Customer acquisition strategy management method and device based on scene perception

Abstract

The application relates to a customer acquisition strategy management method and device based on scene perception. The method comprises the following steps: acquiring multi-dimensional data of a target user group, and acquiring a scene conversion judgment value for representing conversion possibility in a current scene; judging whether a dynamic factor interference exists in a scene where the target user group is located and whether a real-time change occurs in a scene feature; acquiring a first optimization strategy when the dynamic factor interference does not exist and the real-time change does not occur in the scene feature; acquiring a second optimization strategy when the dynamic factor interference exists and the real-time change occurs in the scene feature; determining a final executed customer acquisition strategy scheme; and wherein the customer acquisition strategy scheme is determined based on trial execution feedback data of the first optimization strategy or the second optimization strategy in a sample user group. In this way, the problems of scene factor ambiguity, insufficient dynamic adaptability, lack of scientific verification and the like in the related art customer acquisition strategy can be effectively solved, and the precision, flexibility and economy of the customer acquisition strategy are significantly improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method and apparatus for managing customer acquisition strategies based on scene awareness. Background Technology

[0002] In the wave of digital marketing, competition for customer acquisition is becoming increasingly fierce. Users' needs and decision-making patterns differ significantly across different scenarios (such as commuting, shopping, and work), and their behavioral patterns and surrounding environments have a crucial impact on conversion intentions. However, traditional customer acquisition strategies are often based on extensive user analysis, relying primarily on static basic attributes such as age and location to simply segment user groups, neglecting the deeper value of user behavior patterns and the dynamic changes in scenarios. This results in marketing messages failing to reach the target audience accurately, leading to generally low conversion rates.

[0003] The relevant technologies primarily focus on transforming the static association between customers, scenarios, and products into dynamic associations. They fail to delve into the multi-dimensional value of user behavior trajectories or design tiered strategies based on differences in customer value levels and channel capabilities. This results in strategies remaining at the individual-product matching level, making it difficult to cope with complex and ever-changing market environments. Therefore, these technologies cannot accurately perceive the dynamic changes in user scenarios or quantify the impact of scenarios on conversion intentions to optimize customer acquisition strategies. Summary of the Invention

[0004] This application provides a method and apparatus for managing customer acquisition strategies based on scene awareness.

[0005] According to a first aspect of the embodiments of this application, a customer acquisition strategy management method based on scene awareness is provided, the method comprising: Acquire multi-dimensional data of the target user group, identify the scenario features that affect users' willingness to convert based on the multi-dimensional data, and establish a quantitative correlation between scenario features and conversion probability based on historical customer acquisition data to obtain a scenario conversion judgment value used to characterize the conversion possibility in the current scenario. Quantitatively determine the relationship between different customer acquisition strategies and user responses in historical customer acquisition data to obtain the strategy response coefficient; Determine whether there are dynamic factors interfering with the scene in which the target user group is located, and whether the scene characteristics are changing in real time; When there are no dynamic factors interfering and the scene characteristics do not change in real time, the initial customer acquisition strategy is optimized and adjusted based on the strategy response coefficient and the scene conversion judgment value to obtain the first optimized strategy. When there are dynamic factors interfering and the scene characteristics change in real time, the fluctuation of user conversion intention is calculated by a dynamic impact assessment model based on the dynamic factor interference information and the scene characteristic change information. The calculated fluctuation is then corrected according to the influence relationship between the direction of dynamic factor interference and the direction of scene characteristic change on conversion intention, resulting in a corrected conversion intention fluctuation value. Based on the corrected conversion intention fluctuation value, the strategy response coefficient, and the changed scene characteristic information, the initial customer acquisition strategy is optimized and adjusted to obtain a second optimized strategy. The final customer acquisition strategy is determined; wherein the customer acquisition strategy is determined based on the trial execution feedback data of the first optimization strategy or the second optimization strategy in the sample user group.

[0006] According to a second aspect of the embodiments of this application, a scene-aware customer acquisition strategy management device is provided, the device comprising: The data acquisition module is used to acquire multi-dimensional data of the target user group, identify the scenario features that affect users' willingness to convert based on the multi-dimensional data, and establish a quantitative correlation between scenario features and conversion probability based on historical customer acquisition data to obtain a scenario conversion judgment value that represents the possibility of conversion in the current scenario. The coefficient acquisition module is used to obtain the quantitative relationship between different customer acquisition strategies and user responses in historical customer acquisition data, and to obtain the strategy response coefficient. The judgment module is used to determine whether there are dynamic factors interfering with the scene in which the target user group is located and whether the scene characteristics are changing in real time. The first optimization strategy acquisition module is used to optimize and adjust the initial customer acquisition strategy based on the strategy response coefficient and the scenario conversion judgment value when there are no dynamic factors interfering and the scenario characteristics do not change in real time, so as to obtain the first optimization strategy. The second optimization strategy acquisition module is used to calculate the fluctuation of user conversion intention based on dynamic factor interference information and scene feature change information when there are dynamic factors interference and scene feature change information. It calculates the fluctuation of user conversion intention through dynamic impact assessment model, corrects the calculated fluctuation according to the influence relationship between the direction of dynamic factor interference and the direction of scene feature change on conversion intention, and obtains the corrected conversion intention fluctuation value. Based on the corrected conversion intention fluctuation value, strategy response coefficient and changed scene feature information, the initial customer acquisition strategy is optimized and adjusted to obtain the second optimization strategy. The strategy determination module is used to determine the final customer acquisition strategy to be implemented; wherein, the customer acquisition strategy is determined based on the trial execution feedback data of the first optimization strategy or the second optimization strategy in the sample user group.

[0007] According to a third aspect of the embodiments of this application, an electronic device is provided. The electronic device includes a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the program to implement the method described above.

[0008] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the methods described above in this application.

[0009] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods described above in this application.

[0010] The scenario-aware customer acquisition strategy management method and apparatus provided in this application achieve accurate perception of user scenario conversion potential by constructing a quantitative correlation between scenario features and conversion probability. By introducing a dynamic factor interference identification and classification optimization mechanism, it optimizes reach channels and content formats in static scenarios, and calculates conversion intention fluctuation values ​​and makes corrections based on influence relationships in dynamic interference scenarios using a dynamic impact assessment model. Furthermore, it accurately determines the adjustment parameters for discount intensity and reach timing by combining an adjustment magnitude reference model constructed from historical cases, achieving adaptive strategy optimization for complex and ever-changing scenarios. Further, through small-scale sample trial execution and strategy effect trend curve analysis, it identifies the adjustment dimensions with the most significant effect improvement and the execution interval with stable effect, and outputs the final solution based on cost-benefit data. This effectively solves the problems of ambiguity of scenario factors, insufficient dynamic adaptability, and lack of scientific verification in customer acquisition strategies in related technologies, significantly improving the accuracy, flexibility, and economy of customer acquisition strategies. Attached Figure Description

[0011] Further details, features, and advantages of this application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 A flowchart illustrating a scenario-aware customer acquisition strategy management method provided for an exemplary embodiment of this application; Figure 2 A schematic block diagram of the functional modules of a scene-aware customer acquisition strategy management device provided for an exemplary embodiment of this application; Figure 3 A structural block diagram of an electronic device provided in an exemplary embodiment of this application; Figure 4 A structural block diagram of a computer system provided for an exemplary embodiment of this application. Detailed Implementation

[0012] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While some embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this application. It should be understood that the drawings and embodiments of this application are for illustrative purposes only and are not intended to limit the scope of protection of this application.

[0013] It should be understood that the steps described in the method embodiments of this application may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this application is not limited in this respect.

[0014] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this application are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0015] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more". The names of the messages or information exchanged between multiple devices in the embodiments of this application are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0016] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0017] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this application's technical solution, based on the prompt message.

[0018] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device. It is understood that the above notification and user authorization process is merely illustrative and does not limit the implementation of this application; other methods that comply with relevant laws and regulations may also be applied to the implementation of this application.

[0019] This application first provides a scenario-aware customer acquisition strategy management method. This method can adaptively optimize customer acquisition strategies based on the dynamic changes in the user's scenario, thereby improving customer acquisition efficiency and conversion rate. Figure 1 As shown, the method may include the following steps: In step S110, multi-dimensional data of the target user group is obtained, and the scenario features that affect the user's willingness to convert are identified based on the multi-dimensional data. A quantitative correlation between scenario features and conversion probability is established based on historical customer acquisition data to obtain a scenario conversion judgment value used to characterize the conversion possibility in the current scenario.

