Commission payment method and device, electronic equipment and storage medium

Abstract

One or more embodiments of the present application provide a commission payment method and device, electronic equipment and storage medium, the method comprising: periodically obtaining sales data corresponding to a sales party according to a preset commission settlement period; determining a sales scenario corresponding to the sales data, and obtaining a commission calculation rule corresponding to the sales scenario; wherein the commission calculation rule is based on an adaptive optimization algorithm, and is optimized and calculated for a plurality of historical commission data samples and a plurality of historical sales data samples generated in the sales scenario to obtain a commission calculation rule with the highest matching degree for the sales scenario; determining the commission data corresponding to the sales party according to the commission calculation rule; and transferring the commission specified by the commission data from the account of the management party to the account of the sales party.

Description

Technical Field

[0001] One or more embodiments of this application relate to the field of computer application technology, and in particular to a commission payment method, apparatus, electronic device and storage medium. Background Technology

[0002] Commissions are a form of compensation paid to salespeople or other relevant parties based on sales performance or other performance indicators. They are widely used across various industries, particularly sales, real estate, and insurance. This compensation method links earnings to work results, embodying the principle of "more work, more pay." It is typically used as part of an incentive mechanism in business activities, aiming to encourage employees to work more proactively and achieve higher performance goals through financial rewards.

[0003] In practical applications, for both the management and sales parties in business activities, the management typically prefers to pay less commission, while the sales party prefers to receive more. Therefore, there is a desire to improve the accuracy and reasonableness of commission payments from management to sales parties, achieving a balance between the commissions paid and the needs of both parties. Summary of the Invention

[0004] One or more embodiments of this application provide the following technical solutions:

[0005] This application provides a commission payment method, the method comprising:

[0006] According to the preset commission settlement cycle, regularly obtain the sales data corresponding to the seller;

[0007] Determine the sales scenario corresponding to the sales data and obtain the commission calculation rule corresponding to the sales scenario; wherein, the commission calculation rule is based on an adaptive optimization algorithm, which optimizes the calculation for several historical commission data samples and several historical sales data samples generated in the sales scenario, and obtains the commission calculation rule with the highest matching degree to the sales scenario.

[0008] The commission data corresponding to the seller is determined according to the commission calculation rules.

[0009] The commission specified in the commission data is transferred from the administrator's account to the seller's account.

[0010] This application also provides a commission payment method, the method comprising:

[0011] According to the preset commission settlement cycle, periodically obtain the sales data corresponding to the seller, and obtain the historical commission data corresponding to the seller;

[0012] The historical commission data and the sales data are input into the trained commission prediction model, and the commission prediction model predicts the commission data corresponding to the seller based on the historical commission data and the sales data.

[0013] The commission specified in the commission data is transferred from the administrator's account to the seller's account.

[0014] This application also provides a commission payment device, the device comprising:

[0015] The acquisition module periodically acquires sales data corresponding to the seller according to a preset commission settlement cycle;

[0016] The matching module determines the sales scenario corresponding to the sales data and obtains the commission calculation rule corresponding to the sales scenario; wherein, the commission calculation rule is based on an adaptive optimization algorithm, which optimizes the calculation for several historical commission data samples and several historical sales data samples generated in the sales scenario, and obtains the commission calculation rule with the highest matching degree to the sales scenario.

[0017] The calculation module determines the commission data corresponding to the seller according to the commission calculation rules;

[0018] The payment module transfers the commission specified in the commission data from the administrator's account to the seller's account.

[0019] This application also provides a commission payment device, the device comprising:

[0020] The acquisition module periodically acquires sales data corresponding to the seller according to a preset commission settlement cycle, and also acquires historical commission data corresponding to the seller.

[0021] The calculation module inputs the historical commission data and the sales data into the trained commission prediction model, and the commission prediction model predicts the commission data corresponding to the seller based on the historical commission data and the sales data.

[0022] The payment module transfers the commission specified in the commission data from the administrator's account to the seller's account.

[0023] This application also provides an electronic device, including:

[0024] processor;

[0025] Memory used to store processor-executable instructions;

[0026] The processor executes the executable instructions to implement the steps of the method as described in any of the preceding descriptions.

[0027] This application also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method as described in any of the preceding claims.

