A service operation strategy determination method, device, equipment and storage medium

Abstract

This application discloses a method, apparatus, device, and storage medium for determining business operation strategies, including: acquiring business requirement parameters and business constraint parameters of a target business; matching the business requirement parameters with multiple operation strategies in a preset platform strategy library; determining candidate operation strategies based on the matching results; adjusting the first strategy parameters of the candidate operation strategies based on the business constraint parameters to obtain an optimized strategy; deploying the optimized strategy; and monitoring user behavior funnel data corresponding to the optimized strategy; performing effect analysis on the user behavior funnel data; and adjusting the second strategy parameters of the optimized strategy based on the analysis results to obtain the target operation strategy for the target business. This significantly improves the matching accuracy between operation strategies and business objectives, reduces resource waste, enables automated strategy iteration and continuous effect optimization, and effectively improves strategy optimization efficiency.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device and storage medium for determining business operation strategies. Background Technology

[0002] In scenarios such as game operation and internet business operation, in order to improve user acquisition, retention and conversion, platforms usually need to formulate corresponding operation strategies for different business types, different operation stages and different user groups.

[0003] In related technologies, when determining business operation strategies, the platform's strategy library is usually simply matched with the operation strategies by business type, operation stage and user group. After the matched target operation strategy is launched, it is monitored only based on the overall launch effect. Operation strategies with poor launch effect are replaced or the strategy parameters are manually modified. This leads to problems such as poor adaptability between the target operation strategy and the actual business goal, low strategy optimization efficiency and poor business conversion effect. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for determining business operation strategies, solving problems such as poor adaptability between target operation strategies and actual business objectives, low strategy optimization efficiency, and poor optimization results during the determination of business operation strategies. It can determine candidate strategies by matching business needs with a strategy library, adjust and optimize parameters based on business constraints, and further refine the strategy based on user behavior funnel data. This significantly improves the matching accuracy between operation strategies and business objectives, reduces resource waste, enables automated strategy iteration and continuous optimization, and effectively improves strategy optimization efficiency.

[0005] In a first aspect, embodiments of this application provide a method for determining a business operation strategy, including: Obtain the business requirement parameters and business constraint parameters of the target business, match the business requirement parameters with multiple operation strategies in the preset platform strategy library, and determine the candidate operation strategies based on the matching results; Based on the business constraint parameters, the candidate operation strategies are adjusted by first strategy parameters to obtain optimized strategies, and the optimized strategies are deployed, while monitoring the user behavior funnel data corresponding to the optimized strategies. The user behavior funnel data is analyzed for effectiveness, and the second strategy parameter is adjusted according to the analysis results to obtain the target operation strategy for the target business.

[0006] Optionally, the step of matching the business requirement parameters with multiple operational strategies in a preset platform strategy library, and determining candidate operational strategies based on the matching results, includes: Conflict detection is performed on the business constraint parameters and each operational strategy in the preset platform strategy library, and conflict and non-conflict conditions in each operational strategy are determined based on the detection results. Calculate the first matching score corresponding to the conflict condition, and perform a weighted calculation on the first matching score and the second matching score corresponding to the non-conflict condition to obtain the constraint matching score of the candidate operation strategy. The operation strategy with the constraint matching score greater than the preset score threshold is determined as the candidate operation strategy, and the second matching score is the preset score value.

[0007] Optionally, adjusting the first strategy parameter of the candidate operation strategy based on the business constraint parameters includes: The type of conflict condition in the candidate operation strategy is determined according to the preset priority division rule. If the type of conflict condition is a high-priority conflict condition, the high-priority conflict condition is forcibly reset based on the business constraint parameter. When the conflict condition is of medium priority, the medium priority conflict condition is subjected to interval compression processing based on the business constraint parameters. When the conflict condition is a low-priority conflict condition, the low-priority conflict condition is adapted proportionally based on the business constraint parameters.

[0008] Optionally, the effect analysis of the user behavior funnel data includes: The user behavior funnel data is broken down to obtain funnel data for multiple nodes. Nodes in each funnel data whose completion rate is less than the preset completion rate threshold of the corresponding node are identified as abnormal nodes. Calculate the ratio of the number of abnormal nodes to the preset total number of nodes. If the ratio meets the preset ratio threshold, determine the optimization strategy corresponding to the user behavior funnel data as an abnormal strategy. Accordingly, adjusting the second strategy parameters of the optimization strategy based on the analysis results includes: The second strategy parameter is adjusted for the aforementioned anomaly strategy.

[0009] Optionally, adjusting the second strategy parameters of the anomaly strategy includes: The contribution value of the abnormal node to the overall strategy effect is calculated based on the user behavior funnel data corresponding to the abnormal strategy. Abnormal nodes whose contribution value meets the preset contribution threshold are identified as high contribution nodes, and abnormal nodes whose contribution value does not meet the preset contribution threshold are identified as low contribution nodes. The high-contribution nodes are filled with missing indicators, and the low-contribution nodes are adjusted to balance parameters.

[0010] Optionally, the step of performing indicator gap filling operation on the high-contribution nodes includes: The indicator gap value is calculated based on the completion rate corresponding to the high contribution node and the preset completion rate threshold, and the adjustable parameter corresponding to the indicator gap value and the adjustment range corresponding to the adjustable parameter are determined. The adjustment range is divided into multiple intervals to obtain a stepped adjustment step size. Based on the stepped adjustment step size, the adjustable parameters of the high contribution node are adjusted step by step.

[0011] Optionally, after obtaining the target operational strategy for the target business, the method further includes: The target operation strategy is subjected to grouped comparative testing. If the completion rate in the test results meets the preset storage conditions, the target operation strategy is marked based on the business scenario type corresponding to the target operation strategy, and the marked target operation strategy is stored in the preset platform strategy library.

[0012] In a second aspect, embodiments of this application provide a business operation strategy determination apparatus, comprising: The parameter acquisition module is used to acquire the business requirement parameters and business constraint parameters of the target business. The candidate operation strategy determination module is used to match the business requirement parameters with multiple operation strategies in the preset platform strategy library, and determine the candidate operation strategy based on the matching results. The first adjustment module is used to adjust the first strategy parameters of the candidate operation strategy based on the business constraint parameters to obtain an optimized strategy. The user behavior funnel data monitoring module is used to deploy the optimization strategy and monitor the user behavior funnel data corresponding to the optimization strategy. The effect analysis module is used to perform effect analysis on the user behavior funnel data; The second adjustment module is used to adjust the second strategy parameters of the optimization strategy based on the analysis results, so as to obtain the target operation strategy of the target business.

[0013] In a third aspect, embodiments of this application provide an electronic device, the device comprising: one or more processors; and a storage device configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the business operation strategy determination method described in the first aspect.

[0014] In a fourth aspect, embodiments of this application provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the business operation strategy determination method as described in the first aspect.

