User flow adjusting method and device, electronic equipment and program product

Abstract

The invention discloses a user flow adjusting method and device, electronic equipment and a program product, relates to the field of big data and is applied to the field of financial science and technology, and the method comprises the steps: determining operation targets of a plurality of operation strategies, and determining quantitative evaluation information according to the operation targets; creating a plurality of experimental groups according to the plurality of operation strategies, and randomly distributing the user traffic to the plurality of experimental groups based on a traffic balance principle; acquiring index data of the plurality of experimental groups according to the quantitative evaluation information to obtain first data of the plurality of operation strategies, and matching the first data with a target rule to obtain a matching result; and adjusting the user traffic distribution proportion of the plurality of experimental groups according to the matching result. Through application of the method and the device, the problem of relatively low flow adjustment efficiency caused by the fact that business personnel need to frequently analyze the adjustment mode according to the index data when the user flow of the operation strategy is adjusted in the related technology is solved.

Description

Technical Field

[0001] This application relates to the field of big data and is applied to the field of financial technology. Specifically, it relates to a method, device, electronic device, and program product for adjusting user traffic. Background Technology

[0002] A / B testing systems are widely used in various business scenarios, including recommendation algorithms, advertising optimization, product feature iteration, and search algorithm improvement. They aim to evaluate the effectiveness of different versions of strategies or product features and guide the selection of the optimal solution. However, existing A / B testing systems have limitations in their traffic adjustment mechanisms. They typically employ a static, manual traffic allocation method, where traffic ratios are set at the initial stage of the experiment, and subsequent adjustments rely on business personnel based on performance analysis results. In rapidly changing market environments, especially during peak business periods, this model involves frequent performance monitoring and traffic adjustment operations, which not only increases the workload of business personnel but also often results in missed opportunities by the time adjustment decisions are made, making it difficult to effectively utilize traffic resources during peak periods.

[0003] There is currently no effective solution to the problem that adjusting user traffic when modifying operational strategies in related technologies requires business personnel to frequently analyze and adjust methods based on indicator data, resulting in low efficiency in traffic adjustment. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, electronic device and program product for adjusting user traffic, so as to solve the problem that when adjusting user traffic for operational strategies in related technologies, business personnel need to frequently analyze and adjust the method based on indicator data, resulting in low efficiency of traffic adjustment.

[0005] To achieve the above objectives, according to one aspect of this application, a method for adjusting user traffic is provided. The method includes: determining operational objectives for multiple operational strategies and determining quantitative evaluation information based on the operational objectives; creating multiple experimental groups based on the multiple operational strategies and randomly allocating user traffic to the multiple experimental groups based on a traffic balancing principle; collecting indicator data from the multiple experimental groups based on the quantitative evaluation information to obtain first data for the multiple operational strategies, and matching the first data with target rules to obtain a matching result; and adjusting the user traffic allocation ratio of the multiple experimental groups based on the matching result.

[0006] Further, determining quantitative evaluation information based on the operational objectives includes: determining target indicators, and determining warning thresholds and expected changes for the target indicators, wherein the target indicators include at least: a first type of indicator and a second type of indicator, the first type of indicator being used to evaluate the business operational effectiveness of the operational strategy, and the second type of indicator being used to evaluate the degree of negative impact of the operational strategy; determining indicator weight information based on the target indicators, the multiple operational strategies, and the operational objectives; and determining the quantitative evaluation information based on the target indicators, the warning thresholds, the expected changes, and the indicator weight information.

[0007] Further, determining indicator weight information based on the target indicator, the multiple operational strategies, and the operational objectives includes: determining the degree of influence of the target indicator on the operational objectives; determining the cost information of the target indicator, wherein the cost information includes at least: development cost information and implementation risk information; determining the priority information of the target indicator based on the degree of influence and the cost information; and determining the indicator weight information of the target indicator based on the priority information.

[0008] Further, the first data is matched with the target rule to obtain a matching result, including: for the first type of indicator and the second indicator of the target experimental group, when the change in the first type of indicator is greater than its expected change and the second type of indicator does not exceed its warning threshold, the first data is determined to be successfully matched with the first rule, wherein the target experimental group is any experimental group among the plurality of experimental groups; when the second type of indicator exceeds its warning threshold, the first data is determined to be successfully matched with the second rule; when the change in the first type of indicator is less than its expected change and the change in the first type of indicator is greater than a preset value, and the second type of indicator does not exceed its warning threshold, the first data is determined to be successfully matched with the third rule; when the change in the first indicator is greater than its expected change and the second indicator does not exceed its warning threshold, the first data is determined to be successfully matched with the fourth rule, wherein both the first indicator and the second indicator belong to the first type of indicator, and the first indicator and the second indicator are different.

[0009] Further, adjusting the user traffic allocation ratio of the multiple experimental groups based on the matching results includes: when the first data successfully matches the first rule, increasing the user traffic allocation ratio of the target experimental group and decreasing the user traffic allocation ratio of other experimental groups; when the first data successfully matches the second rule, adjusting the user traffic allocation ratio of the multiple experimental groups based on historical allocation ratios and sending risk warning information to the target; when the first data successfully matches the third rule, allocating user traffic to the multiple experimental groups based on the current user traffic allocation ratio; when the first data successfully matches the fourth rule, performing a weighted calculation on the first data, and using the calculation result to match the target rule again, adjusting the user traffic allocation ratio of the multiple experimental groups based on the matching results.

[0010] Furthermore, the user traffic allocation ratio of the multiple experimental groups is adjusted according to the historical allocation ratio, and risk warning information is sent to the target object, including: adjusting the user traffic allocation ratio of the multiple experimental groups to a preset allocation ratio, and collecting indicator data of the multiple experimental groups to obtain second data of the multiple operation strategies, wherein the preset allocation ratio includes at least one of the following: initial allocation ratio, received allocation ratio, and allocation ratio of the control group; generating risk warning information based on the first data, and sending the second data and the risk warning information to the target object.

[0011] Furthermore, multiple experimental groups are created based on the multiple operational strategies, including: determining the experimental type of the multiple operational strategies based on their complexity and user group characteristics, wherein the multiple operational strategies include: operational strategies for web pages, operational strategies for application functions, and operational strategies for deep learning models or preset algorithms; determining the experimental mode of the multiple operational strategies based on their experimental type, and defining experimental parameters, wherein the experimental mode includes at least one of the following: user-triggered mode and push mode; determining the experimental duration based on the multiple operational strategies and business requirements; and creating the multiple experimental groups based on their experimental type, experimental mode, and experimental duration.