[0028] In the above technical solution, after obtaining the sales data corresponding to the seller according to the commission settlement cycle, the sales scenario corresponding to the sales data can be determined first, and then the commission calculation rule corresponding to the sales scenario can be obtained. The commission data corresponding to the seller can be determined according to the commission calculation rule, so that the commission specified by the commission data can be transferred from the administrator's account to the seller's account. The commission calculation rule can be based on an adaptive optimization algorithm, which optimizes the calculation for several historical commission data samples and several historical sales data samples generated in various sales scenarios to obtain the commission calculation rule with the highest matching degree to the sales scenario.

[0029] By adopting the above approach, on the one hand, commission calculation rules corresponding to different sales scenarios are introduced, making the commission calculation mechanism more diversified and personalized, thereby providing more accurate and reasonable commission settlement services. On the other hand, the commission calculation rule corresponding to a sales scenario is the commission calculation rule with the highest matching degree to that sales scenario obtained through adaptive optimization. Therefore, the accuracy and reasonableness of the commission determined according to this commission calculation rule and corresponding to the sales data generated in that sales scenario can be further guaranteed. Moreover, since the adaptive optimization algorithm itself has high computational efficiency, it can improve the generation and updating efficiency of commission calculation rules, thereby improving the response speed and flexibility of commission calculation. Attached Figure Description

[0030] The accompanying drawings used in the description of the exemplary embodiments will now be explained, wherein:

[0031] Figure 1 This is a schematic diagram illustrating a commission payment system according to an exemplary embodiment of this application.

[0032] Figure 2 This is a flowchart illustrating a commission payment method in an exemplary embodiment of this application.

[0033] Figure 3 This is a schematic diagram illustrating another commission payment system according to an exemplary embodiment of this application.

[0034] Figure 4 This is a flowchart illustrating another commission payment method in an exemplary embodiment of this application.

[0035] Figure 5 This is a schematic diagram of the structure of a device shown in an exemplary embodiment of this application.

[0036] Figure 6 This is a block diagram illustrating a commission payment device in an exemplary embodiment of this application.

[0037] Figure 7 This is a block diagram illustrating another commission payment device in an exemplary embodiment of this application. Detailed Implementation

[0038] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this application. Rather, they are merely examples consistent with some aspects of one or more embodiments of this application.

[0039] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this application in other embodiments. In some other embodiments, the methods may include more or fewer steps than those described in this application. Furthermore, a single step described in this application may be broken down into multiple steps in other embodiments; and multiple steps described in this application may be combined into a single step in other embodiments.

[0040] For both the managers and sellers of business activities, the managers typically want to pay less commission, while the sellers want to earn more.

[0041] Existing commission calculation systems typically use fixed or percentage rates when calculating commissions. While these methods are simple and direct, they lack flexibility and cannot meet diverse commission calculation needs.

[0042] In practice, a fixed commission rate means charging the same commission regardless of the transaction amount. This approach is generally unsuitable for all scenarios. Specifically, it's unfair to small transactions because the commission percentage is too high compared to larger transactions; while for large transactions, a fixed commission may not be enough to cover the service costs provided by the seller.

[0043] A percentage-based commission rate refers to charging commission based on a percentage of the transaction amount. While this seems fair, a uniform rate may not be suitable for all scenarios, depending on the product, service, or market conditions. For example, the sale of certain high-value goods may require more service investment, while low-value goods do not require as many resources, but a percentage-based fee does not accurately reflect this difference.

[0044] Because both of these methods are based on simple and direct rules, they are ill-suited for more complex sales models, such as promotional activities, membership tiers, and market-specific pricing strategies. Furthermore, in a volatile market environment, management may want to dynamically adjust commission rates based on different time periods, customer behavior, or other factors to optimize costs and revenues; however, existing commission calculation systems struggle to respond quickly to these changes.

[0045] To better adapt to various scenarios and enhance competitiveness, some management entities may introduce tiered commission structures, performance-based commission systems, or customized commission schemes for specific partners. However, existing commission calculation systems typically lack sufficient flexibility to support these new commission calculation needs.

[0046] Therefore, it is hoped that more diversified and personalized commission calculation mechanisms can be introduced, so as to provide more accurate and reasonable commission settlement services.