[0015] This application embodiment obtains business requirement parameters and business constraint parameters of the target business, matches the business requirement parameters with multiple operational strategies in a preset platform strategy library, and determines candidate operational strategies based on the matching results. Based on the business constraint parameters, the candidate operational strategies undergo a first strategy parameter adjustment to obtain an optimized strategy, which is then deployed, and the user behavior funnel data corresponding to the optimized strategy is monitored. The user behavior funnel data is then analyzed for effectiveness, and based on the analysis results, the optimized strategy undergoes a second strategy parameter adjustment to obtain the target operational strategy for the target business. This approach, by matching business requirements with the strategy library to determine candidate strategies, adjusting and optimizing parameters based on business constraints, and further refining based on user behavior funnel data, significantly improves the matching accuracy between operational strategies and business objectives, reduces resource waste, achieves automated strategy iteration and continuous effect optimization, and effectively improves strategy optimization efficiency. Attached Figure Description

[0016] Figure 1 This is a flowchart of a business operation strategy determination method provided in an embodiment of this application; Figure 2 This is a flowchart of a method for determining candidate operating strategies provided in an embodiment of this application; Figure 3 This is a flowchart of a first strategy parameter adjustment method provided in an embodiment of this application; Figure 4 This is a flowchart of an effect analysis and second strategy parameter adjustment method provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a business operation strategy determination device provided in an embodiment of this application; Figure 6 This is a schematic diagram of a business operation strategy determination device provided in an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0018] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0019] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0020] The following description, in conjunction with the accompanying drawings, details the business operation strategy determination method, apparatus, equipment, and medium provided in this application through specific embodiments and application scenarios.

[0021] The business operation strategy determination method provided in this application is applicable to scenarios such as game business operation, e-commerce operation, and platform membership operation. Based on the above application scenarios, it can be understood that the executing entity of each step can be a computer device. This computer device refers to any electronic device with data computing, processing, and storage capabilities, such as mobile phones, PCs (Personal Computers), tablet computers, and other terminal devices, or it can be a server or other devices. This application does not limit the scope of the application.

[0022] Figure 1 This is a flowchart of a business operation strategy determination method provided in an embodiment of this application, such as... Figure 1 As shown, it includes: S101. Obtain the business requirement parameters and business constraint parameters of the target business, match the business requirement parameters with multiple operation strategies in the preset platform strategy library, and determine the candidate operation strategy based on the matching results.

[0023] Here, "target business" refers to the commercial business for which operational strategies are to be configured, such as gaming, e-commerce, and app operations. "Business requirement parameters" can refer to business objective parameters, such as user acquisition metrics, retention targets, activity formats, user groups, and expected conversion rates. "Business constraint parameters" can refer to business restriction parameters, including budget limits, channel scope, campaign periods, compliance requirements, and cost thresholds. "Preset platform strategy library" refers to a structured database used to store historically validated and reusable operational strategies in a tagged manner. "Operational strategy" refers to a complete set of user-facing operational plans, including marketing, benefits, and ad placements. "Candidate operational strategies" refers to alternative strategies that match and meet business requirements and have been initially selected for optimization.

[0024] In one embodiment, the business requirement parameters and business constraint parameters of the target business can be obtained by: collecting target business data from multiple sources such as front-end pages, business interfaces, and databases, and performing data verification, format standardization, and field splitting on the target business data, filtering out the requirement parameters and constraint parameters such as budget, compliance, and channels that represent business objectives, and uniformly encapsulating them into a set of structured fields.

[0025] In one embodiment, the business requirement parameters are matched with multiple operational strategies in a preset platform strategy library, and candidate operational strategies are determined based on the matching results. This can be done by: converting the business requirement parameters into standard feature retrieval keywords; retrieving all strategy tag data stored in the platform strategy library based on an inverted index; calculating the matching score between the standard feature retrieval keywords and the strategy tag data of each operational strategy feature using a cosine similarity algorithm; correcting the matching score according to a preset business scenario weight; and determining all strategies with matching scores exceeding a set threshold as candidate operational strategies.

[0026] Figure 2 This is a flowchart of a method for determining candidate operating strategies provided in an embodiment of this application, such as... Figure 2 As shown, it includes: S1011. Perform conflict detection on the business constraint parameters and each operational strategy in the preset platform strategy library, and determine the conflict and non-conflict conditions in each operational strategy based on the detection results.

[0027] Conflict detection refers to the process of comparing business constraint boundaries with the original configuration parameters of the strategy to verify whether the parameters exceed the constraints. Conflict conditions refer to configuration items whose operational strategy parameters exceed the constraints of budget, cost, compliance, etc., and cannot be directly implemented. Non-conflict conditions refer to configuration items whose operational strategy parameters all fall within the limits of various business constraints and meet the implementation requirements.

[0028] In one embodiment, conflict detection between business constraint parameters and operational strategies in a preset platform strategy library can be performed as follows: Extract the parameter constraint ranges corresponding to conditions such as budget cap, channel range, and discount cost; extract the configuration parameters corresponding to each operational strategy in the preset platform strategy library, where each configuration parameter includes the corresponding budget, channel, and discount cost. Match each extracted parameter constraint range with the configuration parameters corresponding to each operational strategy in the preset platform strategy library one by one. If a configuration parameter is within the corresponding parameter constraint range, the condition corresponding to that parameter constraint range is a non-conflicting condition; if a configuration parameter is not within the corresponding parameter constraint range, the condition corresponding to that parameter constraint range is a conflicting condition. For example, if the business constraint limits the single-user subsidy cost to 5 yuan, and a certain strategy sets the subsidy to 6 yuan, then this subsidy condition is determined to be a conflicting condition; the remaining conditions meet the constraint requirements and are therefore determined to be non-conflicting conditions.

[0029] S1012. Calculate the first matching degree score corresponding to the conflict condition, and perform a weighted calculation on the first matching degree score and the second matching degree score corresponding to the non-conflict condition to obtain the constraint matching degree score of the candidate operation strategy. The operation strategy with the constraint matching degree score greater than the preset score threshold is determined as the candidate operation strategy, and the second matching degree score is the preset score value.

[0030] The first matching score can refer to the matching score calculated based on the degree of parameter exceeding the limit for policy conditions with constraint conflicts. The second matching score can refer to the standard score that is pre-set and directly used for conflict-free conditions. The constraint matching score can refer to the overall matching score calculated after considering all conditions for a single policy. The preset scoring threshold can refer to the pre-defined passing score line, which serves as the criterion for selecting candidate policies.