[0020] Specifically, this multi-dimensional data includes basic attribute data of the target user group (such as age, region, and spending power level) and behavioral trajectory data (such as software usage records, web browsing records, and consumption purchase records). By performing scenario identification on the behavioral trajectory data, different scenario types can be distinguished, such as daily commuting scenarios, leisure shopping scenarios, and work / office scenarios. The frequency of occurrence and duration of each scenario type are statistically analyzed, and a threshold for user conversion intention is set. Key scenario features that meet the threshold requirements in terms of frequency and duration are extracted from the identified scenarios. Subsequently, data from the historical customer acquisition strategy execution process is acquired to establish a correspondence database between scenario features and user conversion results. Historical scenario data matching the key scenario features is extracted from the historical customer acquisition data, and the historical scenario conversion probability is statistically analyzed. The ratio of the historical scenario conversion probability to the quantified value of the corresponding scenario feature is used to obtain the scenario conversion coefficient. Then, the quantified value of the key scenario feature is multiplied by the scenario conversion coefficient to obtain the scenario conversion judgment value. This scenario conversion judgment value is used to quantitatively characterize the probability of a user engaging in conversion behavior in the current scenario.

[0021] In step S120, the quantitative relationship between different customer acquisition strategies and user responses in historical customer acquisition data is obtained to obtain the strategy response coefficient.

[0022] User response data for different types of customer acquisition strategies (such as coupon strategies, content marketing strategies, and community traffic generation strategies) is extracted from historical customer acquisition data. The number of responding users and the number of users reached for each strategy are statistically analyzed to calculate the historical strategy response rate. The ratio of the historical strategy response rate to the quantified cost of the corresponding customer acquisition strategy is used to obtain the strategy response coefficient. This strategy response coefficient reflects the response effect of the strategy under unit cost input, providing a cost-effectiveness reference for subsequent strategy optimization.

[0023] In step S130, it is determined whether there are dynamic factors interfering with the scene where the target user group is located and whether the scene characteristics are changing in real time.

[0024] By using real-time monitoring tools to monitor the scenarios in which the target user group is located, it is possible to determine whether there are dynamic factors interfering (such as competitors' promotional activities, the impact of sudden events on users' psychology, etc.) and to detect whether the change of key scenario features within a preset time period is greater than or equal to the feature stability threshold, thereby determining whether the scenario features have changed in real time.

[0025] In step S140, when there are no dynamic factors interfering and the scene characteristics do not change in real time, the initial customer acquisition strategy is optimized and adjusted according to the strategy response coefficient and the scene conversion judgment value to obtain the first optimized strategy.

[0026] When it is detected that there are no dynamic factors interfering with the target user group's scenario, and the change in key scenario features within a preset time period is less than the feature stability threshold, the first optimization condition for the strategy is output. Under this condition, based on the strategy response coefficient, the basic attribute data of the target user group (such as prioritizing high-end outreach channels for users with high spending power), and the scenario conversion judgment value, the outreach channels and content presentation format of the initially proposed customer acquisition strategy are adjusted to obtain the first optimized strategy.

[0027] In step S150, when there are dynamic factors interfering and the scene characteristics change in real time, the fluctuation degree of user conversion intention is calculated by the dynamic factor interference information and scene characteristic change information through the dynamic impact assessment model. The calculated fluctuation degree is corrected according to the influence relationship between the direction of dynamic factor interference and the direction of scene characteristic change on conversion intention, and the corrected conversion intention fluctuation value is obtained. Based on the corrected conversion intention fluctuation value, the strategy response coefficient and the changed scene characteristic information, the initial customer acquisition strategy is optimized and adjusted to obtain the second optimized strategy.

[0028] When dynamic factors are detected interfering with the target user group's environment, and the change in key scene features within a preset time period is greater than or equal to the feature stability threshold, the second strategy optimization condition is output. First, the intensity (quantified by the degree of influence of interfering factors on user behavior trajectories) and type (including information interference and competition interference) of the dynamic factors are detected, along with the change in key scene features. A dynamic impact assessment model is established, and the initial fluctuation value of user conversion intention is calculated using this model. Second, the influence relationship (same direction or opposite direction) between the direction of dynamic factor interference and the direction of scene feature change on conversion intention is determined. Based on this relationship, the initial fluctuation value is corrected: when it is a same direction, the magnitudes of both effects are superimposed for amplification correction; when it is an opposite direction, the larger effect is used as the basis, and the difference between the two is used for adjustment, resulting in the corrected fluctuation value of conversion intention.

[0029] Subsequently, strategy adjustment cases under dynamic interference scenarios were extracted from historical customer acquisition data. The correlation between the adjustment range of strategy discounts, the adjustment offset of reach timing, and changes in conversion effect in each case was analyzed. Based on this correlation, an adjustment range reference model was constructed. The corrected conversion intention fluctuation value, strategy response coefficient, scenario conversion judgment value, and changed scenario feature information were used as input parameters and substituted into the adjustment range reference model to determine the discount adjustment ratio and reach timing offset of the initial customer acquisition strategy. The initial customer acquisition strategy was then optimized according to the determined adjustment ratio and offset to obtain the second optimized strategy.

[0030] Specifically, real-time monitoring tools can be used to detect whether there are dynamic factors interfering with the scene in which the target user group is located, and to determine whether the change in key scene features within a preset time period is greater than or equal to the feature stability threshold. When dynamic factors are detected and the change in key scene features reaches or exceeds the threshold, the second strategy optimization condition is output.

[0031] Key scenario features are core information directly related to user behavior tendencies, such as device usage habits and operation rhythm during commuting, or the area of ​​stay and product categories of interest during shopping. For these non-numerical key scenario features, to determine whether their change within a preset time period reaches the feature stability threshold, the features must first be converted into comparable classification dimensions. For example, operation rhythm can be divided into high-frequency, medium-frequency, and low-frequency levels, and the area of ​​stay can be corresponding to core, normal, and peripheral areas. The number of changes in these levels or layers and the magnitude of cross-category switching within a preset time period are statistically analyzed and compared with the pre-set feature stability threshold. For example, if the operation rhythm level changes more than twice within one hour, or the area of ​​stay switches across one level within 30 minutes, and the actual changes meet or exceed the above standards, it can be determined that the change magnitude has reached the threshold requirement.

[0032] In step S160, the final customer acquisition strategy is determined. This strategy is based on feedback data from the trial implementation of either the first or second optimization strategy within a sample user group.

[0033] Specifically, a sample of users from the target user group (10%-20% of the total group) is selected, and either the first or second optimization strategy is implemented. Click-through rate, inquiry volume, and initial conversion rate are recorded during the trial period. Based on the trial data, a strategy effectiveness trend curve is plotted. Using curve analysis tools, the strategy adjustment dimension with the greatest improvement (corresponding to the steepest slope in the curve) and the strategy execution interval with the smallest fluctuation (corresponding to the smallest fluctuation in the curve) are identified from the trend curve. Combining the identified strategy adjustment dimension, strategy execution interval, and cost-benefit data from the trial execution process, the final customer acquisition strategy is output.

[0034] The scenario-aware customer acquisition strategy management method provided in this application achieves accurate perception of user scenario conversion potential by constructing a quantitative correlation between scenario features and conversion probability. By introducing a dynamic factor interference identification and classification optimization mechanism, it optimizes reach channels and content formats in static scenarios, and calculates conversion intention fluctuation values ​​and makes corrections based on influence relationships in dynamic interference scenarios using a dynamic impact assessment model. Furthermore, it accurately determines the adjustment parameters for discount intensity and reach timing by combining an adjustment magnitude reference model constructed from historical cases, achieving adaptive strategy optimization for complex and ever-changing scenarios. Further, through small-scale sample trial execution and strategy effect trend curve analysis, it identifies the adjustment dimensions with the most significant effect improvement and the execution interval with stable effect, and outputs the final solution based on cost-benefit data. This method effectively solves the problems of ambiguity of scenario factors, insufficient dynamic adaptability, and lack of scientific verification in customer acquisition strategies in related technologies, significantly improving the accuracy, flexibility, and economy of customer acquisition strategies.

[0035] In one specific implementation, step S110 (obtaining the scene transformation judgment value) can be achieved in the following way: First, acquire basic attribute data and behavioral data of the target user group. Basic attribute data includes, but is not limited to, age, region, and spending power level; behavioral data includes, but is not limited to, app usage records, web browsing records, and purchase records. Perform statistical analysis on the behavioral data of the target user group over different time periods to obtain initial behavioral analysis results.