[0047] This application provides one or more embodiments of a technical solution for commission payment, thereby improving the accuracy and rationality of commission payments from management to sellers. Specifically, this application provides two commission calculation methods: one is a commission calculation method based on adaptive optimization and scenario matching, and the other is a commission calculation method based on machine learning.

[0048] In the technical solution for commission calculation based on adaptive optimization and scenario matching, after obtaining the sales data corresponding to the seller according to the commission settlement cycle, the sales scenario corresponding to the sales data can be determined first, and then the commission calculation rule corresponding to the sales scenario can be obtained. The commission data corresponding to the seller can be determined according to the commission calculation rule, so that the commission specified by the commission data can be transferred from the administrator's account to the seller's account. The commission calculation rule can be based on an adaptive optimization algorithm, which optimizes the calculation for several historical commission data samples and several historical sales data samples generated in various sales scenarios to obtain the commission calculation rule with the highest matching degree to the sales scenario.

[0049] By adopting the above approach, on the one hand, commission calculation rules corresponding to different sales scenarios are introduced, making the commission calculation mechanism more diversified and personalized, thereby providing more accurate and reasonable commission settlement services. On the other hand, the commission calculation rule corresponding to a sales scenario is the commission calculation rule with the highest matching degree to that sales scenario obtained through adaptive optimization. Therefore, the accuracy and reasonableness of the commission determined according to this commission calculation rule and corresponding to the sales data generated in that sales scenario can be further guaranteed. Moreover, since the adaptive optimization algorithm itself has high computational efficiency, it can improve the generation and updating efficiency of commission calculation rules, thereby improving the response speed and flexibility of commission calculation.

[0050] In the technical solution of commission calculation based on machine learning, after obtaining the sales data corresponding to the seller according to the commission settlement cycle and obtaining the historical commission data corresponding to the seller, the historical commission data and the sales data can be input into the trained commission prediction model. The commission prediction model predicts the commission data corresponding to the seller based on the historical commission data and the sales data, so that the commission specified by the commission data can be transferred from the manager's account to the seller's account.

[0051] By using the above method to build a commission prediction model through machine learning, and then using this model to determine the commission corresponding to the sales data, the accuracy and reasonableness of the determined commission can be guaranteed, thereby providing a more accurate and reasonable commission settlement service.

[0052] The following sections explain the two commission calculation methods and the corresponding commission payment process.

[0053] I. Commission Calculation Method Based on Adaptive Optimization and Scenario Matching and Corresponding Commission Payment Process

[0054] Please refer to Figure 1 , Figure 1 This is a schematic diagram illustrating a commission payment system according to an exemplary embodiment of this application.

[0055] like Figure 1As shown, the aforementioned commission payment system may include a user interface for the administrator, a commission calculation component, and a commission payment component. The commission calculation and payment components can be deployed on a server, while the user interface can be provided to the administrator through a client. The server can correspond to a single physical host, a server cluster consisting of multiple independent physical hosts, or a virtual server or cloud server hosted by a host cluster. The client can correspond to terminal devices such as smartphones, tablets, laptops, and desktop computers. The client can access the server via any type of wired or wireless network.

[0056] The administrator can use the commission calculation and payment services provided by the aforementioned commission payment system through the user interface. Specifically, the administrator can initiate the commission calculation and payment process, input sales data corresponding to the seller, and input other influencing factors (such as promotion intensity, customer interaction intensity, market trends, etc.) to assist in the decision-making process for paying commissions to the seller. This data will then be provided to the commission calculation component, triggering the component to calculate commissions based on the sales data.

[0057] The commission calculation component described above can acquire sales data input by the administrator for commission calculation and calculate commission data based on this sales data (where commission data refers to the commission percentage or specific amount). Alternatively, the commission calculation component can also collect sales data for commission calculation independently and calculate commission data based on this sales data. For example, the commission calculation component can acquire sales data generated within a commission settlement cycle and calculate commission data based on this sales data for the commission that the administrator will pay to the seller at the end of the specified commission settlement cycle.