[0031] In one embodiment, the first matching score corresponding to a conflict condition can be calculated as follows: The conflict ratio between the conflict parameter and the standard parameter corresponding to the conflict condition is calculated; the deduction value corresponding to the current conflict ratio is determined based on the mapping relationship between the conflict ratio and the deduction value; and the difference between the preset maximum score and the deduction value is calculated to obtain the first matching score. For example, if the maximum cost of a single user activity is constrained to 5 yuan, and a certain strategy is actually set to 7 yuan, the conflict ratio is 0.4. Based on the mapping relationship between the conflict ratio and the deduction value, the deduction value corresponding to the current conflict ratio is determined to be 4 points. The preset maximum score is 10 points. The difference between the preset maximum score and the deduction value is calculated to obtain a first matching score of 6 points.

[0032] In one embodiment, the weighted calculation of the first matching score and the second matching score corresponding to the non-conflict conditions can be performed as follows: after calculating the first matching score corresponding to each conflict condition in the operation strategy, the second matching score corresponding to all non-conflict conditions is counted, and the first matching score corresponding to all conflict conditions in the same operation strategy is accumulated to obtain a first accumulated result, and the second matching score corresponding to all non-conflict conditions in the operation strategy is accumulated to obtain a second accumulated result. The first accumulated result and the second accumulated result are weighted according to the pre-configured weight coefficients to obtain the constraint matching score of the operation strategy. For example, if an operational strategy includes conflict condition A, conflict condition B, non-conflict condition C, and non-conflict condition D, the first matching score for conflict condition A is 6 points, the first matching score for conflict condition B is 4 points, and the first cumulative result is 10 points. The second matching score for non-conflict condition C is 10 points, the second matching score for non-conflict condition D is 10 points, and the second cumulative result is 20 points. If the weights of the first and second scores are pre-set to be 0.4 and 0.6 respectively, the constraint matching score of the operational strategy is calculated as: 10 × 0.4 + 20 × 0.6 = 16.

[0033] In one embodiment, after calculating the constraint matching score corresponding to each operational strategy, the constraint matching score corresponding to each operational strategy is compared with a preset scoring threshold, and the operational strategy with a constraint matching score greater than or equal to the preset scoring threshold is determined as a candidate operational strategy.

[0034] The above-mentioned approach first detects conflicts between business constraint parameters and existing platform operation strategies to distinguish between conflicting and non-conflicting conditions. Based on the conflicting conditions, a first matching degree is calculated, and for the non-conflicting conditions, a preset score is used as a second matching degree, and these are weighted and fused to obtain the constraint matching degree of a single strategy. Then, candidate operation strategies are screened based on preset thresholds. This approach can accurately quantify the suitability of each operation strategy with the current business constraints, quickly eliminate strategies with serious constraint conflicts or those that do not meet the matching standards, narrow down the range of candidate strategies, reduce the computational workload of subsequent strategy selection, and improve the efficiency of operation strategy screening.

[0035] S102. Based on the business constraint parameters, adjust the first strategy parameters of the candidate operation strategy to obtain the optimized strategy, and deploy the optimized strategy, and monitor the user behavior funnel data corresponding to the optimized strategy.

[0036] The first strategy parameter adjustment refers to the initial optimization operation of modifying the configuration parameters of candidate strategies in a hierarchical manner according to conflict priority based on pre-obtained constraints. The optimized strategy refers to an operational plan that, after constraint adaptation and parameter rectification, meets business limitations and can be launched online. User behavior funnel data refers to step-by-step statistical data such as retention and completion rate recorded at each node of the entire user journey from reaching the activity, participating in the operation, to the final conversion.

[0037] In one embodiment, the method of adjusting the first strategy parameter of the candidate operation strategy based on the business constraint parameters to obtain the optimized strategy can be as follows: first, the business constraint parameters are split into multiple sets of restriction labels, and a pre-trained parametric regression model is called to traverse the configuration parameters of the candidate operation strategy. The adjustable range of parameters is determined by using various constraint thresholds as boundaries. Through model iteration and optimization, variables such as discount intensity and deployment scale are automatically fine-tuned within the adjustable range. Parameter combinations that exceed the constraint boundaries are eliminated, and finally, the strategy that meets all the constraint conditions is selected as the optimized strategy.

[0038] In one embodiment, the method of "deploying optimization strategies and monitoring user behavior funnel data corresponding to the optimization strategies" can be as follows: the optimization strategies are distributed to various business channels to complete the full-scale deployment, and user behavior logs from activity exposure, click participation to final conversion are captured in real time through the tracking and collection component. The behavior logs are then cleaned, summarized, and aggregated, and classified and statistically analyzed according to each node of the funnel to form standardized user behavior funnel data.

[0039] Figure 3 This is a flowchart of a first strategy parameter adjustment method provided in an embodiment of this application, such as... Figure 3 As shown, it includes: S1021. Determine the type of conflicting conditions in the candidate operation strategy according to the preset priority division rules. If the type of conflicting condition is a high-priority conflicting condition, perform forced repositioning processing on the high-priority conflicting condition based on the business constraint parameters.

[0040] The preset priority classification rules refer to the pre-configured criteria used to classify the priority levels of various conflict conditions, serving as the basis for distinguishing between high, medium, and low priority conflicts. The type of conflict condition refers to the conflict classification category derived from the priority rules, primarily divided into high-priority, medium-priority, and low-priority conflict conditions. High-priority conflict conditions are those with the highest priority level; failure to correct them would result in critical conflicts such as business violations, cost overruns, or platform rule failures. Forced repositioning refers to the correction operation that forcibly modifies the conflict parameters within the operational strategy based on business constraint parameters, ensuring their values ​​align with business constraints and eliminating high-priority conflicts.

[0041] In one embodiment, determining the type of conflict condition in a candidate operation strategy according to a preset priority classification rule can be achieved by: extracting the constraint fields corresponding to all conflict conditions in the candidate operation strategy one by one according to the priority of each type of constraint item in the pre-stored priority classification rule; comparing the field type of each conflict condition with the pre-stored constraint type in the classification rule; and determining the priority category of the corresponding conflict condition based on the comparison result. For example, in the preset priority classification rule, exceeding the user cost per customer limit is classified as a high-priority conflict, and deviation from the activity's launch time period is classified as a low-priority conflict. When a candidate operation strategy simultaneously has both conflicts of exceeding the user cost limit and mismatched launch time period, the cost exceeding the limit is determined to be a high-priority conflict condition, and the time period deviation is determined to be a low-priority conflict condition.

[0042] In one embodiment, when the conflict condition is classified as a high-priority conflict condition, the method for forcibly resetting the high-priority conflict condition based on business constraint parameters can be as follows: extract the original strategy parameters and baseline business constraint parameters corresponding to the high-priority conflict condition, directly replace the conflict parameters within the strategy with compliant business constraint parameters, and complete the forced parameter correction to eliminate critical constraint conflicts. For example, if the business constraint parameter limits the single-user activity cost to a maximum of 5 yuan, and the original configuration of the candidate operation strategy is 7 yuan per user, exceeding this cost limit constitutes a high-priority conflict. The original 7 yuan parameter in the strategy is then forcibly modified to the 5 yuan stipulated by the business constraint.