[0036] Next, the behavioral trajectory data of the target user group is analyzed to identify different scenario types, such as daily commuting, leisure shopping, and work / office scenarios. The frequency of occurrence and duration of each scenario type are statistically analyzed, and a threshold for user conversion intention is set. Key scenario features that meet the threshold requirements in terms of frequency and duration are extracted from the identified scenarios.

[0037] Next, data from the historical customer acquisition strategy execution process is acquired to establish a database mapping scenario features to user conversion results. Historical scenario data matching key scenario features is extracted from the historical customer acquisition data. The conversion rate of the target user group and the total number of users in these historical scenario data are statistically analyzed to calculate the historical scenario conversion probability. The historical scenario conversion probability is then compared to the quantified values ​​of the corresponding scenario features (such as the frequency of scenario occurrence and the duration of scenario occurrence) to obtain the scenario conversion coefficient. Finally, the quantified values ​​of the key scenario features are multiplied by the scenario conversion coefficient to determine the probability that different scenarios influence the target user group to generate conversion behavior, resulting in a scenario conversion judgment value.

[0038] To facilitate understanding, the following two specific examples illustrate step S110.

[0039] Example 1: After completing a purchase in the shopping scenario, the user enters the logistics inquiry scenario.

[0040] Assume a user completes a purchase in a casual shopping scenario and then enters a logistics tracking scenario. First, we obtain the user's basic attribute data, such as age 30, location in a first-tier city, and moderate spending power. Behavioral data includes shopping records on the e-commerce app and subsequent logistics tracking records. Statistical analysis of the user's behavioral data at different time periods yields the initial behavioral analysis result: frequent logistics tracking after completing a purchase.

[0041] Scene identification is performed on behavioral trajectory data to divide it into leisure shopping scenarios and logistics query scenarios. The frequency and duration of leisure shopping scenarios and logistics query scenarios are statistically analyzed. A threshold for associating user conversion intention is set, for example, a frequency of occurrence greater than or equal to 1 time and a duration greater than or equal to 20 minutes are used as the frequency and duration requirements for key scene features. If a leisure shopping scenario meets these requirements, it is extracted as a key scene feature.

[0042] Acquire historical customer acquisition strategy execution data and establish a database corresponding to scenario characteristics and user conversion results. For example, statistically analyze the proportion of users who completed a purchase in a leisure shopping scenario and subsequently entered the logistics query scenario, and ultimately made another purchase or engaged in other conversion behaviors. Extract historical scenario data matching key scenario characteristics such as leisure shopping and logistics query scenarios from historical customer acquisition data, and statistically analyze the conversion number of the target user group and the total number of users to calculate the historical scenario conversion probability, assumed to be 60%. Ratio the historical scenario conversion probability of 60% with the quantified value of the occurrence frequency of the leisure shopping scenario (assumed to be 1 time) and the quantified value of the duration (assumed to be 3 time units) to obtain the scenario conversion coefficient 60% ÷ (1 × 3) = 0.2. Multiply the quantified value of the key scenario characteristic (assumed to be 3) by the scenario conversion coefficient 0.2 to obtain the scenario conversion judgment value of 0.6, which is used to judge the probability of users engaging in re-conversion behavior in this scenario.

[0043] Example 2: After completing a purchase in the shopping scenario, the user enters a second shopping scenario.

[0044] After completing a purchase in a casual shopping scenario, the user quickly returned to the e-commerce app's shopping page to make another purchase. Basic user attribute data was collected, assuming the user was 25 years old, located in a second-tier city, and had a relatively high spending power. Behavioral data included records of the first and subsequent purchases. Statistical analysis of behavioral data across different time periods yielded the initial behavioral analysis result: repeated shopping within a short period.

[0045] Scene identification was performed on the behavioral trajectory data, dividing it into two leisure shopping scenarios. The first shopping scenario occurred once and lasted for 40 minutes, while the second shopping scenario occurred once and lasted for 35 minutes. Under the set user conversion intention association threshold, both shopping scenarios met the requirements for key scene feature extraction.

[0046] Acquire historical customer acquisition data, establish a database mapping scenario features to conversion results, extract matching historical scenario data, count conversions and total users, and calculate the historical scenario conversion probability, assumed to be 70%. Ratio the historical scenario conversion probability of 70% to the quantified value of the corresponding scenario feature (assuming the sum of the quantified values ​​of the frequency of two shopping scenarios is 2 and the sum of the quantified values ​​of the duration is 7.5) yields a scenario conversion coefficient of approximately 70% ÷ (2 × 7.5) ≈ 0.047. Multiply the quantified value of the key scenario feature (assumed to be 15) by the scenario conversion coefficient of 0.047 to obtain a scenario conversion judgment value of approximately 0.705, used to judge the probability of user conversion behavior in this scenario.

[0047] Through the above methods, the embodiments of this application can transform abstract user scenarios into quantifiable scenario conversion judgment values, providing a precise data foundation for the subsequent optimization and adjustment of customer acquisition strategies.

[0048] In one specific implementation, step S140 (obtaining the first optimization strategy) can be achieved in the following way: First, user response data for different types of customer acquisition strategies is extracted from historical customer acquisition data. These strategies include, but are not limited to, coupon strategies, content marketing strategies, and community-based lead generation strategies. Coupon strategies involve issuing various shopping coupons to attract consumers; content marketing strategies involve attracting user attention by producing high-quality product introductions and usage guides; and community-based lead generation strategies involve guiding users to learn about products through various social communities (such as WeChat groups and QQ groups). The number of responding users and the number of users reached for each strategy are then calculated. The number of responding users refers to the number of users who actively responded to the strategy (e.g., claimed coupons, clicked content links), and the number of users reached refers to the total number of users covered by the strategy. The historical strategy response rate is calculated by dividing the number of responding users by the number of users reached.

[0049] Next, the historical strategy response rate is compared with the quantified value of the corresponding customer acquisition strategy's input cost to obtain the strategy response coefficient. The quantified input cost represents the amount of capital, human resources, and other resources consumed during strategy execution, and this strategy response coefficient reflects the strategy's response under unit cost input.

[0050] Then, real-time monitoring tools are used to monitor the scenario in which the target user group is located. If it is detected that there are no dynamic factors interfering with the scenario in which the target user group is located (such as the absence of sudden competitive promotional activities, network failures, or other situations that interfere with user behavior), and the change of key scenario features within a preset time period is less than the feature stability threshold, it means that the scenario is in a relatively stable state, and at this time, the first strategy optimization condition is output.

[0051] Finally, based on the strategy response coefficient, the basic attribute data of the target user group, and the scenario conversion judgment value, the initial customer acquisition strategy's reach channels and content presentation formats were adjusted to obtain the first optimized strategy. For example, for high-spending users, since these users have higher requirements for service quality and the high-end nature of channels, high-end reach channels (such as exclusive high-end membership apps and high-end magazine advertisements) can be prioritized, while the content presentation format should adopt more textured text or video formats that better reflect the high-end positioning.

[0052] To facilitate understanding, the following two specific examples illustrate this step.

[0053] Example 1: After completing a purchase in the shopping scenario, the user enters the logistics inquiry scenario.

[0054] Suppose that historically, when a coupon strategy was used targeting users in a logistics tracking scenario, it reached 1000 users (who were exposed to the coupon strategy on the logistics tracking page or related push notifications), and 300 of them responded (i.e., claimed the coupon). The quantified cost of the investment was 2000 (including the technical costs of coupon creation and push notifications). Then the historical strategy response rate was 300 ÷ 1000 = 30%, and the strategy response coefficient was 30% ÷ 2000 = 0.00015.

[0055] A high-spending user enters the logistics tracking scenario after completing a purchase. Real-time monitoring shows no dynamic interference in this scenario (e.g., no other merchants suddenly offer more attractive coupons on the logistics tracking page), and the changes in key scenario characteristics (such as the user's dwell time and operation frequency in the logistics tracking scenario) are less than the feature stability threshold within a preset time period, satisfying the first optimization condition. Based on the strategy response coefficient and the attributes of this high-spending user, priority is given to high-end outreach channels, such as pushing coupon information through a premium member-exclusive app. This app has a beautifully designed interface and exclusive functions, matching the identity of a high-spending user. Simultaneously, the content presentation format is adjusted, using more refined graphics and text to display the coupon usage rules, coupled with recommendations for high-end products, thus yielding the first optimization strategy.

[0056] Example 2: After completing a purchase in the shopping scenario, the user enters a second shopping scenario.

[0057] Historically, a content marketing strategy targeting repeat shoppers reached 800 users (those who encountered the content marketing through relevant pages or recommendations on repeat shopping platforms), with 240 users responding (clicking the content link and learning more about the product). The quantified cost of this strategy was 1600 (including content creation and promotion costs). Therefore, the historical strategy response rate was 240 ÷ 800 = 30%, and the strategy response coefficient was 30% ÷ 1600 = 0.0001875.