[0058] The aforementioned commission payment component allows the administrator to make commission payments to the seller through the accounts registered in the commission payment system by both the administrator and the seller. Specifically, the commission payment system can transfer the corresponding commission from the administrator's account to the seller's account based on the commission data calculated by the commission calculation component. For example, assuming the commission data represents a commission percentage, the specific commission amount can be calculated based on this percentage and the sales amount, and then transferred from the administrator's account to the seller's account; or, assuming the commission data represents a specific commission amount, the commission amount can be directly transferred from the administrator's account to the seller's account. The commission can be in the form of physical resources such as currency, stocks, bonds, bills, and accounts receivable, or it can be a virtual resource with specific value.

[0059] Furthermore, the aforementioned commission calculation components may include a data acquisition module, a contract management module, a data analysis module, a rule management module, a feedback module, a rule matching module, and a commission calculation module.

[0060] The aforementioned data acquisition module can be used to obtain sales data corresponding to the seller generated within a commission settlement cycle. For example, at the end of a commission settlement cycle, it can obtain the sales data statistically compiled within that cycle by the administrator through the user interface, or it can collect the sales data generated within that commission settlement cycle itself.

[0061] The aforementioned contract management module can be used to manage information related to contracts signed between the manager and the seller, such as information about the account used by the manager to pay commissions and information about the account used by the seller to receive commissions, thereby making the commission payment process transparent and automated.

[0062] The aforementioned data analysis module can be used to optimize the commission calculation rules based on an adaptive optimization algorithm, with the goal of maximizing the matching degree between commission data and sales data generated in a sales scenario. It performs optimization calculations on several historical commission data samples and several historical sales data samples generated in a sales scenario to obtain the commission calculation rules with the highest matching degree to this sales scenario.

[0063] The aforementioned rule management module can be used to manage the correspondence between sales scenarios and the commission calculation rules with the highest matching degree, and can periodically update the commission calculation rules. For example, it can periodically obtain several historical commission data samples and several historical sales data samples from a sales scenario that are relatively recent in time. Based on the aforementioned adaptive optimization algorithm, with the optimization objective of maximizing the matching degree between the commission data and the sales data generated in the sales scenario, iterative optimization calculations are performed on these historical commission data samples and historical sales data samples to obtain the commission calculation rule with the highest matching degree to this sales scenario. In this way, the matching degree between the commission calculation rules and the latest situation of the sales scenario can be guaranteed, thereby further improving the accuracy and rationality of the commissions paid by the management to the seller.

[0064] The aforementioned feedback module can be used to adjust the commission calculation rules based on feedback from both management and sales parties. Specifically, once commission data has been determined based on sales data and the commission calculation rules, the module can obtain the satisfaction levels of management and sales parties with this commission data in real time. Using this commission data and sales data as new samples, and based on the aforementioned adaptive optimization algorithm, with the optimization objective of maximizing the matching degree between the commission data and the sales data generated in the sales scenario, iterative optimization calculations are performed on the new samples to adjust the commission calculation rules. This ensures that the commission calculation rules always meet the actual needs of management and sales parties.

[0065] The rule matching module described above can be used to match commission calculation rules, that is, to determine the sales scenario corresponding to the sales data and obtain the commission calculation rules corresponding to that sales scenario.

[0066] The commission calculation module described above can be used to calculate the commission data corresponding to the seller based on the matched commission calculation rules and the sales data corresponding to the seller.

[0067] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating a commission payment method in an exemplary embodiment of this application.

[0068] In this embodiment, the above-described commission payment method can be applied to, for example... Figure 1 The server shown is as follows. Figure 2 As shown, the commission payment method may include the following steps:

[0069] Step 202: According to the preset commission settlement cycle, periodically obtain the sales data corresponding to the seller.

[0070] In this embodiment, sales data corresponding to the seller can be periodically acquired according to a preset commission settlement cycle. This allows for the subsequent calculation of the commission percentage or specific amount corresponding to the seller based on the sales data, i.e., the percentage or specific amount of commission paid by the management to the seller. For example, at the end of a commission settlement cycle, the management can acquire the sales data statistically compiled within that cycle, input through a user interface, or the management can collect the sales data generated within that cycle itself.

[0071] It should be noted that the above commission settlement cycle can be set and adjusted according to actual circumstances and the needs of the management and sales parties; that is, the commission settlement cycle can be fixed or it can change according to actual circumstances and needs. For example, the commission settlement cycle can be shortened to one month after entering the peak sales period, and extended to one quarter after entering the sales slump, and so on.