[0012] To achieve the above objectives, according to another aspect of this application, a user traffic adjustment device is provided. The device includes: a determining unit, configured to determine the operational objectives of multiple operational strategies and determine quantitative evaluation information based on the operational objectives; an allocation unit, configured to create multiple experimental groups based on the multiple operational strategies and randomly allocate user traffic to the multiple experimental groups based on a traffic balancing principle; a matching unit, configured to collect indicator data of the multiple experimental groups based on the quantitative evaluation information, obtain first data of the multiple operational strategies, and match the first data with target rules to obtain a matching result; and an adjustment unit, configured to adjust the user traffic allocation ratio of the multiple experimental groups based on the matching result.

[0013] Further, the determining unit includes: a first determining subunit, used to determine a target indicator, and to determine a warning threshold and expected change amount of the target indicator, wherein the target indicator includes at least: a first type of indicator and a second type of indicator, the first type of indicator being used to evaluate the business operation effect of the operation strategy, and the second type of indicator being used to evaluate the degree of negative impact of the operation strategy; a second determining subunit, used to determine indicator weight information based on the target indicator, the multiple operation strategies, and the operation target; and a third determining subunit, used to determine the quantitative evaluation information based on the target indicator, the warning threshold, the expected change amount, and the indicator weight information.

[0014] Further, the second determining subunit includes: a first determining module, used to determine the degree of influence of the target indicator on the operational objective; a second determining module, used to determine the cost information of the target indicator, wherein the cost information includes at least: development cost information and implementation risk information; a third determining module, used to determine the priority information of the target indicator based on the degree of influence and the cost information; and a fourth determining module, used to determine the indicator weight information of the target indicator based on the priority information.

[0015] Further, the matching unit includes: a fourth determining subunit, configured to determine that the first data matches the first rule successfully when the change in the first type of indicator is greater than its expected change and the second type of indicator does not exceed its warning threshold, for the first type of indicator and the second indicator of the target experimental group; a fifth determining subunit, configured to determine that the first data matches the second rule successfully when the second type of indicator exceeds its warning threshold; a sixth determining subunit, configured to determine that the first data matches the third rule successfully when the change in the first type of indicator is less than its expected change and the change in the first type of indicator is greater than a preset value and the second type of indicator does not exceed its warning threshold; and a seventh determining subunit, configured to determine that the first data matches the fourth rule successfully when the change in the first indicator is greater than its expected change and the second indicator does not exceed its warning threshold, wherein both the first indicator and the second indicator belong to the first type of indicator, and the first indicator and the second indicator are different.

[0016] Further, the adjustment unit includes: a first adjustment subunit, configured to increase the user traffic allocation ratio of the target experimental group and decrease the user traffic allocation ratio of other experimental groups when the first data successfully matches the first rule; a second adjustment subunit, configured to adjust the user traffic allocation ratio of the multiple experimental groups according to the historical allocation ratio when the first data successfully matches the second rule, and send risk warning information to the target object; a third adjustment subunit, configured to allocate user traffic to the multiple experimental groups according to the current user traffic allocation ratio when the first data successfully matches the third rule; and a fourth adjustment subunit, configured to perform weighted calculation on the first data when the first data successfully matches the fourth rule, and use the calculation result to match the target rule again, and adjust the user traffic allocation ratio of the multiple experimental groups according to the matching result.

[0017] Further, the second adjustment subunit includes: an adjustment module, used to adjust the user traffic allocation ratio of the multiple experimental groups to a preset allocation ratio, and collect indicator data of the multiple experimental groups to obtain second data of the multiple operational strategies, wherein the preset allocation ratio includes at least one of the following: an initial allocation ratio, a received allocation ratio, and an allocation ratio of the control group; and a generation module, used to generate risk warning information based on the first data, and send the second data and the risk warning information to the target object.

[0018] Furthermore, the allocation unit includes: an eighth determining subunit, used to determine the experiment type of multiple operation strategies based on the complexity of the multiple operation strategies and the characteristics of the user group, wherein the multiple operation strategies include: operation strategies for web pages, operation strategies for application functions, and operation strategies for deep learning models or preset algorithms; a ninth determining subunit, used to determine the experiment mode of multiple operation strategies based on the experiment type of multiple operation strategies, and define experiment parameters, wherein the experiment mode includes at least one of the following: user-triggered mode, push mode; a tenth determining subunit, used to determine the experiment duration based on multiple operation strategies and business needs; and a creation subunit, used to create multiple experiment groups based on the experiment type, experiment mode, and experiment duration of multiple operation strategies.

[0019] To achieve the above objectives, according to one aspect of this application, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the user traffic adjustment method described in any of the above-mentioned embodiments, and the computer program, when executed by a processor, implements the steps of the user traffic adjustment method described in various embodiments of this application.

[0020] To achieve the above objectives, according to one aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including stored computer instructions, wherein, when the computer instructions are executed by a processor, the user traffic adjustment method described in any one of the above claims is implemented.

[0021] To achieve the above objectives, according to one aspect of this application, an electronic device is provided, including one or more processors and a memory, the memory being used 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 cause the one or more processors to implement the user traffic adjustment method described in any of the above claims.

[0022] In this embodiment, by determining the operational objectives of multiple operational strategies and determining quantitative evaluation information based on the operational objectives; creating multiple experimental groups based on the multiple operational strategies, and randomly allocating user traffic to the multiple experimental groups based on the principle of traffic balancing; collecting indicator data of the multiple experimental groups based on the quantitative evaluation information to obtain the first data of the multiple operational strategies, and matching the first data with the target rules to obtain the matching result; adjusting the user traffic allocation ratio of the multiple experimental groups based on the matching result, thereby solving the technical problem of low traffic adjustment efficiency caused by the need for business personnel to frequently analyze and adjust methods based on indicator data when adjusting user traffic of operational strategies.

[0023] By defining the operational objectives of multiple operational strategies and setting quantitative evaluation information accordingly, the experimental design can be systematically guided, achieving the technical effect of clarifying the experimental direction and expected results. Continuously collecting experimental group indicator data and matching it with target rules to obtain matching results allows for objective evaluation of strategy implementation, enabling dynamic strategy adjustment based on empirical analysis. This further enhances operational flexibility and improves strategy success rate. Finally, dynamically adjusting the user traffic allocation ratio for each experimental group based on the matching results ensures that resources are concentrated on the best-performing strategy, further improving operational efficiency. Attached Figure Description

[0024] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0025] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a user traffic adjustment method according to Embodiment 1 of this application;

[0026] Figure 2 This is a flowchart of a user traffic adjustment method according to Embodiment 1 of this application;

[0027] Figure 3 This is a schematic diagram of an optional dynamic adjustment process for user traffic provided in Embodiment 1 of this application;

[0028] Figure 4 This is a schematic diagram of a user traffic adjustment device according to Embodiment 2 of this application;

[0029] Figure 5 This is a schematic diagram of an electronic device for adjusting user traffic according to Embodiment 3 of this application. Detailed Implementation

[0030] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0031] It should be noted that the processing method, apparatus, storage medium, and electronic device specified in this application can be used in the fintech field to adjust user traffic in operational strategies, thereby improving traffic adjustment efficiency. They can also be used in any field other than fintech. The application fields of the processing method, apparatus, storage medium, and electronic device specified in this application are not limited.