[0043] S1022. When the conflict condition is of medium priority, perform interval compression processing on the medium priority conflict condition based on the business constraint parameters.

[0044] Among them, medium-priority conflict conditions refer to conflict items whose impact is less than that of high-priority conditions. They will not directly cause business violations, but will deviate from business control objectives and increase operational losses. There is no need to force uniform parameters; only range adjustments are required. Range compression processing refers to using business constraint parameters as a reference to narrow the value range of the original strategy conflict parameters, converging the parameter fluctuation range towards compliance standards, weakening the conflict amplitude, and not forcing a fixed single standard value.

[0045] In one embodiment, when the conflict condition is classified as a medium-priority conflict condition, the method for range compression processing of the medium-priority conflict condition based on business constraint parameters can be as follows: extract the original parameter range of the strategy corresponding to the medium-priority conflict condition and the compliance range of the business constraint parameters as a reference; use the compliance range of the business constraint parameters as the boundary to shrink the original strategy parameter value range inward, thereby completing range compression to reduce the parameter deviation and mitigate constraint conflicts, without fixing the parameters to standard values. For example, if the business constraint parameters specify an activity subsidy range of 2 to 4 yuan, and the original subsidy parameter range of a candidate operation strategy is 1 to 5 yuan, and the fluctuation deviation of this subsidy belongs to a medium-priority conflict, the original range can be compressed and adjusted to 2 to 4.5 yuan based on the compliance boundary, while retaining a small parameter fluctuation space while conforming to business constraints.

[0046] S1023. When the type of conflict condition is a low-priority conflict condition, the low-priority conflict condition shall be adapted proportionally based on the business constraint parameters.

[0047] Low-priority conflict conditions refer to conflict items with minimal negative impact, which do not affect business compliance or core cost control, and whose detailed parameters only slightly deviate from business requirements. These items do not require mandatory value changes or range compression. Proportional adaptation refers to an optimization method that uses business constraint parameters as a benchmark, synchronously fine-tuning the original conflicting parameters according to a fixed scaling ratio, preserving the original relative proportions of the parameters, and slightly correcting deviations.

[0048] In one embodiment, when the conflict condition is a low-priority conflict condition, the method for proportionally adapting the low-priority conflict condition based on business constraint parameters can be as follows: First, obtain the original strategy parameters and benchmark business constraint parameters corresponding to the low-priority conflict condition, calculate the deviation ratio of the original parameters relative to the standard parameters, and then scale and fine-tune the strategy conflict parameters proportionally according to the deviation ratio, retaining the original ratio of each parameter to achieve minor adaptation and rectification. For example, the business constraint parameters stipulate that the new and old user subsidy ratio is 1:2, and the original new and old user subsidy ratio of a certain operation strategy is 1:2.4. This ratio deviation is a low-priority conflict. After calculation, the old user subsidy is 20% higher than the standard. According to the preset correction coefficient, only 50% of the deviation is eliminated for proportional adaptation, and the required adjustment is: (2.4-2)×50%=0.2. The original old user parameter is adjusted from 2.4 to 2.2, and the corrected ratio is 1:2.2.

[0049] The above-mentioned approach classifies and manages various conflict conditions of candidate operational strategies according to preset priority classification rules. For high-priority conflicts, mandatory repositioning is used to achieve hard compliance rectification; for medium-priority conflicts, the parameter value range is narrowed by range compression to reduce the conflict magnitude; and for low-priority conflicts, small-scale fine-tuning and optimization are performed by proportional adaptation. This approach ensures that high-priority core constraints are strictly implemented and avoids business violation risks, while flexibly preserving the original parameter design space for medium and low-priority conflicts. It avoids using the same adjustment method to affect the flexibility of operational strategy adjustments, and maximizes the retention of personalized configurations of candidate operational strategies while meeting business constraint control requirements, thereby improving the rationality and adaptation efficiency of conflict optimization and handling.

[0050] S103. Perform effect analysis on user behavior funnel data, and adjust the second strategy parameters of the optimization strategy based on the analysis results to obtain the target operation strategy for the target business.

[0051] Among these, performance analysis refers to the data analysis process of comparing the actual completed data at each node of the funnel with preset indicators to identify data anomalies and pinpoint conversion shortcomings. Secondary strategy parameter adjustment refers to a second round of refined parameter correction based on feedback from actual implementation data. The target operational strategy refers to the final operational plan, adapted to business needs and ready for formal implementation, obtained after two rounds of parameter optimization and data verification.

[0052] In one embodiment, the method for analyzing the effectiveness of user behavior funnel data can be as follows: group and classify the data of all nodes in the entire link using a clustering algorithm; calculate the deviation of the actual conversion rate of each node based on the historical benchmark data of the same type and the control group data of the same period; compare the deviation with the preset level division parameters; determine the level parameter range to which the deviation belongs based on the comparison results; and determine the level corresponding to the level parameter range. The level may include normal level, slightly abnormal level, and severely abnormal level.

[0053] In one embodiment, the method for adjusting the second strategy parameters of the optimization strategy based on the analysis results to obtain the target operation strategy for the target business is as follows: Based on the pre-set mapping relationship between adjustment coefficients and anomaly levels, adjustment coefficients corresponding to minor and severe anomaly levels are determined. The adjustment coefficient corresponding to the severe anomaly level is greater than that corresponding to the minor anomaly level. The normal strategy corresponding to the normal level remains unchanged, therefore its corresponding adjustment coefficient is 0. Adjustable parameters in the severe anomaly strategy are adjusted first based on the adjustment coefficient corresponding to the severe anomaly level. After adjustment, the adjustable parameters in the minor anomaly strategy are adjusted based on the adjustment coefficient corresponding to the minor anomaly level, ultimately obtaining an operation plan that fully adapts to business needs. The adjustment coefficients corresponding to each level are expected funnel indicators that have been pre-calculated, verified, and adjusted through multiple rounds of simulation.

[0054] Figure 4 This is a flowchart of an effect analysis and second strategy parameter adjustment method provided in an embodiment of this application, such as... Figure 4 As shown, it includes: S1031. Decompose the user behavior funnel data to obtain funnel data of multiple nodes, and identify the nodes in each funnel data whose completion rate is less than the preset completion rate threshold of the corresponding node as abnormal nodes.

[0055] The funnel data for a node can refer to statistical indicators such as the user base, number of participants, number of successful completions, and completion rate for a single node after splitting. The completion rate threshold for a node refers to a pre-set standard completion rate reference value for each funnel node; each node can be configured with an independent threshold as a benchmark for judging node anomalies. An abnormal node refers to a process node whose actual completion rate exceeds its preset threshold, exhibiting abnormal conversion performance, and requiring further investigation.

