reference volume of each sales product and the product sales volume in each historical price increase cycle, and obtain the product sales change volume in each historical price increase cycle of each sales product; Perform difference analysis on the reference sales volume of each product for sale and the product sales volume in each price reduction cycle in history, and obtain the product sales volume change in each price reduction cycle in history for each product for sale; Comprehensively analyze the sales reference volume of each product, the sales change volume of each price increase cycle, the product price increase value, the sales change volume of each price reduction cycle, and the product price reduction value to obtain the price change coefficient of each product. The specific formulas for calculating the product sales increase change in each historical price increase cycle, the product sales decrease change in each historical price decrease cycle, and the price change coefficient for each sales product are as follows: ; in, For the The history of sales products The change in product sales during a price increase cycle, For the The history of sales products The sales volume of products increased during the price increase cycle, For the The product sales reference volume of the product sold. For the The history of sales products The sales change of products in a price reduction cycle, For the The history of sales products The sales volume of products in the price reduction cycle is reduced. For the The price variation coefficient of the product sold. For the The history of sales products The product price increase value within a price increase cycle, For the The history of sales products The product price reduction value within a price reduction cycle, , is the number of products sold, , is the number of historical price increase cycles, , The number of cycles by which the historical price is adjusted downward.
3. The digital marketing method based on intelligent algorithm according to claim 1, characterized in that: The specific steps to obtain the adjustment value of the number of ad pushes for each sales product are as follows: Perform mean analysis on the historical conversion rates of each sales product in each sales cycle to obtain the historical average conversion rate of each sales product; Obtain the marginal revenue and current total advertising revenue of each sales product, and conduct a comprehensive analysis based on the historical average conversion rate, current number of ad pushes, and current conversion rate to obtain the adjustment value of the number of ad pushes for each sales product.
4. The digital marketing method based on intelligent algorithm according to claim 3 is characterized in that: The specific formula for calculating the historical average conversion rate and the adjustment value of the number of ad pushes for each sales product is as follows: ; in, For the The historical average conversion rate of the products sold, For the The history of sales products Historical conversion rate within sales cycles, For the The adjustment value of the number of advertisement pushes for the sales product. For the The current number of ad pushes for the product being sold. For the Current conversion rate of products sold, For the The marginal revenue from selling a product, For the The current total advertising revenue of the products sold, , is the number of products sold, , is the number of historical sales cycles.
5. The digital marketing method based on intelligent algorithm according to claim 1, characterized in that: The specific steps to obtain the ad dwell time adjustment value for each sales product are as follows: Perform mean analysis on the historical page browsing time of each user at each purchase of each product in each sales cycle to obtain the historical average page browsing time of each sales product; A comprehensive analysis is performed on the historical average page browsing time of each sales product combined with the current advertisement dwell time to obtain an advertisement dwell time adjustment value for each sales product.
6. The digital marketing method based on intelligent algorithm according to claim 5 is characterized in that: The specific formula for calculating the historical average page browsing time and ad dwell time adjustment value for each sales product is as follows: ; in, For the Average browsing time of historical pages of sales products, For the The history of sales products sales cycle History of users Historical page browsing time when purchasing products, For the The ad dwell time adjustment value of the product being sold. For the The current ad dwell time of the product being sold, For the The stay adjustment factor of the sales product, , is the number of products sold, , is the number of historical sales cycles, , is the number of users, , The number of historical product purchases.
7. A digital marketing system based on intelligent algorithms, applying the digital marketing method based on intelligent algorithms as described in any one of claims 1 to 6, characterized in that: include: Data acquisition module, price adjustment analysis module, advertising adjustment analysis module, real-time adjustment module; The data acquisition module is used to acquire the current sales data and historical sales data of each product for sale, wherein the current sales data includes the current price value, the current number of advertisement pushes, and the current advertisement dwell time, and the historical sales data includes the historical price increase data, the historical price reduction data, and the historical advertisement data; The price adjustment analysis module is used to comprehensively analyze the current price value, historical price increase data, and historical price reduction data of each sales product to obtain the adjusted price value of each sales product; The advertising adjustment analysis module is used to analyze the current number of advertising pushes, the current advertising dwell time, and the historical advertising data of each sales product, and obtain an adjustment value for the number of advertising pushes and the advertising dwell time of each sales product; The real-time adjustment module is used to make real-time adjustments to the current sales data for each sales product based on the adjusted price value, the adjusted number of advertisement push times, and the adjusted advertisement stay time.
Citation Information
Patent Citations
Advertisement pushing method and system based on Internet of Things
CN116739664A
Intelligent management method and system for hotel online marketing
CN118396661A
Advertisement marketing method and system
CN118469648A
Shopping system based on app shopping mall
CN118674587A