[0058] A user with moderate spending power has completed a purchase and is now entering a repurchase scenario. Real-time monitoring shows no dynamic interference in the scenario, and key scenario characteristics are stable, satisfying the first condition for strategy optimization. Based on the strategy response coefficient and the user's attributes, social media platforms are selected as the outreach channel (because social media platforms have a large user base and strong dissemination capabilities, suitable for reaching a broad range of users with moderate spending power). Marketing content is presented in a lively and engaging short video format (e.g., demonstrating product usage scenarios, sharing positive user reviews, etc.) to enhance appeal. This adjusts the initial customer acquisition strategy, resulting in the first optimized strategy.

[0059] Through the above methods, this application embodiment can quickly generate an optimized customer acquisition strategy adapted to the current scenario by combining the strategy response coefficient, user attributes, and scenario conversion judgment value under stable and interference-free conditions, thereby improving the accuracy and efficiency of strategy formulation.

[0060] Based on the above embodiments, in another embodiment provided in this application, in order to detail how to calculate the fluctuation degree of user conversion intention through a dynamic impact assessment model, and to correct the calculated fluctuation degree according to the influence relationship between the direction of dynamic factor interference and the direction of scene feature change on conversion intention, the above step S150 may specifically include the following steps: In step S151, the interference intensity and type of dynamic factors, as well as the change range of scene features, are detected.

[0061] When dynamic factors are detected interfering with the target user group's environment and key scene characteristics change in real time, the interfering factors can be quantitatively analyzed first. The intensity of interference is quantified by the degree to which these factors affect user behavior trajectories; for example, it can be measured by indicators such as the frequency of user operation interruptions and the degree of attention shift. Types of interference include information interference and competitive interference. Information interference refers to interference arising from the information itself, such as promotional content with low relevance to the current scene, irrelevant information pushed by the platform, or pop-up prompts received by users while browsing target content. This content distracts users from the target information. Competitive interference refers to interference from competitive actions by similar entities, such as promotional activities launched by competitors, more attractive product displays, or instant marketing actions initiated by similar service providers. These actions may divert potential conversions. Simultaneously, the magnitude of changes in key scene characteristics is detected, which can be characterized by the degree of change in the quantified feature values ​​over a preset time period.

[0062] In step S152, the detected interference intensity, interference type and change magnitude are used as input parameters, and a pre-built dynamic impact assessment model is invoked to calculate the initial fluctuation value of the user's conversion intention.

[0063] In this embodiment, the dynamic impact assessment model can be pre-built based on historical data to characterize the mapping relationship between interference intensity, interference type, and the magnitude of changes in scene characteristics and the degree of fluctuation in user conversion intention. The interference intensity, interference type, and the magnitude of changes in scene characteristics detected in step S151 are used as input parameters to calculate and output the initial fluctuation value of user conversion intention. This initial fluctuation value reflects the initial degree of fluctuation in user conversion intention under the combined effect of dynamic factor interference and changes in scene characteristics.

[0064] In step S153, the influence relationship between the direction of interference from dynamic factors and the direction of change in scene features on the conversion intention is determined. The influence relationship includes unidirectional influence and inverse influence.

[0065] This study examines the relationship between the direction of dynamic factor interference and the direction of scene feature changes on conversion intention. A synergistic effect means that the direction of dynamic factor interference and the direction of scene feature changes have the same impact on conversion intention. For example, if a scene feature change increases the user's attention span for a product, and the dynamic interference is a greater discount on that product, both will boost conversion intention. A synergistic effect, on the other hand, means that the two factors have opposite effects. For example, if a scene feature change increases user dwell time (increasing conversion intention), but a dynamic interference is a competitor offering a lower-priced similar product (decreasing conversion intention).

[0066] In step S154, the initial fluctuation value is corrected according to the influence relationship, and the corrected result is output as the fluctuation value of the conversion intention.

[0067] Specifically, based on the influence relationship determined in step S153, the initial fluctuation value is corrected. When the direction of dynamic factor interference and the direction of scene feature change have the same effect on conversion intention, the magnitude of the effect of dynamic factor interference on conversion intention is superimposed with the magnitude of the effect of scene feature change on conversion intention, and the initial fluctuation value is amplified and corrected. When the direction of dynamic factor interference and the direction of scene feature change have opposite effects on conversion intention, the initial fluctuation value is adjusted and corrected based on the difference between the magnitudes of the two, with the larger effect as the basis. The corrected result is used as the final conversion intention fluctuation value output for subsequent strategy optimization.

[0068] To facilitate understanding, a specific example will be used to illustrate this embodiment below.

[0069] Example: After completing a purchase in a shopping scenario, a user encounters competition interference when entering the logistics tracking scenario.

[0070] Suppose that when a user enters the logistics tracking scenario after completing a purchase, they encounter competitive interference, such as other e-commerce platforms placing more attractive advertisements near the logistics tracking page. At this point, the interference intensity is detected as moderate, the interference type as competitive interference, and the key scenario features show significant changes. These parameters are input into a pre-built dynamic impact assessment model, calculating an initial fluctuation value of 0.3 for the user's conversion intention. Further analysis of the relationship between the direction of dynamic interference and the direction of scenario feature changes on conversion intention reveals that competitive interference inhibits conversion intention, while changes in scenario features (such as increased user dwell time in the logistics tracking scenario) promote conversion intention; the two have an inverse effect, and the magnitude of the effect of scenario feature changes is greater than that of competitive interference. Therefore, the initial fluctuation value is corrected using the difference in magnitude, resulting in a corrected conversion intention fluctuation value of 0.25.

[0071] Through the above methods, the embodiments of this application can accurately quantify the comprehensive impact of dynamic factors and changes in scene characteristics on users' conversion intentions, providing an accurate decision-making basis for subsequent strategy optimization.

[0072] Based on the above embodiments, in another embodiment provided in this application, the step S154 of correcting the initial fluctuation value according to the influence relationship may specifically include: (1) When the direction of dynamic factor interference and the direction of scene feature change have the same effect on the conversion intention, the magnitude of the effect of dynamic factor interference on the conversion intention and the magnitude of the effect of scene feature change on the conversion intention are accumulated and superimposed to amplify and correct the initial fluctuation value.

[0073] This embodiment provides a correction method under the condition of unidirectional influence. Specifically, unidirectional influence means that the direction of dynamic factor interference and the direction of scene feature change have the same effect on conversion intention. For example, a change in scene feature manifests as an increase in the user's attention time to a certain product, which has a positive promoting effect on conversion intention; at the same time, dynamic interference manifests as an increase in the discount of the product, which also has a positive promoting effect on conversion intention. In this case, both effects point to an increase in conversion intention, and their magnitudes are superimposed, jointly amplifying the fluctuation of user conversion intention. The corrected fluctuation value of conversion intention can be expressed as: Corrected fluctuation value = Initial fluctuation value + Superimposed amount of unidirectional influence, where the superimposed amount of unidirectional influence is the sum of the magnitude of the effect of dynamic factor interference and the magnitude of the effect of scene feature change.

[0074] (2) When the direction of dynamic factor interference and the direction of scene feature change have a reverse effect on the conversion intention, the initial fluctuation value is adjusted to the difference between the magnitude of the effect of dynamic factor interference on the conversion intention and the magnitude of the effect of scene feature change on the conversion intention.

[0075] This embodiment provides a correction method under reverse influence. Specifically, reverse influence means that the direction of dynamic factor interference and the direction of scene feature change have opposite effects on conversion intention. For example, scene feature change manifests as an increase in user dwell time, which has a positive promoting effect on conversion intention; however, dynamic interference manifests as competitors launching similar products at lower prices, which has a negative inhibitory effect on conversion intention. In this case, the two effects cancel each other out, and the fluctuation of user conversion intention depends on the one with the larger effect. The corrected conversion intention fluctuation value can be expressed as: Corrected fluctuation value = |larger effect| - |smaller effect|, that is, taking the difference between the two effects, with the fluctuation direction consistent with the one with the larger effect.

[0076] To facilitate understanding, a specific example will be used to illustrate this embodiment below.

[0077] Example: Users encounter competitive interference in shopping scenarios.