[0056] In one embodiment, the method for decomposing user behavior funnel data into multiple nodes can be as follows: The user behavior funnel data is broken down into sequentially connected behavioral nodes according to the business process order. Then, statistical indicators such as the number of users entering and successfully completing each node are extracted from the user behavior funnel data, and these are summarized to generate independent funnel data for each node. For example, the e-commerce order placement process is broken down into five nodes: homepage exposure, product browsing, adding to cart, order submission, and payment. The number of visitors and the number of users completing each step are extracted from the overall funnel raw data to form the funnel data for each of the five nodes.

[0057] In one embodiment, after determining the funnel data for each node, the actual completion rate of each node's funnel data is retrieved one by one, and a pre-configured completion rate threshold for that node is matched. The actual completion rate of each node is compared with the corresponding threshold. If the actual completion rate of a node is less than its own preset threshold, the node is determined to be an abnormal node. For example, the preset completion rate threshold for the "add to cart" node is 25%, and the threshold for the "place order" node is 12%. The actual completion rate for "add to cart" is 32%, and the actual completion rate for "place order" is 10%. After comparison, the completion rate of the "place order" node is less than the corresponding threshold, so the "place order" node is marked as an abnormal node.

[0058] S1032. Calculate the ratio of the number of abnormal nodes to the preset total number of nodes. If the ratio meets the preset ratio threshold, determine the optimization strategy corresponding to the user behavior funnel data as the abnormal strategy.

[0059] The preset total number of nodes refers to the total number of statistical nodes pre-defined in the user behavior funnel. The preset percentage threshold refers to a pre-set critical value for the percentage of abnormalities, which is the standard value for determining whether the corresponding optimization strategy is abnormal. Abnormal strategies refer to operational strategies that require rectification and optimization when the percentage of abnormal nodes in the funnel reaches the standard and the overall conversion performance of the funnel is abnormal.

[0060] In one embodiment, the ratio of the number of abnormal nodes to the preset total number of nodes can be calculated as follows: first, count the actual number of abnormal nodes after filtering; then, retrieve the total number of nodes preset in the funnel link; and finally, divide the number of abnormal nodes by the preset total number of nodes to obtain the abnormality percentage. In one embodiment, after obtaining the abnormality percentage of the optimization strategy, compare the abnormality percentage with a preset ratio threshold. If the abnormality percentage is greater than or equal to the preset ratio threshold, then the optimization strategy corresponding to the user behavior funnel data is determined to be an abnormal strategy.

[0061] S1033, Adjust the second strategy parameters for the exception strategy.

[0062] In one embodiment, the method for adjusting the second strategy parameters of an abnormal strategy is as follows: extract all operational parameters associated with the abnormal strategy and redistribute the allocation of resources according to a tiered quota allocation rule. For example, if a user acquisition strategy is determined to be an abnormal strategy, and the original channel allocation resources are evenly distributed at 20% each, a tiered allocation method is adopted. Based on the historical conversion performance of each channel, high-quality channel resources and inefficient channel resources are determined, with high-quality channel resources increased to 30% and inefficient channel resources decreased to 10%.

[0063] Optionally, the second strategy parameter adjustment is performed on the abnormal strategy, including: calculating the contribution value of the abnormal node to the overall strategy effect based on the user behavior funnel data corresponding to the abnormal strategy; identifying the abnormal node whose contribution value meets the preset contribution threshold as a high contribution node; and identifying the abnormal node whose contribution value does not meet the preset contribution threshold as a low contribution node; performing indicator gap filling operation on the high contribution node and parameter balancing adjustment processing on the low contribution node.

[0064] The contribution value refers to the weighted value of the impact of data fluctuations at a single abnormal node on the overall conversion effect of the entire operational strategy. The preset contribution threshold refers to a pre-defined critical weight value, which can be used as a criterion for distinguishing between high and low contribution nodes. A high contribution node refers to a critical abnormal node whose contribution value exceeds the preset threshold and whose abnormality would significantly affect the overall strategy's effectiveness. A low contribution node refers to a minor abnormal node whose contribution value does not reach the preset threshold and whose abnormality has a negligible impact on the overall strategy. The indicator gap filling operation refers to targeting high contribution nodes, making up the difference between the actual data and the standard indicator, and specifically addressing and eliminating key shortcomings. The parameter balancing adjustment process refers to targeting low contribution nodes, making small, even adjustments to relevant configuration parameters to smoothly optimize node data.

[0065] In one embodiment, the method for calculating the contribution value of abnormal nodes to the overall strategy effect based on the user behavior funnel data corresponding to the abnormal strategy can be as follows: calculate the difference between the completion rate of each abnormal node in the user behavior funnel data corresponding to the abnormal strategy and the preset standard completion rate, and convert the difference in completion rate of each abnormal node into a contribution value according to the preset conversion rule, wherein the larger the difference in completion rate, the smaller the corresponding contribution value. For example, the reciprocal of the completion rate difference for each abnormal node is calculated to obtain the reciprocal result of the completion rate for each abnormal node. The reciprocals of the completion rates for each abnormal node are then summed. The ratio of the reciprocal result of the completion rate difference for each abnormal node to the summation result is determined as the contribution value of the corresponding abnormal node. For example, if the completion rate difference for node A is 0.2, its reciprocal is 5, and the completion rate difference for node B is 0.05, its reciprocal is 20. The summation of the reciprocals of the completion rate differences yields a result of 25. The contribution value of node A is 5 / 25 = 0.2, and the contribution value of node B is 20 / 25 = 0.8.

[0066] In one embodiment, after calculating the contribution value of each abnormal node, each contribution value is compared with a preset contribution threshold. If it is greater than or equal to the preset contribution threshold, the abnormal node corresponding to the contribution value is determined as a high contribution node; if it is less than the preset contribution threshold, the abnormal node corresponding to the contribution value is determined as a low contribution node.

[0067] In one embodiment, the method for filling the performance gap for high-contribution nodes can be as follows: First, retrieve the historical conversion data of the high-contribution nodes. Based on this historical conversion data, determine the historical average conversion rate target ratio for new and old users. Then, calculate the performance gap value based on the completion rate corresponding to the high-contribution node and a preset completion rate threshold. Finally, calculate the gap filling amount for new users and the gap filling amount for old users based on the performance gap value and the historical average conversion rate target ratio for new and old users. For example, if the performance gap for a high-contribution node is 200 orders, the performance gap is split according to the historical average conversion rate target ratio of new and old customers (6:4). Targeted discount coupons are issued to new customers to fill the gap of 120 orders, and exclusive instant discount benefits are provided to old customers to fill the remaining gap of 80 orders.