[0032] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, collected data, used data, generated data, processed data, etc.) and the data (including but not limited to data used for analysis, stored data, displayed data, collected information, used information, generated information, processed information, etc.) are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations, providing users with corresponding operation entry points for users to choose to agree to or refuse automated decision results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0033] Example 1

[0034] According to an embodiment of this application, a method embodiment for adjusting user traffic is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] The method embodiment provided in Embodiment 1 of this application can be executed in a mobile terminal, computer terminal or similar computing device. Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a user traffic adjustment method according to Embodiment 1 of this application. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the user traffic adjustment method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned user traffic adjustment method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 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.

[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0039] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0040] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for adjusting user traffic is shown. Figure 2 This is a flowchart of an optional user traffic adjustment method provided according to Embodiment 1 of this application.

[0041] Step S201: Determine the operational objectives of multiple operational strategies and determine quantitative evaluation information based on the operational objectives.

[0042] In this Example 1, to evaluate multiple operational strategies through split testing (also known as A / B testing), it is necessary to determine the operational objectives of each strategy, that is, to clarify the specific business results that each strategy aims to achieve, such as improving conversion rates or increasing user activity. Based on the operational objectives, a series of quantitative evaluation information is established. This quantitative evaluation information is used to measure the effectiveness of strategy implementation, ensuring that operational activities achieve business growth without adversely affecting key areas such as user experience and business system stability.

[0043] Step S202: Create multiple experimental groups based on multiple operational strategies, and randomly allocate user traffic to multiple experimental groups based on the principle of traffic balancing.

[0044] In this embodiment 1, multiple experimental groups are constructed based on the determined operational strategies to evaluate the effectiveness of different strategies through comparative analysis. The creation of experimental groups is based on strategy variables, including but not limited to different implementations of interface design, functional characteristics, or algorithm models. In addition to the experimental groups corresponding to the multiple operational strategies, the multiple experimental groups may also include a control group, which is a set of samples that were not subjected to experimental variables or only received standard treatment during the experiment. The role of the control group is to provide a benchmark for comparison with the results of the experimental groups, assessing the specific impact of experimental variables on the results.

[0045] Subsequently, based on the principle of traffic balancing, the overall user traffic was randomly divided to ensure that the user traffic data received by each experimental group was averaged, avoiding the introduction of bias. This random allocation process had to follow statistical principles to maintain the consistency of user attribute distribution among the experimental groups in order to obtain reliable and effective experimental data. By precisely controlling the traffic allocation, the performance of each experimental group could be independently evaluated under controlled variables, providing a solid foundation for subsequent dynamic traffic adjustments.

[0046] Step S203: Collect indicator data from multiple experimental groups based on quantitative evaluation information to obtain the first data of multiple operational strategies, and match the first data with the target rules to obtain the matching results.

[0047] In this embodiment 1, indicator data for each experimental group is continuously collected based on pre-set quantitative evaluation information. This process ensures that all relevant data is accurately recorded, forming the initial data for multiple operational strategies. Subsequently, the collected initial data is compared with the target rules. This comparison step aims to identify whether the actual performance of each experimental group meets or deviates from expectations, thereby generating matching results. The matching results are a key basis for subsequent dynamic traffic adjustment decisions, reflecting the degree of consistency between the experimental strategies and business operation goals.

[0048] Step S204: Adjust the user traffic allocation ratio of multiple experimental groups based on the matching results.

[0049] In this embodiment 1, based on the matching results, the degree of conformity between the experimental group's indicator data and the target rules is analyzed. For example, for experimental groups that meet or exceed expectations, their traffic allocation ratio is increased to enhance the testing intensity of the strategy. Through continuous monitoring and timely adjustments, the experiment optimizes traffic configuration while ensuring business stability, promoting the efficient achievement of operational goals.

[0050] Optionally, in the user traffic adjustment method provided in Embodiment 1 of this application, determining quantitative evaluation information based on operational objectives includes: determining target indicators, and determining warning thresholds and expected changes of target indicators, wherein the target indicators include at least: a first type of indicator and a second type of indicator, the first type of indicator being used to evaluate the business operation effectiveness of the operational strategy, and the second type of indicator being used to evaluate the degree of negative impact of the operational strategy; determining indicator weight information based on the target indicators, multiple operational strategies, and operational objectives; and determining quantitative evaluation information based on the target indicators, warning thresholds, expected changes, and indicator weight information.

[0051] In this embodiment 1, the aim is to optimize the decision-making mechanism of the A / B testing system. First, the target indicators are defined as two categories: Category 1 indicators and Category 2 indicators. Category 1 indicators, also known as core indicators (core objectives), are specifically used to measure the impact of specific operational strategies on business operations, such as conversion rates and retention rates. Category 2 indicators, also known as guardrail indicators, focus on examining the potential adverse effects of strategy implementation, including but not limited to decreased user experience and functional stability risks. For each indicator, a warning threshold is established, representing the degree to which the indicator deviates from its normal range due to adjustments in the operational strategy, and an expected change is set, clearly defining the minimum benefit standard required for the strategy to succeed.

[0052] By setting the minimum detectable effect (MDE) and business expectations, quantitative assessment information provides a benchmark for evaluating the degree to which operational goals are achieved, thereby supporting data-driven decision-making, optimizing resource allocation, and enabling dynamic adjustments during the implementation of operational strategies to ensure goal achievement.

[0053] For example, core objectives may include customer conversion rate and customer retention rate. Guardrail metrics may include user experience metrics. The warning threshold for changes in traffic can be set to 1%, meaning a decrease in traffic cannot exceed 1%. The warning threshold for critical function error rate can be set to 0.5%, meaning a critical function error rate cannot exceed 0.5%. Expected changes can define the minimum Detectable Effect (MDE) and the business expectation. For example, the expected change in registration conversion rate is at least 3% (MDE), with a target increase of 5% (business expectation).

[0054] Then, based on the diversity of operational goals and strategies, indicator weight information is constructed. This step requires in-depth analysis of the importance of each indicator to the achievement of the overall goal and the cost and risk relationship of strategy implementation. Based on this, different weight values ​​are assigned to various indicators to achieve a reasonable balance in multi-objective decision-making.

[0055] Secondly, by combining the target indicators, warning thresholds, expected changes, and indicator weights, quantitative evaluation information is generated. This quantitative evaluation information serves as the standard for experimental evaluation; it integrates the expected state and weight information of all target indicators to guide experimental data collection and subsequent strategy performance evaluation.