[0072] In some embodiments, the sales data described above may include one or more of the following: sales amount; marketing activity data; competitor data; and seasonal data. Marketing activity data may further include numerical data such as promotion intensity and customer activity intensity; competitor data may further include numerical data such as competitor sales amount and competitor promotion intensity; and seasonal data may further include statistical data such as customer activity time distribution and purchase intention time distribution.

[0073] Step 204: Determine the sales scenario corresponding to the sales data and obtain the commission calculation rule corresponding to the sales scenario; wherein, the commission calculation rule is based on an adaptive optimization algorithm, which optimizes the calculation for several historical commission data samples and several historical sales data samples generated in the sales scenario, and obtains the commission calculation rule with the highest matching degree with the sales scenario.

[0074] In this embodiment, to introduce a more diversified and personalized commission calculation mechanism and improve the accuracy and rationality of commission payments from management to sellers, different sales scenarios can be defined, and different commission calculation rules can be set for each scenario. For example, sales scenarios can be divided into spring, summer, autumn, and winter based on the season. The commission calculation rule for the winter sales scenario is a high-incentive mode, meaning that when sales data is roughly the same, the commission percentage or amount calculated according to the commission calculation rules corresponding to these four sales scenarios will be the highest. As another example, sales scenarios can be divided into high-investment and low-investment scenarios based on promotional intensity and customer interaction intensity. The commission calculation rule for the high-investment sales scenario is a high-incentive mode, intended to encourage sellers to hold more promotional activities and strengthen customer interaction.

[0075] Having obtained the aforementioned sales data, we can first determine the sales scenario corresponding to that sales data, and then obtain the commission calculation rules corresponding to that sales scenario.

[0076] Specifically, on the one hand, the sales scenario corresponding to the sales data means that the sales data was generated within that specific sales scenario. Therefore, the sales scenario corresponding to the sales data can be determined based on its specific content. For example, assuming the sales data includes the transaction date of every transaction occurring within the current commission settlement period, and these transaction dates are all within December, then the winter sales scenario can be identified as the sales scenario corresponding to the sales data. As another example, assuming the sales data includes the number of promotional activities occurring within the current commission settlement period, and the number of promotional activities falls within the range of high-intensity promotional activities, then the high-investment sales scenario can be identified as the sales scenario corresponding to the sales data.

[0077] In practical applications, when determining the sales scenarios corresponding to sales data, different priorities can be set for different types of sales scenarios. When multiple corresponding sales scenarios can be identified based on the specific content of the sales data, the sales scenario with the highest priority can be determined as the sales scenario corresponding to the sales data. For example, sales scenarios divided according to promotion intensity and customer interaction intensity can be given higher priority, while sales scenarios divided according to season can be given lower priority. Suppose that the sales data includes both the transaction date of every transaction that occurs within the current commission settlement period, and these transaction dates are all within December, and the number of promotional activities that occur within the current commission settlement period, and the number of promotional activities falls within the high-intensity promotional activity range, then according to the priority, the high-investment sales scenario can be determined as the sales scenario corresponding to the sales data.

[0078] On the other hand, a mapping between sales scenarios and commission calculation rules can be maintained, including each sales scenario and its corresponding commission calculation rule. In this case, after determining the sales scenario corresponding to the sales data, the commission calculation rule corresponding to that sales scenario can be determined by querying this mapping.

[0079] For a given sales scenario, the commission calculation rule corresponding to that scenario can be based on an adaptive optimization algorithm. This algorithm optimizes the calculation by applying several historical commission data samples (where commission data refers to the commission percentage or specific amount) and several historical sales data samples generated within that sales scenario, resulting in the commission calculation rule with the highest degree of matching for that sales scenario. The degree of matching between this commission calculation rule and the sales scenario can be transformed into the degree of matching between the commission data in the commission calculation rule and the sales data generated within that sales scenario.

[0080] Adaptive optimization algorithms are a class of algorithms that can dynamically adjust their parameters or strategies during the optimization process to improve convergence speed, solution quality, or better cope with non-stationary environments. These algorithms are typically used to solve complex optimization problems, particularly those with unknown, discontinuous, multimodal, or multi-objective objectives. Common adaptive optimization algorithms include Adaptive Gradient Algorithms (AGAs), Evolutionary Algorithms (EAs), Adaptive Random Search (ARS), and Bayesian Optimization (BO). Evolutionary algorithms further include Genetic Algorithms (GAs), Differential Evolution (DE), and Particle Swarm Optimization (PSO).