[0068] Optionally, a gap-filling operation is performed on high-contribution nodes, including: calculating the gap value of the indicator based on the completion rate corresponding to the high-contribution node and the preset completion rate threshold, and determining the adjustable parameter corresponding to the gap value and the adjustment range corresponding to the adjustable parameter; dividing the adjustment range into multi-level intervals to obtain the step size of the step adjustment, and adjusting the adjustable parameter of the high-contribution node step by step based on the step size of the step adjustment.

[0069] The indicator gap value refers to the difference between the preset completion rate threshold and the current actual completion rate of the node, representing the conversion gap that the node needs to bridge. Adjustable parameters refer to operational variables that can be modified through operational configuration to boost the node's completion rate, such as targeted subsidies and user-targeted advertising quotas. The adjustment range refers to the total change in the adjustable parameters required to fill the indicator gap. Multi-level interval division refers to breaking down the total adjustment range into multiple segments of increasing size. The step size of the tiered adjustment refers to the amount of parameter adjustment per segment after the multi-level interval division. Step-by-step adjustment refers to modifying parameters segment by segment according to the step size of the tiered adjustment to gradually fill the indicator gap.

[0070] In one embodiment, the method for calculating the indicator gap value based on the completion rate corresponding to a high-contribution node and a preset completion rate threshold is as follows: The difference between the preset completion rate threshold and the current actual completion rate of the high-contribution node is calculated, and the product of this calculation result and the total number of users entering the node from the pre-acquired funnel data is determined as the indicator gap value that the high-contribution node needs to fill. For example, if the preset completion rate threshold for a high-contribution node is 12%, the current actual completion rate is 10%, and the current total number of users entering the node is 10,000, the calculated indicator gap value is (12% - 10%) × 10,000 = 200 orders.

[0071] In one embodiment, the method for determining the adjustable parameter corresponding to the indicator gap value and the adjustment range corresponding to the adjustable parameter can be as follows: Based on the priority of adjustable parameters pre-configured for the node, prioritize the adjustment of high-priority operational parameters that have a faster response and a more direct boosting effect. Then, calculate the total adjustment range required to fill the indicator gap based on the conversion improvement rate corresponding to the unit adjustment amount of the parameter obtained from historical data statistics. For example, for an indicator gap of 200 orders at the order placement node, the subsidy issuance parameter is prioritized as the adjustable parameter. Based on historical data, issuing 100 discount coupons can increase the conversion rate by 20 orders, and the total adjustment range is calculated to be issuing an additional 1000 discount coupons.

[0072] In one embodiment, the method of dividing the adjustment range into multi-level intervals to obtain the step size of the adjustment can be as follows: the total adjustment range to be adjusted is divided into multiple sub-intervals of equal length, and the change corresponding to each sub-interval is the step size of a single adjustment. For example, if the total adjustment range is to issue 1,000 discount coupons, and it is divided into 5 intervals, with each interval corresponding to 200 coupons, then the step size of the step size is to issue 200 discount coupons at a time.

[0073] In one embodiment, the method of adjusting the adjustable parameters of high contribution nodes step by step based on the step adjustment step size can be as follows: after each step adjustment is completed, the current actual completion rate of the node is recalculated, and the current remaining indicator gap value is recalculated. If the remaining indicator gap value is greater than 0, the next step adjustment is carried out until the actual completion rate of the node reaches or exceeds the preset completion rate threshold, and the parameter adjustment is stopped.

[0074] As described above, by breaking down the adjustment range into tiered adjustment steps and adjusting them step by step, we can avoid data fluctuations caused by a large adjustment of parameters at once. After each adjustment, we can re-observe the node conversion effect, gradually approach the target indicator, improve the accuracy and stability of parameter adjustment, and avoid the waste of operational resources caused by over-adjustment.

[0075] In one embodiment, the parameter balancing adjustment process for low-contribution nodes can be performed as follows: All configuration parameters of all low-contribution nodes are aggregated, the current configuration range of each parameter is statistically analyzed, and parameters with significant configuration discrepancies or uneven distributions are identified. These parameters, such as the exposure push frequency, are then used as the balancing adjustment target. After determining the exposure push frequency as the balancing adjustment target, the configuration parameters of the exposure push frequency for each node are compared. Based on the comparison results, the minimum and maximum configuration parameters are determined. The minimum configuration parameter is increased by a preset adjustment range, and the maximum configuration parameter is decreased.

[0076] The above-mentioned approach quantifies the contribution of each abnormal node to the overall strategy effect and divides nodes into high and low contribution nodes according to preset thresholds. It then targets high contribution nodes to fill the indicator gaps and implements parameter balancing adjustments for low contribution nodes. This approach can not only focus on adjusting key nodes that have a significant impact on conversion losses, effectively reducing the overall indicator gaps and improving the overall conversion benefits of the strategy, but also adjust the configuration of secondary nodes through balancing to avoid excessive adjustments that could cause data fluctuations.

[0077] In one embodiment, after obtaining the target operation strategy for the target business, the method further includes: conducting group comparison tests on the target operation strategies; if the completion rate in the test results meets the preset storage conditions, marking the target operation strategies based on the business scenario type corresponding to the target operation strategies, and storing the marked target operation strategies in the preset platform strategy library.

[0078] Among these, A / B testing involves dividing users into an experimental group and a control group. The experimental group adopts the target operational strategy, while the control group continues with the original strategy. The completion rates of the two groups are compared under the same environment. Pre-defined entry conditions refer to pre-defined admission criteria, such as the improvement in the completion rate of the experimental group compared to the control group. Business scenario types refer to the funnel stages and business categories for adapting the operational strategy, such as order placement scenarios, browsing and outreach scenarios, and payment conversion scenarios. Tagging refers to the process of adding category tags to strategies according to scenario types.

[0079] In one embodiment, the method for conducting group-based comparative testing of the target operation strategy can be as follows: two groups of independent users are randomly selected from the current active user pool of the business and labeled as the experimental group and the control group, respectively. Ensure that there is no significant difference in the distribution characteristics of user attributes between the two groups of users. Push the target operation strategy with adjusted parameters to the experimental group, and the control group carries out operation actions according to the original strategy parameters. Maintain the same test period, and after the test period ends, calculate the overall link completion rate of the experimental group and the control group respectively.

[0080] In one embodiment, if the completion rate in the test results meets the preset entry conditions, the way to mark the target operation strategy based on the business scenario type corresponding to the target operation strategy can be as follows: calculate the improvement ratio of the overall link completion rate of the experimental group compared with the control group. If the improvement ratio reaches the preset improvement ratio threshold, it is determined that the preset entry conditions are met, and extract the business scenario keywords that the target operation strategy is adapted to, add the corresponding scenario tags to the strategy, and if there are multiple adapted scenarios during the marking process, add multiple corresponding tags in sequence.