[0056] Finally, as the experiment progressed, the experimental group's indicator data was continuously collected and analyzed based on quantitative evaluation information, and compared with preset warning thresholds and expected changes. Based on the comparison results, the experimental system could provide real-time feedback, such as dynamically adjusting traffic flow, triggering early warning mechanisms, or maintaining the status quo, ensuring that the implementation of operational strategies was both effective and risk-controlled.

[0057] Through the above steps, the A / B testing system has been transformed from passive feedback to active control, improving the timeliness and accuracy of experimental decisions, ultimately promoting the optimization of business operation results, while effectively preventing the negative impacts that may be caused by strategy adjustments. This achieves the technical effect of improving experimental efficiency and effectiveness and ensuring the steady development of business.

[0058] Optionally, in the user traffic adjustment method provided in Embodiment 1 of this application, determining indicator weight information based on target indicators, multiple operational strategies, and operational goals includes: determining the degree of influence of target indicators on operational goals; determining cost information of target indicators, wherein the cost information includes at least: development cost information and implementation risk information; determining priority information of target indicators based on the degree of influence and cost information; and determining indicator weight information of target indicators based on priority information.

[0059] In this 1st embodiment, the aim is to optimize the A / B testing mechanism to ensure that the adjustment of operational strategies can closely align with business objectives, while taking into account cost and risk control. First, the target indicators are analyzed in detail to quantify their contribution to the overall operational objectives, i.e., the degree of influence.

[0060] Then, comprehensively consider the costs required to achieve the target indicators, including development cost information, i.e., the direct resource input (e.g., human resources or equipment resources) to achieve indicator improvement or strategy change, and implementation risk information, referring to the potential adverse consequences that may be caused by strategy adjustments, such as a decline in user experience or system stability risks. The determination of cost information needs to be based on historical data, expert evaluation, and market trend forecasts, etc., to ensure the comprehensiveness and accuracy of the decision-making basis.

[0061] Secondly, based on a comprehensive analysis of the impact of target indicators and cost information, the priority information of each indicator is determined. This process involves constructing a priority matrix, which identifies key indicators with high impact, low cost, and low risk by comparing their contribution to business objectives with their implementation costs / risks, and assigns them higher priority, while inefficient or high-risk indicators are ranked lower priority.

[0062] Finally, based on the priority information, indicator weights are assigned to each target indicator. Weight allocation must follow scientific principles, ensuring that the weights of high-priority indicators are significantly higher than those of low-priority indicators. This allows for greater emphasis on indicators crucial to achieving business objectives during performance analysis, thus achieving a reasonable balance in multi-objective decision-making.

[0063] Through the above steps, it is ensured that, under the condition of limited resources, the A / B testing system can prioritize and vigorously promote the implementation of strategies that contribute significantly to business objectives, have low implementation costs, and controllable risks, while remaining vigilant against strategies that may cause negative impacts and taking timely measures, thus achieving the dual goals of promoting business growth and ensuring operational safety.

[0064] Optionally, in the user traffic adjustment method provided in Embodiment 1 of this application, the first data is matched with the target rule to obtain the matching result, including: for the first type of indicator and the second indicator of the target experimental group, when the change of the first type of indicator is greater than its expected change and the second type of indicator does not exceed its warning threshold, the first data is determined to be successfully matched with the first rule, wherein the target experimental group is any experimental group among multiple experimental groups; when the second type of indicator exceeds its warning threshold, the first data is determined to be successfully matched with the second rule; when the change of the first type of indicator is less than its expected change and the change of the first type of indicator is greater than a preset value and the second type of indicator does not exceed its warning threshold, the first data is determined to be successfully matched with the third rule; when the change of the first indicator is greater than its expected change and the second indicator does not exceed its warning threshold, the first data is determined to be successfully matched with the fourth rule, wherein both the first indicator and the second indicator belong to the first type of indicator, and the first indicator and the second indicator are different.

[0065] In this embodiment 1, in order to achieve dynamic traffic adjustment for A / B experiments based on operational objectives and ensure that strategy optimization is both effective and risk-controllable, the change in the first type of indicator for each target experimental group is first monitored in real time. When the change is better than expected (for example, the change in the first type of indicator is greater than its expected change), it has a positive impact on the business operation effect. Furthermore, if the second type of indicator, which reflects the negative impact of the strategy, does not reach the preset warning threshold (equivalent to the second type of indicator not exceeding its warning threshold), then it is determined that the experimental data matches the first rule successfully.

[0066] Then, the status of the second type of indicators is continuously verified. If these indicators exceed their warning thresholds during the experiment, it is determined that the experimental data matches the second rule successfully.

[0067] Secondly, if the change in the first type of indicator does not meet the standard but shows a positive trend (i.e., the change in the first type of indicator is less than its expected change and the change in the first type of indicator is greater than the preset value of 0, which is equivalent to showing a positive trend), and the second type of indicator does not break through the warning threshold (i.e., the second type of indicator does not exceed its warning threshold), it is determined that the first data and the third rule are successfully matched.

[0068] Finally, we focus on the overall changes among different indicators in the first category. For the same target experimental group, there are multiple core targets and inconsistent results. That is, the change in the first indicator is greater than its expected change, while the second indicator, as another indicator in the same category, does not exceed its warning threshold. In this case, we determine that the first data and the fourth rule are successfully matched.

[0069] Through the above steps, the A / B testing system achieved refined control over strategy adjustment and dynamic traffic allocation, ensuring effect monitoring and risk warning during the operational strategy optimization process. This achieved the technical effect of effectively managing negative impacts and dynamically balancing resource allocation while improving business performance, thus realizing the dual goals of business growth and operational security.

[0070] Optionally, in the user traffic adjustment method provided in Embodiment 1 of this application, adjusting the user traffic allocation ratio of multiple experimental groups based on the matching result includes: when the first data successfully matches the first rule, increasing the user traffic allocation ratio of the target experimental group and decreasing the user traffic allocation ratio of other experimental groups; when the first data successfully matches the second rule, adjusting the user traffic allocation ratio of multiple experimental groups based on the historical allocation ratio and sending risk warning information to the target object; when the first data successfully matches the third rule, allocating user traffic to multiple experimental groups based on the current user traffic allocation ratio; when the first data successfully matches the fourth rule, performing a weighted calculation on the first data, and using the calculation result to match the target rule again, adjusting the user traffic allocation ratio of multiple experimental groups based on the matching result.

[0071] In this embodiment 1, to dynamically optimize the traffic allocation strategy in the A / B experiment and ensure efficient resource utilization and controllable risks, the traffic allocation ratio is automatically adjusted when the experimental data matches the set first rule. More resources are allocated to strategies with better performance, increasing the traffic for high-performing experimental groups, while correspondingly reducing the traffic share of other experimental groups that do not meet expectations. This mechanism, through dynamic balancing, concentrates resources on effective strategies to accelerate the verification and promotion of their benefits.