[0081] When optimizing historical commission data samples and historical sales data samples based on an adaptive optimization algorithm to obtain commission calculation rules, in some embodiments, for a sales scenario, several historical commission data samples and several historical sales data samples generated in this sales scenario can be obtained first. The historical commission data samples can be a batch of commission data selected from previously generated commission data, and the historical sales data samples can be a batch of sales data selected from previously generated sales data.

[0082] It should be noted that there is a correspondence between the aforementioned historical commission data samples and the aforementioned historical sales data samples. A historical commission data sample and a historical sales data sample correspond to each other, meaning that the commission data calculated based on the historical sales data sample is the same as that historical commission data sample.

[0083] Subsequently, based on an adaptive optimization algorithm, with the optimization objective of maximizing the matching degree between commission data and sales data generated in the sales scenario, iterative optimization calculations can be performed on the aforementioned historical commission data samples and historical sales data samples. This will yield the commission calculation rule with the highest matching degree to the aforementioned sales scenario. The matching degree between commission data and sales data generated in the sales scenario can be used as an indicator to quantify the satisfaction of both the management and the sales party. In practical applications, the sales party satisfaction can specifically be the sales party's satisfaction with the commission data after the sales data was generated in the sales scenario; similarly, the management party satisfaction can specifically be the management's satisfaction with the commission data. For example, the sales party satisfaction could be the sales party's satisfaction with the management paying a 5,000 yuan commission on a 100,000 yuan sales amount in the sales scenario; similarly, the management party satisfaction could be the management's satisfaction with paying a 5,000 yuan commission on the 100,000 yuan sales amount.

[0084] Since management generally prefers to pay less commission to control costs, while sales want to earn more commission, the ratio of commission amount to sales amount can be used to replace the quantitative value of management satisfaction or sales satisfaction. The ratio of commission amount to sales amount is inversely proportional to the quantitative value of management satisfaction and directly proportional to the quantitative value of sales satisfaction.

[0085] It should be noted that the calculation method for the matching degree of commission data with sales data generated in the sales scenario can be set according to actual conditions and needs, and this application does not impose any special restrictions on this. For example, indicators used to quantify market reaction can also be included as part of the matching degree; market reaction refers to the willingness of each seller to continue selling after the sales data was generated in the sales scenario and the commission indicated by the commission data was paid accordingly.

[0086] To further improve the accuracy and rationality of commission payments made by management to sellers, in some embodiments, for any sales scenario, the specific content of the sales data generated in that scenario can be divided into different intervals, and different commission data can be set for different intervals to achieve tiered commissions. Specifically, various types of data in the sales data can be converted into sales indicators, and these sales indicators can include multiple sales indicator intervals. For example, a sales indicator can be sales amount (unit: ten thousand yuan), which can include four sales indicator ranges: 0-10, 10-50, 50-100, and above 100. A sales indicator can also be an indicator used to indicate the season, with a value of 1 representing spring, a value of 2 representing summer, a value of 3 representing autumn, and a value of 4 representing winter. In this case, the indicator can include two sales indicator ranges: [1,2] and [3,4]. Alternatively, a sales indicator can include sales amount (unit: ten thousand yuan) and promotion intensity (unit: level). These two sales indicators can include 16 combinations of sales indicator ranges, such as (0-10, 0-2), (10-50, 0-2), (50-100, 0-2), (above 100, 0-2), (0-10, 2-4), (10-50, 2-4), (50-100, 2-4), and (above 100, 2-4).

[0087] In the above scenario, the commission calculation rules corresponding to the sales scenario can include the correspondence between various sales indicator ranges and commission data within multiple sales indicator ranges. For example, the commission calculation rules can be shown in Table 1 below:

[0088] Table 1

[0089]

[0090] In this commission calculation rule, if the sales amount is 80,000 yuan and the promotion intensity is level 1, then the commission amount can be determined to be 5,000 yuan.