[0081] In one embodiment, the method for storing the marked target operation strategy in the preset platform strategy library can be as follows: the marked target operation strategy is stored in the corresponding category directory of the preset platform strategy library according to the business scenario, and the full parameter configuration and test improvement data information after the strategy adjustment are stored synchronously, so as to facilitate direct retrieval and reuse when optimizing the operation strategy in the same scenario in the future.

[0082] As mentioned above, by classifying and storing the target operational strategies that have passed testing and been optimized into a strategy library, high-quality operational strategy assets can be accumulated. Mature solutions can be directly reused when optimizing similar business scenarios in the future, reducing the cost of repeated adjustments and improving the efficiency of iterative optimization of business operational strategies.

[0083] This application embodiment obtains business requirement parameters and business constraint parameters of the target business, matches the business requirement parameters with multiple operational strategies in a preset platform strategy library, and determines candidate operational strategies based on the matching results. Based on the business constraint parameters, the candidate operational strategies undergo a first strategy parameter adjustment to obtain an optimized strategy, which is then deployed, and the user behavior funnel data corresponding to the optimized strategy is monitored. The user behavior funnel data is then analyzed for effectiveness, and based on the analysis results, the optimized strategy undergoes a second strategy parameter adjustment to obtain the target operational strategy for the target business. This approach, by matching business requirements with the strategy library to determine candidate strategies, adjusting and optimizing parameters based on business constraints, and further refining based on user behavior funnel data, significantly improves the matching accuracy between operational strategies and business objectives, reduces resource waste, achieves automated strategy iteration and continuous effect optimization, and effectively improves strategy optimization efficiency.

[0084] Figure 5 This is a schematic diagram of the structure of a business operation strategy determination device provided in an embodiment of this application, such as... Figure 5 As shown, it includes: Parameter acquisition module 21 is used to acquire the business requirement parameters and business constraint parameters of the target business; The candidate operation strategy determination module 22 is used to match the business requirement parameters with multiple operation strategies in the preset platform strategy library, and determine the candidate operation strategy based on the matching result. The first adjustment module 23 is used to adjust the first strategy parameters of the candidate operation strategy based on the business constraint parameters to obtain an optimized strategy. User behavior funnel data monitoring module 24 is used to deploy the optimization strategy and monitor the user behavior funnel data corresponding to the optimization strategy. The effect analysis module 25 is used to perform effect analysis on the user behavior funnel data; The second adjustment module 26 is used to adjust the second strategy parameters of the optimization strategy according to the analysis results, so as to obtain the target operation strategy of the target business.

[0085] This application embodiment obtains business requirement parameters and business constraint parameters of the target business, matches the business requirement parameters with multiple operational strategies in a preset platform strategy library, and determines candidate operational strategies based on the matching results. Based on the business constraint parameters, the candidate operational strategies undergo a first strategy parameter adjustment to obtain an optimized strategy, which is then deployed, and the user behavior funnel data corresponding to the optimized strategy is monitored. The user behavior funnel data is then analyzed for effectiveness, and based on the analysis results, the optimized strategy undergoes a second strategy parameter adjustment to obtain the target operational strategy for the target business. This approach, by matching business requirements with the strategy library to determine candidate strategies, adjusting and optimizing parameters based on business constraints, and further refining based on user behavior funnel data, significantly improves the matching accuracy between operational strategies and business objectives, reduces resource waste, achieves automated strategy iteration and continuous effect optimization, and effectively improves strategy optimization efficiency.

[0086] In one possible embodiment, the candidate operation strategy determination module 22 is used for: Conflict detection is performed on the business constraint parameters and each operational strategy in the preset platform strategy library, and conflict and non-conflict conditions in each operational strategy are determined based on the detection results. Calculate the first matching score corresponding to the conflict condition, and perform a weighted calculation on the first matching score and the second matching score corresponding to the non-conflict condition to obtain the constraint matching score of the candidate operation strategy. The operation strategy with the constraint matching score greater than the preset score threshold is determined as the candidate operation strategy, and the second matching score is the preset score value.

[0087] In one possible embodiment, the first adjustment module 23 is used for: The type of conflict condition in the candidate operation strategy is determined according to the preset priority division rule. If the type of conflict condition is a high-priority conflict condition, the high-priority conflict condition is forcibly reset based on the business constraint parameter. When the conflict condition is of medium priority, the medium priority conflict condition is subjected to interval compression processing based on the business constraint parameters. When the conflict condition is a low-priority conflict condition, the low-priority conflict condition is adapted proportionally based on the business constraint parameters.

[0088] In one possible embodiment, the effect analysis module 25 is used for: The user behavior funnel data is broken down to obtain funnel data for multiple nodes. Nodes in each funnel data whose completion rate is less than the preset completion rate threshold of the corresponding node are identified as abnormal nodes. Calculate the ratio of the number of abnormal nodes to the preset total number of nodes. If the ratio meets the preset ratio threshold, determine the optimization strategy corresponding to the user behavior funnel data as an abnormal strategy. Accordingly, the second adjustment module 26 is used for: The second strategy parameter is adjusted for the aforementioned anomaly strategy.

[0089] In one possible embodiment, the second adjustment module 26 is used for: The contribution value of the abnormal node to the overall strategy effect is calculated based on the user behavior funnel data corresponding to the abnormal strategy. Abnormal nodes whose contribution value meets the preset contribution threshold are identified as high contribution nodes, and abnormal nodes whose contribution value does not meet the preset contribution threshold are identified as low contribution nodes. The high-contribution nodes are filled with missing indicators, and the low-contribution nodes are adjusted to balance parameters.

[0090] In one possible embodiment, the second adjustment module 26 is used for: The indicator gap value is calculated based on the completion rate corresponding to the high contribution node and the preset completion rate threshold, and the adjustable parameter corresponding to the indicator gap value and the adjustment range corresponding to the adjustable parameter are determined. The adjustment range is divided into multiple intervals to obtain a stepped adjustment step size. Based on the stepped adjustment step size, the adjustable parameters of the high contribution node are adjusted step by step.

[0091] In one possible embodiment, it further includes a grouped control test module, a tagging module, and a strategy storage module, wherein the control test module is used to perform grouped control tests on the target operation strategy; The tagging module is used to tag the target operation strategy based on the business scenario type corresponding to the target operation strategy when the completion rate in the test results meets the preset entry conditions. The strategy storage module is used to store the marked target operation strategies into the preset platform strategy library.

[0092] This application also provides an electronic device that can integrate a business operation strategy determination apparatus provided in this application. Figure 6 This is a schematic diagram of the structure of a business operation strategy determination device provided in an embodiment of this application, with reference to... Figure 6The business operation strategy determination device includes: an input device 33, an output device 34, a memory 32, and one or more processors 31; the memory 32 is used to store one or more programs; when one or more programs are executed by one or more processors 31, the one or more processors 31 implement the business operation strategy determination method provided in the above embodiments. The input device 33, output device 34, memory 32, and processor 31 can be connected via a bus or other means. Figure 6 Taking the bus connection between China and Israel as an example.