[0072] Then, when the experimental data meets the second rule—that is, when the second type of indicator exceeds its warning threshold—it means that the current strategy has a significant negative impact and user traffic needs to be reallocated. In this case, the user traffic allocation ratio is rolled back to the historical allocation ratio. Furthermore, if a control group exists, the user traffic allocation ratio can also be rolled back to the control group's allocation ratio. After rolling back the user traffic allocation ratio, a risk warning is sent to relevant decision-makers (i.e., the target group mentioned above), alerting them to potential ineffective resource allocation and prompting them to pay attention and potentially take further strategy optimization or experimental design adjustments.

[0073] Secondly, when the experimental data matches the third rule, that is, when the first type of indicator has not achieved significant improvement but the trend is positive, and the risk of the second type of indicator is controllable, the current traffic allocation remains unchanged, and data continues to be collected to verify the stability of the trend and the long-term effect, so as to avoid making premature traffic adjustments due to short-term fluctuations and maintain the consistency of strategy implementation and the integrity of data.

[0074] Finally, for complex experiments involving multiple Category I indicators, when the data matches the fourth rule (i.e., there is an inconsistency in the trend of the effects of Category I indicators), a weighted calculation is performed on all Category I indicators. The weights of each indicator are comprehensively considered to evaluate the overall impact of the strategy. Based on a re-matching of the weighted calculation results with the predetermined target rules, the traffic allocation ratio is dynamically adjusted according to the matching results. This ensures that resource allocation reflects the overall effectiveness of the strategy and can be adjusted in a timely manner to cope with complex experimental results, achieving a balanced optimization of multiple objectives.

[0075] Through the above steps, the technical effects of adjusting traffic allocation in real time based on experimental results, promoting efficient resource utilization, and providing early warning and control of potential risks are achieved. This realizes the automation and intelligence of the A / B testing process, enhances the adaptability and flexibility of the testing process to operational strategy optimization, and further improves the consistency between strategy execution and business objectives.

[0076] Optionally, in the user traffic adjustment method provided in Embodiment 1 of this application, the user traffic allocation ratio of multiple experimental groups is adjusted according to the historical allocation ratio, and risk warning information is sent to the target object. This includes: adjusting the user traffic allocation ratio of multiple experimental groups to a preset allocation ratio, collecting indicator data of multiple experimental groups, and obtaining second data of multiple operation strategies. The preset allocation ratio includes at least one of the following: initial allocation ratio, received allocation ratio, and allocation ratio of the control group; generating risk warning information based on the first data, and sending the second data and risk warning information to the target object.

[0077] In this embodiment 1, in order to ensure the reliability and safety of the A / B experiment and to provide comprehensive data support for decision-makers, the user traffic allocation ratio of the experimental group is first adjusted according to the preset allocation ratio. These allocation ratios include, but are not limited to: the initial allocation ratio set in the experiment initialization phase, the allocation ratio adjusted based on the latest experimental effect analysis, or the allocation ratio that is rolled back to the control group to restore the experimental baseline.

[0078] Next, we continue to collect metric data for each experimental group under the adjusted traffic distribution to form the second dataset. This step includes real-time monitoring of the experimental strategy's effectiveness, covering all target metrics, including first-category metrics (core performance metrics) and second-category metrics (guardrail metrics), ensuring that the collected data comprehensively reflects the actual performance of the experimental strategy after resetting the traffic.

[0079] Secondly, for any situation that triggers the risk warning mechanism, risk warning information will be generated based on the first data. This information will include, but is not limited to, the specific changes in the experimental group's indicators, the extent of deviation from the warning threshold, and a description of potential risks, providing decision-makers with an intuitive risk warning.

[0080] Finally, the second dataset and risk warning information are integrated and sent to the designated target audience, namely decision-makers or relevant staff. This data aggregation enables the recipients to fully understand the actual effectiveness and risk profile of the experimental strategy, providing a basis for further strategy adjustments or experimental design optimization.

[0081] Through the above steps, the safety management of the experimental process and data-driven decision support are effectively realized, ensuring that A / B experiments can identify and respond to potential risks in a timely manner while pursuing business objectives, thereby achieving the technical effect of promoting the healthy development of business.

[0082] Optionally, in the user traffic adjustment method provided in Embodiment 1 of this application, multiple experimental groups are created based on multiple operational strategies, including: determining the experimental type of multiple operational strategies based on the complexity of the multiple operational strategies and the characteristics of the user group, wherein the multiple operational strategies include: operational strategies for web pages, operational strategies for application functions, and operational strategies for deep learning models or preset algorithms; determining the experimental mode of multiple operational strategies based on the experimental type of multiple operational strategies, and defining experimental parameters, wherein the experimental mode includes at least one of the following: user-triggered mode and push mode; determining the experimental duration based on multiple operational strategies and business needs; and creating multiple experimental groups based on the experimental type, experimental mode, and experimental duration of multiple operational strategies.

[0083] In this Example 1, to accurately match the operational strategy with the experimental design and ensure the effectiveness and relevance of the A / B experiment, the experiment type is first determined based on the complexity of the strategy and the characteristics of the target user group. This process involves a detailed analysis of the strategy, such as webpage optimization strategies, application function adjustment strategies, or deep learning model update strategies, while also considering the diversity of the user group, such as usage habits and preferences, to ensure that the experimental design can comprehensively cover the potential impact area of ​​the strategy implementation and improve the representativeness and reliability of the experimental results.

[0084] Then, based on the determined experiment type, select or customize the experiment mode and define the experiment parameters. The choice of experiment mode, such as user-triggered mode or push mode, must match the implementation method of the strategy to ensure the accuracy of the experimental data and the controllability of the experimental process. The definition of experiment parameters includes key indicators such as traffic allocation ratio, experimental group size, and experimental objectives, providing specific operational guidelines for the execution of the experiment and ensuring the scientific nature of the experimental design and the analyzability of the experimental results.

[0085] Secondly, the duration of the experiment should be determined by comprehensively considering factors such as the nature of the strategy and business needs. The duration of the experiment needs to balance the thorough validation of the strategy's effectiveness with a rapid response to market changes, ensuring that sufficient data is collected within a limited timeframe, while also enabling timely adjustments to the strategy based on the experimental results, thereby enhancing the experiment's guiding value for business decisions.

[0086] Finally, based on a comprehensive consideration of the experiment type, mode, duration, and parameters, multiple experimental groups were created, including a control group and multiple test groups. The design of each experimental group must strictly follow statistical principles to ensure the randomness of traffic allocation and the consistency of user characteristics, thereby eliminating experimental bias and ensuring the objectivity and validity of the experimental results.

[0087] Through the above steps, the technical effect of refined operational strategy experimental design was achieved, ensuring the scientific nature of the experimental process and the reliability of the experimental results, providing solid data support for business decision-making, and realizing the goal of accurately evaluating and optimizing operational strategies.