[0091] It should be noted that when sales metrics generated in a sales scenario are divided into multiple sales metric intervals, the matching degree between the commission calculation rule and this sales scenario can be transformed into the matching degree of the commission data in the commission calculation rule relative to its corresponding sales metric interval. For example, suppose the sales metrics generated in this sales scenario are divided into sales metric interval 1, sales metric interval 2, and sales metric interval 3. In this commission calculation rule, sales metric interval 1 corresponds to commission data 1, sales metric interval 2 corresponds to commission data 2, and sales metric interval 3 corresponds to commission data 3. Then, the following formula can be used: the matching degree of the commission calculation rule with this sales scenario = (the matching degree of commission data 1 relative to sales metric interval 1 + the matching degree of commission data 2 relative to sales metric interval 2 + the matching degree of commission data 3 relative to sales metric interval 3) / 3. As mentioned earlier, the matching degree of commission data relative to the sales metric interval can be an indicator used to quantify the satisfaction of management and sales. Specifically, the management's satisfaction can be the satisfaction of the management with the commission data after the sales metrics belonging to the sales metric interval are generated. Similarly, the sales' satisfaction can be the sales' satisfaction with the commission data.

[0092] To ensure timely adjustments to the commission tiers and align them with the actual needs of both management and sales, some implementations may establish a feedback mechanism to incorporate feedback from both parties and adjust the commission calculation rules. Specifically, once commission data is determined based on sales data and the commission calculation rules, the satisfaction levels of management and sales regarding this data can be obtained in real-time. This commission data and sales data are then used as new samples. Based on the aforementioned adaptive optimization algorithm, with the optimization objective of maximizing the matching degree between the commission data and the sales data generated in the sales scenario, iterative optimization calculations are performed on the new samples to adjust the commission calculation rules.

[0093] To further improve the accuracy and rationality of commission payments made by the management to sellers, in some embodiments, for a given sales scenario, several historical commission data samples and several historical sales data samples generated in that sales scenario can be periodically acquired according to a preset rule update cycle. Based on the aforementioned adaptive optimization algorithm, with the optimization objective of maximizing the matching degree between the commission data and the sales data generated in the sales scenario, iterative optimization calculations are performed on the historical commission data samples and the historical sales data samples to obtain the commission calculation rule with the highest matching degree to the sales scenario. The historical commission data samples and the historical sales data samples can be historical commission data samples and historical sales data samples whose generation time is relatively close to the current time. The commission calculation rule obtained in this case can be used as the updated commission calculation rule corresponding to the sales scenario. This ensures that the matching degree between the commission calculation rule and the latest situation of the sales scenario can be maintained, thereby further improving the accuracy and rationality of commission payments made by the management to sellers.

[0094] In some embodiments, the adaptive optimization algorithm described above may specifically be a genetic algorithm.

[0095] Genetic algorithms work by mimicking the evolutionary processes that occur in natural selection and genetics. In a genetic algorithm, the population refers to a set of candidate solutions to a problem, each candidate solution being called an individual. A chromosome represents the encoded form of a solution in a genetic algorithm, typically composed of a series of parameters. A gene is a locus on a chromosome representing a specific parameter. The fitness function evaluates the quality of a solution; a higher fitness value indicates a better solution. Selection refers to determining which individuals can serve as parents for the next generation based on their fitness. Crossover refers to generating new offspring by exchanging partial information between two parent individuals. Mutation refers to randomly altering certain genes in some individuals to maintain population diversity and prevent premature convergence. Replacement refers to replacing older individuals with newly generated offspring to form a new population.

[0096] Genetic algorithms can specifically include the following steps: initializing the population, i.e., randomly generating a set of initial solutions; evaluating fitness, i.e., using a fitness function to calculate the fitness of each individual in the population; performing selection operations, i.e., selecting superior individuals as parents based on fitness; performing crossover operations, i.e., combining the selected parents to produce new offspring; performing mutation operations, i.e., randomly changing some genes of the offspring with a certain probability; performing replacement operations, i.e., replacing old individuals with new offspring to form a new population; if a preset termination condition (such as the number of iterations, fitness threshold, etc.) is reached, the iteration stops; otherwise, the fitness is re-evaluated to continue iteration.