[0078] Assuming users spend more time in a shopping scenario, this change in scenario characteristics has a positive impact of +15% on conversion intention (i.e., this contribution to the initial fluctuation value is +15%). Simultaneously, a competitor launches a more attractive promotional activity, and this dynamic factor has a negative impact of -10% on conversion intention. Since the direction of the dynamic factor interference and the direction of the scenario characteristic change have opposite effects on conversion intention, and the positive impact (+15%) is greater than the negative impact (-10%), the corrected fluctuation value of conversion intention is the difference of 5%, with a positive fluctuation direction. If the magnitude of the reverse interference exceeds the magnitude of the scenario characteristic change, for example, a positive impact of +10% and a negative impact of -15%, then the corrected fluctuation value of conversion intention is -5%, with a negative fluctuation direction.

[0079] Through the aforementioned correction methods, this application embodiment can accurately quantify the combined impact of dynamic factor interference and scene feature changes on user conversion intention. Under the same-direction influence, the fluctuation value is amplified by cumulative superposition, fully reflecting the synergistic effect of the two on enhancing conversion intention. Under the opposite-direction influence, the difference adjustment accurately reflects the mutual cancellation relationship between the two, avoiding overestimation or underestimation of conversion intention. This refined correction mechanism based on the direction of influence makes the calculation of conversion intention fluctuation value more in line with the actual scenario, providing more accurate input parameters for subsequent strategy optimization based on the adjustment amplitude reference model, thereby improving the adaptability and optimization accuracy of customer acquisition strategy in dynamic interference environments.

[0080] Based on the above embodiments, in another embodiment provided in this application, in order to describe in detail how to obtain the second optimization strategy, the above step S150 may further include the following steps: In step S155, strategy adjustment cases under dynamic interference scenarios are extracted from historical customer acquisition data, and the correlation between the adjustment range of strategy discount and the adjustment offset of the timing of the reach in each case and the change in conversion effect is obtained.

[0081] Specifically, strategy adjustment cases under dynamic interference scenarios are selected from historical customer acquisition data. For each case, the following information is extracted: the adjustment range of the strategy discount (e.g., the change in discount percentage), the adjustment offset of the outreach timing (e.g., the amount by which the outreach time is earlier or later than usual), and the corresponding changes in conversion effect (e.g., the percentage increase in conversion rate, changes in user response speed, etc.). Through statistical analysis, the correlation between the discount adjustment range and the change in conversion effect, as well as the correlation between the outreach timing adjustment offset and the change in conversion effect, can be obtained. For example, quantitative correlation patterns such as "when the discount is increased by 5%, the conversion rate increases by an average of 3%" or "when the outreach time is advanced by 1 hour, the response speed increases by an average of 20%" can be statistically derived.

[0082] In step S156, an adjustment range reference model is constructed based on the correlation.

[0083] Specifically, the implementation can construct an adjustment range reference model based on the correlation obtained in step S155. This model is used to map various parameters in the current scenario (such as conversion intention fluctuation value, strategy response coefficient, scenario conversion judgment value, and scenario feature information) to specific strategy adjustment parameters (discount adjustment ratio and reach timing offset). In the model construction process, firstly, the numerical range of the conversion intention fluctuation value can be determined, and a mapping relationship can be established between this numerical range and the basic adjustment range of the discount, forming a first correlation rule; secondly, the numerical range of the strategy response coefficient can be determined, and a mapping relationship can be established between this numerical range and the adjustment range correction coefficient, forming a second correlation rule; then, corresponding weight values ​​can be configured for the feature information of different scenario types, forming a third correlation rule; finally, based on the above three correlation rules, an adjustment range reference model is constructed with the conversion intention fluctuation value, strategy response coefficient, and scenario feature information as inputs, and the discount adjustment ratio and reach timing offset as outputs.

[0084] In step S157, the corrected conversion intention fluctuation value, strategy response coefficient, scenario conversion judgment value, and changed scenario feature information are used as inputs to the adjustment range reference model to determine the adjustment ratio of the initial customer acquisition strategy's discount and the offset of the reach timing.

[0085] The embodiment can use the corrected conversion intention fluctuation value obtained in step S154, the strategy response coefficient obtained in step S120, the scenario conversion judgment value obtained in step S110, and the currently changed scenario feature information as input parameters for the adjustment magnitude reference model. Based on pre-built mapping rules and weight configurations, the model automatically calculates the discount adjustment ratio and reach timing offset matching the current scenario. For example, the model can output specific adjustment parameters such as "discount increase by 12%" and "reach timing advanced by 30 minutes".

[0086] In step S158, the initial customer acquisition strategy is optimized according to the determined discount adjustment ratio and the timing offset to obtain the second optimized strategy.

[0087] Specifically, the discount adjustment ratio and reach timing offset determined in step S157 can be applied to the initial customer acquisition strategy. For example, if the discount in the initial strategy is "10 off for every 100 spent," and the determined adjustment ratio is an increase of 50%, then the discount will be optimized to "15 off for every 100 spent." If the initial reach timing is 30 minutes after the user browses the product, and the determined offset is 20 minutes earlier, then the reach timing will be adjusted to 10 minutes after browsing the product. Simultaneously, the corresponding strategy details are matched with the changed scenario feature information. For example, if the scenario features indicate that the user is currently commuting, then the graphic promotion format in the initial strategy will be replaced with short copy adapted for mobile devices, forming the final second optimization strategy.

[0088] To facilitate understanding, a specific example will be used to illustrate this embodiment below.

[0089] Example: Strategies are adjusted after a user encounters competition interference in a logistics query scenario.

[0090] Suppose that a user encounters competitive interference when entering the logistics tracking scenario after completing a purchase (e.g., a competitor displays a more attractive advertisement on the logistics tracking page). After correction in step S154, the conversion intention fluctuation value is 0.25, the strategy response coefficient is 0.00015, the scenario conversion judgment value is 0.6, and the changed scenario feature information shows that the user is in the logistics tracking scenario and the dwell time has increased.

[0091] By extracting strategy adjustment cases under similar competitive interference scenarios from historical customer acquisition data, analysis revealed that when competitive interference was moderate, a 15% increase in discount and a 2-hour advance in the timing of outreach significantly improved conversion rates. Based on this, a reference model for adjustment magnitude was constructed. The above parameters were input into the model, determining the initial customer acquisition strategy's discount adjustment ratio to be 15% and the outreach timing offset to be 2 hours earlier. The initial strategy was then optimized according to this adjustment ratio and offset to obtain the second optimized strategy.

[0092] Through the above methods, this application embodiment constructs an adjustment range reference model based on historical cases, transforming historical experience under dynamic interference scenarios into quantifiable decision-making basis. This model can accurately determine the adjustment ratio of discounts and the offset of reach timing based on the corrected conversion intention fluctuation value, strategy response coefficient, scenario conversion judgment value, and changed scenario characteristic information, achieving automated decision-making for strategy adjustment parameters. Compared to related technologies that rely on manual experience for strategy adjustment, this embodiment significantly improves the scientific nature and efficiency of strategy optimization, ensuring the rapid generation of optimized strategies highly adapted to the current scenario under dynamic interference environments. This effectively addresses complex situations such as market competition and information interference, improving the flexibility and effectiveness of customer acquisition strategies.

[0093] Based on the above embodiments, in another embodiment provided in this application, the above-mentioned construction of the adjustment range reference model can be implemented in the following way: (1) Determine the numerical range of the fluctuation value of conversion intention, and establish a mapping relationship between the numerical range and the basic adjustment range of the preferential intensity as the first association rule.

[0094] Specifically, firstly, a reasonable range for the fluctuation of conversion intention can be determined through historical data statistics, for example, set as [-0.5, 0.5], where negative numbers represent a decrease in user conversion intention and positive numbers represent an increase in user conversion intention. Then, this range is precisely mapped to the basic adjustment range of the discount: when the fluctuation value of conversion intention is -0.5 (i.e., intention drops significantly), the corresponding basic adjustment range for the discount is "+15% to +20%" (i.e., the discount needs to be significantly increased to win back users); when the fluctuation value is 0 (intention is stable), the basic adjustment range is "0% to +5%"; when the fluctuation value reaches 0.5 (intention rises significantly), the basic adjustment range can be set to "-5% ​​to 0%" (i.e., the discount can be appropriately reduced). Through this mapping relationship, a direct link is achieved between "changes in conversion intention" and "adjustments to discount."

[0095] (2) Determine the numerical range of the strategy response coefficient and establish a mapping relationship between the numerical range and the adjustment magnitude correction coefficient as the second association rule.

[0096] Determine the numerical range of the strategy response coefficient and establish a mapping relationship between this numerical range and the adjustment magnitude correction coefficient, which serves as the second association rule.