[0088] Optionally, in this embodiment 1, Figure 3 This is a schematic diagram of an optional dynamic user traffic adjustment process provided in Embodiment 1 of this application. Figure 3As shown, the process begins with setting operational goals, creating the basic framework for the A / B experiment. This is the starting point of the entire process, ensuring consistency between the experimental design and business needs. Next, the experiment enters the traffic allocation phase, where users are randomly assigned to different experimental groups, including a control group and a test group, to collect comparative data and verify the strategy's effectiveness. Then, during the experiment, quantitative analysis is performed based on the real-time collected performance data. Finally, based on the results of the performance analysis, user traffic to each experimental group is automatically or semi-automatically adjusted to optimize resource allocation, improve strategy effectiveness, and control risks to ensure the achievement of operational goals. This flowchart visually demonstrates the core concept and operating mechanism of the invention's technical solution: achieving efficient iteration and strategy optimization of A / B experiments through goal-driven approaches, data support, intelligent analysis, and dynamic adjustment.

[0089] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0090] In summary, the user traffic adjustment method provided in this application addresses the problem in related technologies where adjusting user traffic for operational strategies requires frequent analysis of indicator data, resulting in low efficiency. This is achieved by: determining operational objectives for multiple operational strategies and establishing quantitative evaluation information based on these objectives; creating multiple experimental groups based on these strategies and randomly allocating user traffic to them based on traffic balancing principles; collecting indicator data from multiple experimental groups based on the quantitative evaluation information to obtain first data for each operational strategy; matching this first data with target rules to obtain matching results; and adjusting the user traffic allocation ratio for multiple experimental groups based on the matching results.

[0091] By defining the operational objectives of multiple operational strategies and setting quantitative evaluation information accordingly, the experimental design can be systematically guided, achieving the technical effect of clarifying the experimental direction and expected results. Continuously collecting experimental group indicator data and matching it with target rules to obtain matching results allows for objective evaluation of strategy implementation, enabling dynamic strategy adjustment based on empirical analysis. This further enhances operational flexibility and improves strategy success rate. Finally, dynamically adjusting the user traffic allocation ratio for each experimental group based on the matching results ensures that resources are concentrated on the best-performing strategy, further improving operational efficiency.

[0092] Example 2

[0093] This application also provides a user traffic adjustment device. It should be noted that the user traffic adjustment device of this application can be used to execute the user traffic adjustment method provided in this application. The user traffic adjustment device provided in this application is described below.

[0094] According to an embodiment of this application, an apparatus for implementing the above-described user traffic adjustment method is also provided. Figure 4 This is a schematic diagram of a user traffic adjustment device according to Embodiment 2 of this application. Figure 4 As shown, the device includes: a determining unit 401, an allocation unit 402, a matching unit 403, and an adjustment unit 404.

[0095] Specifically, the determination unit 401 is used to determine the operational objectives of multiple operational strategies and to determine quantitative evaluation information based on the operational objectives.

[0096] The allocation unit 402 is used to create multiple experimental groups based on multiple operational strategies and to randomly allocate user traffic to multiple experimental groups based on the principle of traffic balancing.

[0097] The matching unit 403 is used to collect indicator data from multiple experimental groups based on quantitative evaluation information, obtain the first data of multiple operational strategies, and match the first data with the target rules to obtain the matching results.

[0098] Adjustment unit 404 is used to adjust the user traffic allocation ratio of multiple experimental groups based on the matching results.

[0099] The user traffic adjustment device provided in this application embodiment determines the operational objectives of multiple operational strategies by a determining unit 401 and determines quantitative evaluation information based on the operational objectives; an allocation unit 402 creates multiple experimental groups based on multiple operational strategies and randomly allocates user traffic to multiple experimental groups based on the principle of traffic balance; a matching unit 403 collects indicator data of multiple experimental groups based on the quantitative evaluation information to obtain the first data of multiple operational strategies, and matches the first data with the target rules to obtain the matching result; and an adjustment unit 404 adjusts the user traffic allocation ratio of multiple experimental groups based on the matching result. This solves the problem in related technologies where adjusting user traffic for operational strategies requires business personnel to frequently analyze and adjust methods based on indicator data, resulting in low efficiency in traffic adjustment.

[0100] By defining the operational objectives of multiple operational strategies and setting quantitative evaluation information accordingly, the experimental design can be systematically guided, achieving the technical effect of clarifying the experimental direction and expected results. Continuously collecting experimental group indicator data and matching it with target rules to obtain matching results allows for objective evaluation of strategy implementation, enabling dynamic strategy adjustment based on empirical analysis. This further enhances operational flexibility and improves strategy success rate. Finally, dynamically adjusting the user traffic allocation ratio for each experimental group based on the matching results ensures that resources are concentrated on the best-performing strategy, further improving operational efficiency.

[0101] Optionally, in the user traffic adjustment device provided in Embodiment 2 of this application, the aforementioned determining unit 402 includes: a first determining subunit, used to determine a target indicator and determine the warning threshold and expected change amount of the target indicator, wherein the target indicator includes at least: a first type of indicator and a second type of indicator, the first type of indicator being used to evaluate the business operation effect of the operation strategy, and the second type of indicator being used to evaluate the degree of negative impact of the operation strategy; a second determining subunit, used to determine indicator weight information based on the target indicator, multiple operation strategies and operation objectives; and a third determining subunit, used to determine quantitative evaluation information based on the target indicator, the warning threshold, the expected change amount and the indicator weight information.

[0102] Optionally, in the user traffic adjustment device provided in Embodiment 2 of this application, the second determining subunit includes: a first determining module for determining the degree of influence of the target indicator on the operational target; a second determining module for determining the cost information of the target indicator, wherein the cost information includes at least: development cost information and implementation risk information; a third determining module for determining the priority information of the target indicator based on the degree of influence and the cost information; and a fourth determining module for determining the indicator weight information of the target indicator based on the priority information.

[0103] Optionally, in the user traffic adjustment device provided in Embodiment 2 of this application, the matching unit 403 includes: a fourth determining subunit, used to determine that the first data matches the first rule successfully when the change in the first type of indicator is greater than its expected change and the second type of indicator does not exceed its warning threshold, for the first type of indicator and the second indicator of the target experimental group; a fifth determining subunit, used to determine that the first data matches the second rule successfully when the second type of indicator exceeds its warning threshold; a sixth determining subunit, used to determine that the first data matches the third rule successfully when the change in the first type of indicator is less than its expected change and the change in the first type of indicator is greater than a preset value and the second type of indicator does not exceed its warning threshold; and a seventh determining subunit, used to determine that the first data matches the fourth rule successfully when the change in the first indicator is greater than its expected change and the second indicator does not exceed its warning threshold, wherein both the first indicator and the second indicator belong to the first type of indicator, and the first indicator and the second indicator are different.