[0093] The memory 32, as a computing device readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the business operation strategy determination method provided in any embodiment of this application. The memory 32 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the device. Furthermore, the memory 32 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 32 may further include memory remotely located relative to the processor 31, and these remote memories can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0094] Input device 33 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Output device 34 may include display devices such as a display screen.

[0095] The processor 31 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 32, thereby realizing the above-mentioned business operation strategy determination method.

[0096] The business operation strategy determination apparatus, equipment, and computer provided above can be used to execute the business operation strategy determination method provided in any of the above embodiments, and have corresponding functions and beneficial effects.

[0097] This application embodiment also provides a storage medium for storing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to execute the business operation strategy determination method provided in the above embodiment. The business operation strategy determination method includes: obtaining business requirement parameters and business constraint parameters of a target business; matching the business requirement parameters with multiple operation strategies in a preset platform strategy library; determining candidate operation strategies based on the matching results; adjusting the first strategy parameters of the candidate operation strategies based on the business constraint parameters to obtain an optimized strategy; deploying the optimized strategy; and monitoring the user behavior funnel data corresponding to the optimized strategy; performing effect analysis on the user behavior funnel data; and adjusting the second strategy parameters of the optimized strategy based on the analysis results to obtain the target operation strategy of the target business.

[0098] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disks or optical storage); registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. Furthermore, storage media may reside in a first computer system in which a program is executed, or may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). Storage media may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0099] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the business operation strategy determination method described above, but can also execute related operations in the business operation strategy determination method provided in any embodiment of this application.

[0100] The business operation strategy determination apparatus, device, and storage medium provided in the above embodiments can execute the business operation strategy determination method provided in any embodiment of this application. For technical details not described in detail in the above embodiments, please refer to the business operation strategy determination method provided in any embodiment of this application.

[0101] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A method for determining business operation strategies, characterized in that, include: Obtain the business requirement parameters and business constraint parameters of the target business, match the business requirement parameters with multiple operation strategies in the preset platform strategy library, and determine the candidate operation strategies based on the matching results; Based on the business constraint parameters, the candidate operation strategies are adjusted by first strategy parameters to obtain an optimized strategy, and the optimized strategy is deployed, while monitoring the user behavior funnel data corresponding to the optimized strategy. The user behavior funnel data is analyzed for effectiveness, and the second strategy parameter is adjusted according to the analysis results to obtain the target operation strategy for the target business.

2. The method for determining business operation strategies according to claim 1, characterized in that, The step of matching the business requirement parameters with multiple operational strategies in a preset platform strategy library, and determining candidate operational strategies based on the matching results, includes: Conflict detection is performed on the business constraint parameters and each operational strategy in the preset platform strategy library, and conflict and non-conflict conditions in each operational strategy are determined based on the detection results. Calculate the first matching score corresponding to the conflict condition, and perform a weighted calculation on the first matching score and the second matching score corresponding to the non-conflict condition to obtain the constraint matching score of the candidate operation strategy. The operation strategy with the constraint matching score greater than the preset score threshold is determined as the candidate operation strategy, and the second matching score is the preset score value.

3. The method for determining business operation strategies according to claim 1, characterized in that, The adjustment of the first strategy parameters of the candidate operation strategy based on the business constraint parameters includes: The type of conflict condition in the candidate operation strategy is determined according to the preset priority division rule. If the type of conflict condition is a high-priority conflict condition, the high-priority conflict condition is forcibly reset based on the business constraint parameter. When the conflict condition is of medium priority, the medium priority conflict condition is subjected to interval compression processing based on the business constraint parameters. When the conflict condition is a low-priority conflict condition, the low-priority conflict condition is adapted proportionally based on the business constraint parameters.

4. The method for determining business operation strategies according to claim 1, characterized in that, The effect analysis of the user behavior funnel data includes: The user behavior funnel data is broken down to obtain funnel data for multiple nodes. Nodes in each funnel data whose completion rate is less than the preset completion rate threshold of the corresponding node are identified as abnormal nodes. Calculate the ratio of the number of abnormal nodes to the preset total number of nodes. If the ratio meets the preset ratio threshold, determine the optimization strategy corresponding to the user behavior funnel data as an abnormal strategy. Accordingly, adjusting the second strategy parameters of the optimization strategy based on the analysis results includes: The second strategy parameter is adjusted for the aforementioned anomaly strategy.

5. The method for determining business operation strategies according to claim 4, characterized in that, The adjustment of the second strategy parameters for the anomaly strategy includes: The contribution value of the abnormal node to the overall strategy effect is calculated based on the user behavior funnel data corresponding to the abnormal strategy. Abnormal nodes whose contribution value meets the preset contribution threshold are identified as high contribution nodes, and abnormal nodes whose contribution value does not meet the preset contribution threshold are identified as low contribution nodes. The high-contribution nodes are filled with missing indicators, and the low-contribution nodes are adjusted to balance parameters.

6. The method for determining business operation strategies according to claim 5, characterized in that, The operation of filling the indicator gaps for the high-contribution nodes includes: The indicator gap value is calculated based on the completion rate corresponding to the high contribution node and the preset completion rate threshold, and the adjustable parameter corresponding to the indicator gap value and the adjustment range corresponding to the adjustable parameter are determined. The adjustment range is divided into multiple intervals to obtain a stepped adjustment step size. Based on the stepped adjustment step size, the adjustable parameters of the high contribution node are adjusted step by step.

7. The method for determining business operation strategies according to claim 1, characterized in that, After obtaining the target operational strategy for the target business, the following is also included: The target operation strategy is subjected to grouped comparative testing. If the completion rate in the test results meets the preset storage conditions, the target operation strategy is marked based on the business scenario type corresponding to the target operation strategy, and the marked target operation strategy is stored in the preset platform strategy library.

8. A business operation strategy determination device, characterized in that, include: The parameter acquisition module is used to acquire the business requirement parameters and business constraint parameters of the target business. The candidate operation strategy determination module is used to match the business requirement parameters with multiple operation strategies in the preset platform strategy library, and determine the candidate operation strategy based on the matching results. The first adjustment module is used to adjust the first strategy parameters of the candidate operation strategy based on the business constraint parameters to obtain an optimized strategy. The user behavior funnel data monitoring module is used to deploy the optimization strategy and monitor the user behavior funnel data corresponding to the optimization strategy. The effect analysis module is used to perform effect analysis on the user behavior funnel data; The second adjustment module is used to adjust the second strategy parameters of the optimization strategy based on the analysis results, so as to obtain the target operation strategy of the target business.

9. An electronic device, characterized in that, The device includes: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the business operation strategy determination method as described in any one of claims 1-7.

10. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the business operation strategy determination method as described in any one of claims 1-7.

Images