[0097] Specifically, the strategy response coefficient reflects the responsiveness of a strategy per unit cost input, and its calculation formula can be "historical response rate ÷ historical input cost". The numerical range of the strategy response coefficient is determined through historical data statistics, for example, set to [0.2, 1.2]. A mapping relationship is established between this range and the adjustment magnitude correction coefficient: when the strategy response coefficient is 0.2 (i.e., low historical response rate, high input cost), the correction coefficient is 1.2 to amplify the discount adjustment magnitude; when the coefficient is 0.8 (moderate historical effect), the correction coefficient is 1.0 to maintain the basic adjustment magnitude; when the coefficient reaches 1.2 (high historical response rate, low cost), the correction coefficient is 0.8 to reduce the adjustment magnitude. Through this mapping relationship, dynamic calibration of the basic discount intensity is achieved.

[0098] (3) Configure corresponding weight values ​​for feature information of different scene types as the third association rule.

[0099] Specifically, user behavior and attention distribution differ across scenarios, requiring the matching of appropriate weight values ​​for each scenario type to adjust the model output. For example, in a "commuting scenario," users' attention is relatively scattered, and their sensitivity to marketing information is low; therefore, a weight of 1.1 can be set, with the adjustment range appropriately increased to ensure the strategy's effectiveness. In a "shopping scenario," users have a strong willingness to consume and a high acceptance of marketing information; a weight of 0.9 can be set, with the adjustment range appropriately decreased to avoid over-marketing. By configuring scenario weights, the model can adapt to the actual characteristics of different scenarios.

[0100] (4) Based on the first association rule, the second association rule and the third association rule, construct an adjustment range reference model with the conversion intention fluctuation value, strategy response coefficient and scenario feature information as inputs, and the discount adjustment ratio and the timing offset as outputs.

[0101] Based on the first association rule, the second association rule, and the third association rule, an adjustment range reference model is constructed, which takes the conversion intention fluctuation value, strategy response coefficient, and scenario feature information as inputs and the discount adjustment ratio and the timing offset as outputs.

[0102] Specifically, the model's calculation logic is as follows: First, it matches the basic discount range corresponding to the conversion intention fluctuation value based on the first association rule; then, based on the second association rule, it calibrates this basic range using the correction coefficient corresponding to the strategy response coefficient; next, based on the third association rule, it corrects the calibrated adjustment range using the weight value corresponding to the scene feature information; finally, it determines the reach timing offset by combining information such as the scene's active time period. The model ultimately outputs the discount adjustment ratio and the reach timing offset, and can also incorporate historical case conversion effect thresholds to verify the output results, ensuring that the adjustment range is within a reasonable and effective range.

[0103] To facilitate understanding, a specific example will be used to illustrate this embodiment below.

[0104] Example: Calculation of strategy adjustment parameters in commuting scenarios.

[0105] Assuming a user is in a commuting scenario, their corrected conversion intention fluctuation value is -0.3 (indicating a decrease in intention), the strategy response coefficient is 0.3 (indicating a low historical response rate), and the scenario weight is 1.1 (the adjustment range needs to be increased for commuting scenarios).

[0106] First, according to the first association rule, the basic discount range corresponding to a conversion intention fluctuation value of -0.3 is "+10% to +15%", taking the midpoint +12.5%. Second, according to the second association rule, the correction coefficient corresponding to a strategy response coefficient of 0.3 is 1.2, multiplying the basic adjustment range +12.5% ​​by 1.2, we get +15%. Third, according to the third association rule, multiplying by the scenario weight of 1.1, we finally obtain a discount adjustment ratio of 16.5%. At the same time, based on the active time period of commuting scenarios (such as 7-9 am), the reach timing is adjusted from "random time period" to "8 am", determining the reach timing offset.

[0107] Through the above methods, this application constructs a hierarchical and quantifiable adjustment range reference model. This model maps the transformation of willingness fluctuation values ​​to a basic adjustment range for discount intensity, transforms the strategy response coefficient into a dynamic correction coefficient for the adjustment range, and configures differentiated weight values ​​for different scenario characteristics, achieving collaborative decision-making across multiple dimensions. Compared to traditional methods relying on manual experience for strategy adjustment, this model can establish accurate quantitative mapping relationships based on historical data, transforming abstract concepts such as "willingness fluctuation," "strategy effect," and "scenario characteristics" into specific "discount intensity adjustment ratios" and "reach timing offsets." This enables the scientific and automated generation of strategy adjustment parameters, significantly improving the accuracy and efficiency of strategy optimization in dynamic interference scenarios.

[0108] Based on the above embodiments, in another embodiment provided in this application, step S160 may specifically include the following steps: In step S161, sample users from the target user group are selected, and the first optimization strategy or the second optimization strategy is executed respectively, and user interaction data is collected during the trial execution period.

[0109] Specifically, after obtaining the first optimization strategy (for stable scenarios) or the second optimization strategy (for dynamic interference scenarios), the strategy is not immediately rolled out on a large scale, but rather piloted on a small scale. A sample of users from the target user group is selected, with the sample size ranging from 10% to 20% of the total group, to ensure the statistical representativeness of the pilot results. The first or second optimization strategy is applied to the selected sample users, and user interaction data is collected during the pilot period. User interaction data includes, but is not limited to, metrics reflecting the effectiveness of the strategy, such as click-through rate, number of inquiries, initial conversion rate, page dwell time, and coupon redemption rate.

[0110] In step S162, a trend curve of the strategy effect is plotted based on the collected user interaction data.

[0111] The example demonstrates how time-series analysis of collected user interaction data can be performed to plot a strategy effectiveness trend curve with time on the horizontal axis and strategy effectiveness metrics (such as conversion rate) on the vertical axis. This curve visually reflects the dynamic changes in strategy effectiveness over time during the trial execution period, including different stages such as the effectiveness growth period, the stable period, and the fluctuation period.

[0112] In step S163, the strategy adjustment dimension with the largest improvement in effect and the strategy execution interval with the smallest fluctuation in effect are identified from the strategy effect trend curve.

[0113] Specifically, curve analysis tools can be used to quantitatively analyze the trend curve of strategy effectiveness. Identify the segment with the steepest slope in the curve; this segment corresponds to the strategy adjustment dimension with the greatest improvement in effectiveness. In other words, the improvement in strategy effectiveness is most significant within this time period, indicating that this adjustment dimension (such as optimizing reach channels, adjusting content presentation, adjusting discounts, or adjusting reach timing) has the most positive contribution to customer acquisition. Simultaneously, identify the segment with the smallest fluctuation in the curve; this segment corresponds to the strategy execution interval with stable effectiveness. In other words, the strategy effectiveness remains stable with minimal fluctuation within this execution interval, indicating that the strategy parameter settings within this execution interval have good stability and reliability.

[0114] In step S164, the final customer acquisition strategy is output by combining the identified strategy adjustment dimensions, strategy execution intervals, and cost-benefit data during the trial execution process.

[0115] Specifically, the strategy adjustment dimension with the most significant effect improvement identified in step S163 can be used as the key direction for strategy optimization, and the strategy execution range with stable effect can be used as the reference range for strategy parameters. Simultaneously, a comprehensive evaluation is conducted by combining cost-benefit data recorded during trial execution (such as marketing investment costs, user acquisition costs, conversion revenue, etc.). The strategy parameters within the stable effect range are selected for the dimension with significant effect improvement and optimal cost-benefit ratio to form the final customer acquisition strategy plan. This plan ensures both the significance and stability of the strategy's effect while also considering the economic efficiency of marketing investment.

[0116] To facilitate understanding, a specific example will be used to illustrate this embodiment below.

[0117] Example: Trial execution of optimization strategies and final solution determination in logistics query scenarios.

[0118] Assuming users encounter competition interference in logistics tracking scenarios, a second optimization strategy was generated (15% increase in discounts and 2-hour earlier delivery time). This strategy was implemented on a sample of 15% of the target user group for a 7-day trial period. Click-through rate, inquiry volume, and conversion rate data were collected during the trial period, and a trend curve of the strategy's effectiveness was plotted.

[0119] Curve analysis revealed that the curve slope was steepest from day 3 to day 5 of the trial run, indicating that the adjustment of the discount level had the most significant effect during this period. From day 2 to day 6, the curve fluctuation was minimal, suggesting that the strategy's effectiveness was relatively stable within the range of 1.5 to 2.5 hours earlier in reaching the target audience. Combining cost-benefit data from the trial run, the optimal cost-benefit ratio was found when the discount level was increased by 15% and the reach was advanced by 2 hours. Therefore, the final customer acquisition strategy is: a 15% increase in discount level and a 2-hour earlier reach, and this strategy will be applied to all target user groups.