[0104] Optionally, in the user traffic adjustment device provided in Embodiment 2 of this application, the adjustment unit 404 includes: a first adjustment subunit, used to increase the user traffic allocation ratio of the target experimental group and decrease the user traffic allocation ratio of other experimental groups when the first data successfully matches the first rule; a second adjustment subunit, used to adjust the user traffic allocation ratio of multiple experimental groups according to the historical allocation ratio when the first data successfully matches the second rule, and send risk warning information to the target object; a third adjustment subunit, used to allocate user traffic to multiple experimental groups according to the current user traffic allocation ratio when the first data successfully matches the third rule; and a fourth adjustment subunit, used to perform weighted calculation on the first data when the first data successfully matches the fourth rule, and use the calculation result to match the target rule again, and adjust the user traffic allocation ratio of multiple experimental groups according to the matching result.

[0105] Optionally, in the user traffic adjustment device provided in Embodiment 2 of this application, the second adjustment subunit includes: an adjustment module, used to adjust the user traffic allocation ratio of multiple experimental groups to a preset allocation ratio, and collect indicator data of multiple experimental groups to obtain second data of multiple operation strategies, wherein the preset allocation ratio includes at least one of the following: initial allocation ratio, received allocation ratio, and allocation ratio of the control group; and a generation module, used to generate risk warning information based on the first data, and send the second data and risk warning information to the target object.

[0106] Optionally, in the user traffic adjustment device provided in Embodiment 2 of this application, the allocation unit 402 includes: an eighth determining subunit, used to determine the experiment type of multiple operation strategies based on the complexity of multiple operation strategies and user group characteristics, wherein the multiple operation strategies include: operation strategies for web pages, operation strategies for application functions, and operation strategies for deep learning models or preset algorithms; a ninth determining subunit, used to determine the experiment mode of multiple operation strategies based on the experiment type of multiple operation strategies, and define experiment parameters, wherein the experiment mode includes at least one of the following: user trigger mode and push mode; a tenth determining subunit, used to determine the experiment duration based on multiple operation strategies and business needs; and a creation subunit, used to create multiple experiment groups based on the experiment type, experiment mode, and experiment duration of multiple operation strategies.

[0107] It should be noted that the aforementioned determining unit 401, allocation unit 402, matching unit 403, and adjustment unit 404 correspond to steps S201 to S204 in Embodiment 1. The two modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the aforementioned modules or units may be hardware or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The aforementioned modules may also be part of a device and can run in the computer terminal 10 provided in Embodiment 1.

[0108] Example 3

[0109] Embodiments of this application may provide an electronic device. Figure 5 This is a schematic diagram of an electronic device for adjusting user traffic according to Embodiment 3 of this application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (Only one is shown) processor 502, memory 504, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0110] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal 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.

[0111] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: determine the operational objectives of multiple operational strategies and determine quantitative evaluation information based on the operational objectives; create multiple experimental groups based on multiple operational strategies and randomly allocate user traffic to multiple experimental groups based on the principle of traffic balancing; collect indicator data of multiple experimental groups based on the quantitative evaluation information to obtain the first data of multiple operational strategies, and match the first data with the target rules to obtain the matching results; adjust the user traffic allocation ratio of multiple experimental groups based on the matching results.

[0112] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: determining quantitative evaluation information based on operational objectives, including: determining target indicators and determining warning thresholds and expected changes for the target indicators, wherein the target indicators include at least: a first type of indicator and a second type of indicator, the first type of indicator being used to evaluate the business operational effectiveness of the operational strategy, and the second type of indicator being used to evaluate the degree of negative impact of the operational strategy; determining indicator weight information based on the target indicators, multiple operational strategies, and operational objectives; and determining quantitative evaluation information based on the target indicators, warning thresholds, expected changes, and indicator weight information.

[0113] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: determining indicator weight information based on target indicators, multiple operational strategies, and operational objectives, including: determining the degree of impact of target indicators on operational objectives; determining cost information of target indicators, wherein the cost information includes at least: development cost information and implementation risk information; determining priority information of target indicators based on the degree of impact and cost information; and determining indicator weight information of target indicators based on the priority information.

[0114] The processor can access information and applications stored in the memory via a transmission device to execute the following steps: matching first data with target rules to obtain matching results, including: for the first and second indicators of the target experimental group, when the change in the first type of indicator is greater than its expected change and the second type of indicator does not exceed its warning threshold, determining that the first data and the first rule are successfully matched, wherein the target experimental group is any experimental group among multiple experimental groups; when the second type of indicator exceeds its warning threshold, determining that the first data and the second rule are successfully matched; when the change in the first type of indicator is less than its expected change and the change in the first type of indicator is greater than a preset value and the second type of indicator does not exceed its warning threshold, determining that the first data and the third rule are successfully matched; when the change in the first indicator is greater than its expected change and the second indicator does not exceed its warning threshold, determining that the first data and the fourth rule are successfully matched, wherein both the first and second indicators belong to the first type of indicator, and the first and second indicators are different.

[0115] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: adjusting the user traffic allocation ratio of multiple experimental groups based on the matching results, including: when the first data successfully matches the first rule, increasing the user traffic allocation ratio of the target experimental group and decreasing the user traffic allocation ratio of other experimental groups; when the first data successfully matches the second rule, adjusting the user traffic allocation ratio of multiple experimental groups based on historical allocation ratios and sending risk warning information to the target group; when the first data successfully matches the third rule, allocating user traffic to multiple experimental groups based on the current user traffic allocation ratio; when the first data successfully matches the fourth rule, performing a weighted calculation on the first data, and using the calculation result to match the target rule again, adjusting the user traffic allocation ratio of multiple experimental groups based on the matching results.

[0116] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: adjusting the user traffic allocation ratio of multiple experimental groups according to historical allocation ratios and sending risk warning information to the target, including: adjusting the user traffic allocation ratio of multiple experimental groups to a preset allocation ratio, collecting indicator data of multiple experimental groups, and obtaining second data of multiple operational strategies, wherein the preset allocation ratio includes at least one of the following: initial allocation ratio, received allocation ratio, and allocation ratio of the control group; generating risk warning information based on the first data, and sending the second data and risk warning information to the target.

[0117] The processor can access information and applications stored in memory via a transmission device to execute the following steps: creating multiple experimental groups based on multiple operational strategies, including: determining the experimental types of multiple operational strategies based on the complexity of the multiple operational strategies and user group characteristics, wherein the multiple operational strategies include: operational strategies for web pages, operational strategies for application functions, and operational strategies for deep learning models or preset algorithms; determining the experimental modes of multiple operational strategies based on the experimental types of multiple operational strategies, and defining experimental parameters, wherein the experimental modes include at least one of the following: user-triggered mode and push mode; determining the experimental duration based on multiple operational strategies and business needs; and creating multiple experimental groups based on the experimental types, experimental modes, and experimental durations of multiple operational strategies.