[0120] Through the above methods, this application establishes a scientific verification closed loop of "small-scale trial execution - effect trend analysis - optimal solution determination". This verification mechanism avoids the resource waste and risks that may result from blindly promoting a strategy on a large scale by selecting representative samples for strategy trial execution; by plotting the strategy effect trend curve and identifying the segment with the largest slope and the segment with the smallest fluctuation, it accurately locates the adjustment dimension with the most significant effect improvement and the execution interval with the most stable effect; and by combining cost-benefit data for comprehensive evaluation, it ensures that the final output strategy solution achieves an optimal balance between effect and cost. This verification process fills the gap in traditional customer acquisition strategies that lack a scientific effect verification and optimization closed loop, providing reliable effect verification and decision-making basis for the practical application of customer acquisition strategies, and significantly improving the practicality and economy of customer acquisition strategies.

[0121] By dividing each functional module according to its corresponding functions, this application provides a scene-aware customer acquisition strategy management device, which can be a server, a terminal, or a chip applied to a server. Figure 2 This is a schematic block diagram of the functional modules of a scene-aware customer acquisition strategy management device provided for an exemplary embodiment of this application. Figure 2 As shown, the scene-aware customer acquisition strategy management device includes: The data acquisition module 21 is used to acquire multi-dimensional data of the target user group, identify the scene features that affect the user's conversion intention based on the multi-dimensional data, and establish a quantitative correlation between scene features and conversion probability based on historical customer acquisition data to obtain a scene conversion judgment value that represents the conversion possibility in the current scene. The coefficient acquisition module 22 is used to obtain the quantitative relationship between different customer acquisition strategies and user responses in historical customer acquisition data, and to obtain the strategy response coefficient. Judgment module 23 is used to determine whether there are dynamic factors interfering with the scene where the target user group is located and whether the scene characteristics have changed in real time. The first optimization strategy acquisition module 24 is used to optimize and adjust the initial customer acquisition strategy based on the strategy response coefficient and the scenario conversion judgment value when there is no dynamic interference and the scenario characteristics do not change in real time, so as to obtain the first optimization strategy. The second optimization strategy acquisition module 25 is used to calculate the fluctuation degree of user conversion intention based on dynamic factor interference information and scene feature change information when there is dynamic factor interference and scene feature change information, and to correct the calculated fluctuation degree according to the influence relationship between the direction of dynamic factor interference and the direction of scene feature change on conversion intention, so as to obtain the corrected conversion intention fluctuation value. Based on the corrected conversion intention fluctuation value, strategy response coefficient and changed scene feature information, the initial customer acquisition strategy is optimized and adjusted to obtain the second optimization strategy. The strategy determination module 26 is used to determine the final customer acquisition strategy to be executed; wherein the customer acquisition strategy is determined based on the trial execution feedback data of the first optimization strategy or the second optimization strategy in the sample user group.

[0122] In another embodiment provided in this application, the second optimization strategy acquisition module 25 is specifically used for: Detect the intensity and type of interference from dynamic factors, as well as the magnitude of changes in scene characteristics; Using the detected interference intensity, type, and magnitude of change as input parameters, a pre-built dynamic impact assessment model is invoked to calculate the initial fluctuation value of user conversion intention. Determine the relationship between the direction of interference from dynamic factors and the direction of change in scene characteristics on conversion intention. The relationship includes both unidirectional and inverse influences. The initial fluctuation value is corrected based on the influence relationship, and the corrected result is output as the fluctuation value of the conversion intention.

[0123] In another embodiment provided in this application, the second optimization strategy acquisition module 25 is specifically used for: When the direction of dynamic factor interference and the direction of scene feature change have the same effect on conversion intention, the magnitude of the effect of dynamic factor interference on conversion intention and the magnitude of the effect of scene feature change on conversion intention are accumulated and superimposed to amplify and correct the initial fluctuation value. When the direction of dynamic factor interference and the direction of scene feature change have an inverse effect on conversion intention, the initial fluctuation value is adjusted to the difference between the magnitude of the effect of dynamic factor interference on conversion intention and the magnitude of the effect of scene feature change on conversion intention.

[0124] In another embodiment provided in this application, the second optimization strategy acquisition module 25 is specifically used for: Extract strategy adjustment cases under dynamic interference scenarios from historical customer acquisition data, and obtain the correlation between the adjustment range of strategy discount and the adjustment offset of the timing of the reach in each case and the change in conversion effect; Construct an adjustment range reference model based on the correlation relationships; The corrected conversion intention fluctuation value, strategy response coefficient, scenario conversion judgment value, and changed scenario feature information are used as inputs to the adjustment range reference model to determine the adjustment ratio of the initial customer acquisition strategy's discount and the offset of the reach timing. The initial customer acquisition strategy was optimized by adjusting the determined discount rate and the timing of the outreach, resulting in a second optimized strategy.

[0125] In another embodiment provided in this application, the second optimization strategy acquisition module 25 is specifically used for: Determine the numerical range of the fluctuation value of conversion intention, and establish a mapping relationship between the numerical range and the basic adjustment range of the discount intensity, as the first association rule; Determine the numerical range of the strategy response coefficient and establish a mapping relationship between the numerical range and the adjustment magnitude correction coefficient, as the second association rule; Configure corresponding weight values ​​for feature information of different scene types, as the third association rule; Based on the first association rule, the second association rule, and the third association rule, an adjustment range reference model is constructed, which takes the conversion intention fluctuation value, strategy response coefficient, and scenario feature information as inputs and the discount adjustment ratio and the timing offset as outputs.

[0126] In another embodiment provided in this application, the strategy determination module 26 is specifically used for: Select sample users from the target user group, execute the first optimization strategy or the second optimization strategy respectively, and collect user interaction data during the trial execution period; Draw a trend curve of strategy effectiveness based on the collected user interaction data; Identify the strategy adjustment dimension with the greatest improvement in effect and the strategy execution interval with the smallest fluctuation in effect from the strategy effect trend curve; By combining the identified strategy adjustment dimensions, strategy execution intervals, and cost-benefit data during the trial execution process, the final customer acquisition strategy solution is output.

[0127] The scenario-aware customer acquisition strategy management device provided in this application achieves accurate perception of user scenario conversion potential by constructing a quantitative correlation between scenario features and conversion probability. By introducing a dynamic factor interference identification and classification optimization mechanism, it optimizes reach channels and content formats in static scenarios, and calculates conversion intention fluctuation values ​​and makes corrections based on influence relationships in dynamic interference scenarios using a dynamic impact assessment model. Furthermore, it accurately determines the adjustment parameters for discount intensity and reach timing by combining an adjustment magnitude reference model constructed from historical cases, achieving adaptive strategy optimization for complex and ever-changing scenarios. Further, through small-scale sample trial execution and strategy effect trend curve analysis, it identifies the adjustment dimensions with the most significant effect improvement and the execution interval with stable effect, and outputs the final solution based on cost-benefit data. This method effectively solves the problems of ambiguity of scenario factors, insufficient dynamic adaptability, and lack of scientific verification in customer acquisition strategies in related technologies, significantly improving the accuracy, flexibility, and economy of customer acquisition strategies.

[0128] This application also provides an electronic device, including: at least one processor; a memory for storing executable instructions of the at least one processor; wherein the at least one processor is configured to execute the instructions to implement the method disclosed in the embodiments of this application.

[0129] Figure 3 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application. For example... Figure 3 As shown, the electronic device 1800 includes at least one processor 1801 and a memory 1802 coupled to the processor 1801. The processor 1801 can perform the corresponding steps in the methods disclosed in the embodiments of this application.

[0130] The processor 1801 described above can also be called a central processing unit (CPU), which can be an integrated circuit chip with signal processing capabilities. Each step in the method disclosed in this application can be implemented by the integrated logic circuitry in the hardware of the processor 1801 or by instructions in software form. The processor 1801 can be a general-purpose processor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this application can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can be located in the memory 1802, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor 1801 reads information from the memory 1802 and, in conjunction with its hardware, completes the steps of the above method.

[0131] Furthermore, the various operations / processes according to this application, when implemented via software and / or firmware, can be transmitted from a storage medium or network to a computer system with a dedicated hardware architecture, such as... Figure 4 The computer system 1900 shown is equipped with the programs that constitute the software. When various programs are installed, the computer system is able to perform various functions, including those described above. Figure 4 A structural block diagram of a computer system provided for an exemplary embodiment of this application.

[0132] Computer System 1900 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0133] like Figure 4As shown, the computer system 1900 includes a computing unit 1901, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 1902 or a computer program loaded from a storage unit 1908 into a random access memory (RAM) 1903. The RAM 1903 may also store various programs and data required for the operation of the computer system 1900. The computing unit 1901, ROM 1902, and RAM 1903 are interconnected via a bus 1904. An input / output (I / O) interface 1905 is also connected to the bus 1904.

[0134] Multiple components in computer system 1900 are connected to I / O interface 1905, including: input unit 1906, output unit 1907, storage unit 1908, and communication unit 1909. Input unit 1906 can be any type of device capable of inputting information into computer system 1900. Input unit 1906 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of the electronic device. Output unit 1907 can be any type of device capable of presenting information and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1908 may include, but is not limited to, hard disks and optical disks. Communication unit 1909 allows computer system 1900 to exchange information / data with other devices via a network such as the Internet, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0135] The computing unit 1901 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1901 performs the various methods and processes described above. For example, in some embodiments, the methods disclosed in the embodiments of this application can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 1908. In some embodiments, part or all of the computer program can be loaded and / or installed on an electronic device via ROM 1902 and / or communication unit 1909. In some embodiments, the computing unit 1901 can be configured to perform the methods disclosed in the embodiments of this application by any other suitable means (e.g., by means of firmware).

[0136] This application also provides a computer-readable storage medium, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to perform the methods disclosed in this application.

[0137] The computer-readable storage medium in this application embodiment may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The aforementioned computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specifically, the aforementioned computer-readable storage medium may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.

[0138] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0139] This application also provides a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the methods disclosed in the embodiments of this application.

[0140] In embodiments of this application, computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer.

[0141] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0142] The modules, components, or units described in the embodiments of this application can be implemented in software or hardware. The names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.

[0143] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0144] The above description is merely an embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

[0145] While specific embodiments of this application have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and are not intended to limit the scope of this application. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this application. The scope of this application is defined by the appended claims.

Claims

1. A customer acquisition strategy management method based on scene awareness, characterized in that, The method includes: Acquire multi-dimensional data of the target user group, identify scenario features that affect users' willingness to convert based on the multi-dimensional data, and establish a quantitative correlation between scenario features and conversion probability based on historical customer acquisition data to obtain a scenario conversion judgment value used to characterize the conversion possibility in the current scenario. Quantitatively determine the relationship between different customer acquisition strategies and user responses in historical customer acquisition data to obtain the strategy response coefficient; Determine whether there are dynamic factors interfering with the scene in which the target user group is located, and whether the scene characteristics are changing in real time; When there are no dynamic factors interfering and the scene characteristics do not change in real time, the initial customer acquisition strategy is optimized and adjusted according to the strategy response coefficient and the scene conversion judgment value to obtain the first optimized strategy; When dynamic factors interfere and scene characteristics change in real time, the fluctuation of user conversion intention is calculated by a dynamic impact assessment model based on the dynamic factor interference information and scene characteristic change information. The calculated fluctuation is then corrected according to the influence relationship between the direction of dynamic factor interference and the direction of scene characteristic change on conversion intention, resulting in a corrected conversion intention fluctuation value. Based on the corrected conversion intention fluctuation value, the strategy response coefficient, and the changed scene characteristic information, the initial customer acquisition strategy is optimized and adjusted to obtain a second optimized strategy. The final customer acquisition strategy is determined; wherein the customer acquisition strategy is determined based on the trial execution feedback data of the first optimization strategy or the second optimization strategy in the sample user group.

2. The method of claim 1, wherein, The process of calculating the fluctuation level of user conversion intention using a dynamic impact assessment model, and correcting the calculated fluctuation level based on the influence relationship between the direction of dynamic factor interference and the direction of scene feature changes on conversion intention, includes: Detect the intensity and type of interference from dynamic factors, as well as the magnitude of changes in scene characteristics; Using the detected interference intensity, type, and magnitude of change as input parameters, a pre-built dynamic impact assessment model is invoked to calculate the initial fluctuation value of user conversion intention. Determine the relationship between the direction of interference from dynamic factors and the direction of change in scene features on conversion intention, wherein the relationship includes both unidirectional and inverse influences; The initial fluctuation value is corrected according to the influence relationship, and the corrected result is output as the fluctuation value of the conversion intention.

3. The method of claim 2, wherein, The step of correcting the initial fluctuation value according to the influence relationship includes: When the direction of dynamic factor interference and the direction of scene feature change have the same effect on conversion intention, the magnitude of the effect of dynamic factor interference on conversion intention and the magnitude of the effect of scene feature change on conversion intention are accumulated and superimposed to amplify and correct the initial fluctuation value. When the direction of dynamic factor interference and the direction of scene feature change have an inverse effect on conversion intention, the initial fluctuation value is adjusted to the difference between the magnitude of the effect of dynamic factor interference on conversion intention and the magnitude of the effect of scene feature change on conversion intention.

4. The method of claim 3, wherein, The obtained second optimization strategy includes: Extract strategy adjustment cases under dynamic interference scenarios from historical customer acquisition data, and obtain the correlation between the adjustment range of strategy discount and the adjustment offset of the timing of the reach in each case and the change in conversion effect; Construct an adjustment range reference model based on the aforementioned correlation; The corrected conversion intention fluctuation value, the strategy response coefficient, the scenario conversion judgment value, and the changed scenario feature information are used as inputs to the adjustment range reference model to determine the discount adjustment ratio and the timing offset of the initial customer acquisition strategy. The initial customer acquisition strategy was optimized by adjusting the determined discount rate and the timing of the outreach, resulting in a second optimized strategy.

5. The method of claim 4, wherein, The construction of the adjustment range reference model includes: Determine the numerical range of the conversion intention fluctuation value, and establish a mapping relationship between the numerical range and the basic adjustment range of the discount intensity as the first association rule; Determine the numerical range of the strategy response coefficient, and establish a mapping relationship between the numerical range and the correction coefficient of the adjustment range as the second association rule; Configure corresponding weight values ​​for feature information of different scene types, as the third association rule; Based on the first association rule, the second association rule, and the third association rule, an adjustment range reference model is constructed, which takes the conversion intention fluctuation value, strategy response coefficient, and scenario feature information as inputs and the discount adjustment ratio and the timing offset as outputs.

6. The method of claim 1, wherein, The process of determining the final customer acquisition strategy includes: Select sample users from the target user group, execute the first optimization strategy or the second optimization strategy respectively, and collect user interaction data during the trial execution period; Draw a trend curve of strategy effectiveness based on the collected user interaction data; Identify the strategy adjustment dimension with the greatest improvement in effect and the strategy execution interval with the smallest fluctuation in effect from the strategy effect trend curve; By combining the identified strategy adjustment dimensions, strategy execution intervals, and cost-benefit data during the trial execution process, the final customer acquisition strategy solution is output. 7.A scenario-aware customer acquisition strategy management apparatus, characterized in that, The device includes: The data acquisition module is used to acquire multi-dimensional data of the target user group, identify the scene features that affect the user's conversion intention based on the multi-dimensional data, and establish a quantitative correlation between scene features and conversion probability based on historical customer acquisition data to obtain a scene conversion judgment value that represents the conversion possibility in the current scene. The coefficient acquisition module is used to obtain the quantitative relationship between different customer acquisition strategies and user responses in historical customer acquisition data, and to obtain the strategy response coefficient. The judgment module is used to determine whether there are dynamic factors interfering with the scene in which the target user group is located and whether the scene characteristics are changing in real time. The first optimization strategy acquisition module is used to optimize and adjust the initial customer acquisition strategy based on the strategy response coefficient and the scenario conversion judgment value when there are no dynamic factors interfering and the scenario characteristics do not change in real time, so as to obtain the first optimization strategy. The second optimization strategy acquisition module is used to calculate the fluctuation degree of user conversion intention based on dynamic factor interference information and scene feature change information when there is dynamic factor interference and scene feature change information, through a dynamic impact assessment model, and correct the calculated fluctuation degree according to the influence relationship between the direction of dynamic factor interference and the direction of scene feature change on conversion intention to obtain a corrected conversion intention fluctuation value. Based on the corrected conversion intention fluctuation value, the strategy response coefficient and the changed scene feature information, the initial customer acquisition strategy is optimized and adjusted to obtain the second optimization strategy. The strategy determination module is used to determine the final customer acquisition strategy to be executed; wherein the customer acquisition strategy is determined based on the trial execution feedback data of the first optimization strategy or the second optimization strategy in the sample user group.

8. An electronic device, comprising: include: At least one processor; Memory for storing the at least one processor-executable instruction; The at least one processor is configured to execute the instructions to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the method as described in any one of claims 1-6.

10. A computer program product, characterised in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images