[0118] This application provides a method for adjusting user traffic. It involves determining the operational goals of multiple operational strategies and establishing quantitative evaluation information based on these goals; creating multiple experimental groups based on these strategies and randomly allocating user traffic to these groups based on a traffic balancing principle; collecting indicator data from the experimental groups based on the quantitative evaluation information to obtain first data for each operational strategy; matching this first data with target rules to obtain matching results; and adjusting the user traffic allocation ratio among the experimental groups based on the matching results. This method solves the technical problem of low efficiency in adjusting user traffic when operational strategies require frequent analysis of indicator data by business personnel.

[0119] By defining the operational objectives of multiple operational strategies and setting quantitative evaluation information accordingly, the experimental design can be systematically guided, achieving the technical effect of clarifying the experimental direction and expected results. Continuously collecting experimental group indicator data and matching it with target rules to obtain matching results allows for objective evaluation of strategy implementation, enabling dynamic strategy adjustment based on empirical analysis. This further enhances operational flexibility and improves strategy success rate. Finally, dynamically adjusting the user traffic allocation ratio for each experimental group based on the matching results ensures that resources are concentrated on the best-performing strategy, further improving operational efficiency.

[0120] Those skilled in the art will understand that Figure 5 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 5 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 5 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 5 The different configurations shown.

[0121] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0122] Example 4

[0123] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the user traffic adjustment method provided in Embodiment 1.

[0124] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0125] This application also provides a computer program product, which, when executed on a data processing device, is adapted to perform steps of a method for adjusting user traffic.

[0126] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0127] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0129] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0131] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0132] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of adjusting user traffic, characterized by, The method comprises the following steps: determining operation targets of a plurality of operation strategies, and determining quantitative evaluation information according to the operation targets; creating a plurality of experimental groups according to the plurality of operation strategies, and randomly allocating user traffic to the plurality of experimental groups based on a traffic balancing principle; collecting index data of the plurality of experimental groups according to the quantitative evaluation information, obtaining first data of the plurality of operation strategies, and matching the first data with target rules to obtain a matching result; adjusting user traffic allocation proportions of the plurality of experimental groups according to the matching result.

2. The method of claim 1, wherein, The method comprises the following steps: determining target indexes, and determining alert thresholds and expected change amounts of the target indexes, wherein the target indexes at least include first indexes and second indexes, the first indexes are used to evaluate business operation effects of operation strategies, and the second indexes are used to evaluate negative influence degrees of operation strategies; determining index weight information according to the target indexes, the plurality of operation strategies and the operation targets; determining the quantitative evaluation information according to the target indexes, the alert thresholds, the expected change amounts and the index weight information.

3. The method of claim 2, wherein, The method comprises the following steps: determining influence degrees of the target indexes on the operation targets; determining cost information of the target indexes, wherein the cost information at least includes development cost information and implementation risk information; determining priority information of the target indexes according to the influence degrees and the cost information; determining index weight information of the target indexes according to the priority information.

4. The method of claim 2, wherein, The method comprises the following steps: for the first indexes and the second indexes of a target experimental group, when a change amount of the first indexes is greater than an expected change amount of the first indexes, and the second indexes do not exceed the alert thresholds of the second indexes, it is determined that the first data matches first rules successfully, wherein the target experimental group is any experimental group in the plurality of experimental groups; when the second indexes exceed the alert thresholds of the second indexes, it is determined that the first data matches second rules successfully; when the change amount of the first indexes is less than the expected change amount of the first indexes, and the change amount of the first indexes is greater than a preset value, and the second indexes do not exceed the alert thresholds of the second indexes, it is determined that the first data matches third rules successfully; when a change amount of first indexes is greater than an expected change amount of the first indexes, and second indexes do not exceed the alert thresholds of the second indexes, it is determined that the first data matches fourth rules successfully, wherein the first indexes and the second indexes both belong to the first indexes, and the first indexes are different from the second indexes.

5. The method of claim 4, wherein, The method comprises the following steps: when the first data matches the first rules successfully, the user traffic allocation proportion of the target experimental group is increased, and the user traffic allocation proportions of other experimental groups are reduced. When the first data matches the second rule successfully, the user traffic distribution proportion of the multiple experimental groups is adjusted according to a historical distribution proportion, and risk prompt information is sent to the target object; When the first data matches the third rule successfully, the user traffic is distributed to the multiple experimental groups according to a current user traffic distribution proportion; When the first data matches the fourth rule successfully, the first data is weighted and calculated, and the calculation result is matched with the target rule again, and the user traffic distribution proportion of the multiple experimental groups is adjusted according to the matching result.

6. The method of claim 5, wherein, The method for adjusting user traffic comprises the following steps: The user traffic distribution proportion of the multiple experimental groups is adjusted to a preset distribution proportion, and index data of the multiple experimental groups is collected to obtain second data of the multiple operation strategies, wherein the preset distribution proportion at least includes one of the following: an initial distribution proportion, a received distribution proportion, and a distribution proportion of a control group; Risk prompt information is generated according to the first data, and the second data and the risk prompt information are sent to the target object.

7. The method of claim 1, wherein, The multiple experimental groups are created according to the multiple operation strategies, comprising the following steps: The experiment types of the multiple operation strategies are determined according to the complexity of the multiple operation strategies and the characteristics of a user group, wherein the multiple operation strategies include: an operation strategy for a webpage, an operation strategy for an application program function, and an operation strategy for a deep learning model or a preset algorithm; The experiment modes of the multiple operation strategies are determined according to the experiment types of the multiple operation strategies, and experiment parameters are defined, wherein the experiment modes at least include one of the following: a user trigger mode and a push mode; The experiment duration is determined according to the multiple operation strategies and business requirements; The multiple experimental groups are created according to the experiment types, the experiment modes, and the experiment duration of the multiple operation strategies.

8. An apparatus for adjusting user traffic, characterized by comprising: Comprise: A determination unit is configured to determine operation targets of multiple operation strategies, and determine quantitative evaluation information according to the operation targets; An allocation unit is configured to create multiple experimental groups according to the multiple operation strategies, and randomly distribute user traffic to the multiple experimental groups based on a traffic balancing principle; A matching unit is configured to collect index data of the multiple experimental groups to obtain first data of the multiple operation strategies according to the quantitative evaluation information, and match the first data with a target rule to obtain a matching result; An adjustment unit is configured to adjust a user traffic distribution proportion of the multiple experimental groups according to the matching result.

9. An electronic device, comprising: Comprise: A memory storing an executable program; A processor is configured to run the program, wherein the program performs the method for adjusting user traffic of any one of claims 1 to 7 when running.

10. A computer program product comprising computer instructions, characterized in that, The computer instructions are executed by the processor to implement the steps of the method for adjusting user traffic of any one of claims 1 to 7. The computer instructions are executed by the processor to implement the steps of the method for adjusting user traffic of any one of claims 1 to 7.

Images