[0097] In a genetic algorithm-based approach, with the optimization objective of maximizing the matching degree between commission data and sales data generated in a sales scenario, iterative optimization calculations are performed on the aforementioned historical commission data samples and historical sales data samples to obtain the commission calculation rule with the highest matching degree to the aforementioned sales scenario. Individuals in the population can be commission data, fitness can be the matching degree score of commission data relative to sales data generated in the sales scenario, crossover can be calculating the average value, and mutation can be adding or subtracting a random value not exceeding a preset threshold. Specifically, the following steps can be iteratively executed until the commission data with the highest matching degree to the sales scenario is generated, and the commission calculation rule with the highest matching degree to the sales scenario is generated based on this commission data: calculating the matching degree score of commission data relative to the historical sales data sample (which is essentially the sales data generated in the sales scenario); selecting a preset number of commission data with the highest matching degree; and performing combination processing (i.e., crossover, mutation, and replacement operations) on the selected commission data to generate new commission data (i.e., a new population). To simplify the calculation process of the genetic algorithm, the aforementioned historical commission data samples can be directly used as the initial commission data (i.e., the initial population).

[0098] As mentioned above, in some embodiments, the matching degree of commission data relative to the historical sales data sample generated in the aforementioned sales scenario may specifically include: a weighted sum of a first score obtained by quantifying the manager's satisfaction and a second score obtained by quantifying the seller's satisfaction. Specifically, the manager's satisfaction may be the manager's satisfaction with the commission data given that the historical sales data sample was generated in the aforementioned sales scenario; the seller's satisfaction may be the seller's satisfaction with the commission data given that the historical sales data sample was generated in the aforementioned sales scenario.

[0099] Step 206: Determine the commission data corresponding to the seller according to the commission calculation rules.

[0100] In this embodiment, once the commission calculation rule corresponding to the aforementioned sales scenario is obtained, the commission data corresponding to the aforementioned seller can be determined based on the commission calculation rule. Specifically, when the commission calculation rule contains commission data corresponding to the sales scenario, the commission data can be directly determined as the commission data corresponding to the seller. When the sales indicators generated in the sales scenario are divided into multiple sales indicator ranges, since the commission calculation rule contains each sales indicator range and its corresponding commission data, the corresponding sales indicator range can be determined first based on the aforementioned sales data, and then the commission data corresponding to that sales indicator range can be determined as the commission data corresponding to the seller.

[0101] Step 208: Transfer the commission indicated by the commission data from the administrator's account to the seller's account.

[0102] In this embodiment, once the commission data corresponding to the aforementioned seller is determined, the commission indicated by that commission data can be transferred from the administrator's account to the seller's account, completing the commission payment for the current commission settlement cycle. For example, assuming the commission data represents a commission percentage, the specific commission amount can be calculated based on that percentage and the sales amount in the aforementioned sales data, and that commission amount can be transferred from the administrator's account to the seller's account; alternatively, assuming the commission data represents a specific commission amount, that commission amount can be directly transferred from the administrator's account to the seller's account. The commission can be in the form of physical resources such as currency, stocks, bonds, notes, and accounts receivable in the real world, or it can be a virtual resource with specific value.

[0103] In the above technical solution, after obtaining the sales data corresponding to the seller according to the commission settlement cycle, the sales scenario corresponding to the sales data can be determined first, and then the commission calculation rule corresponding to the sales scenario can be obtained. The commission data corresponding to the seller can be determined according to the commission calculation rule, so that the commission specified by the commission data can be transferred from the administrator's account to the seller's account. The commission calculation rule can be based on an adaptive optimization algorithm, which optimizes the calculation for several historical commission data samples and several historical sales data samples generated in various sales scenarios to obtain the commission calculation rule with the highest matching degree to the sales scenario.

[0104] By adopting the above approach, on the one hand, commission calculation rules corresponding to different sales scenarios are introduced, making the commission calculation mechanism more diversified and personalized, thereby providing more accurate and reasonable commission settlement services. On the other hand, the commission calculation rule corresponding to a sales scenario is the commission calculation rule with the highest matching degree to that sales scenario obtained through adaptive optimization. Therefore, the accuracy and reasonableness of the commission determined according to this commission calculation rule and corresponding to the sales data generated in that sales scenario can be further guaranteed. Moreover, since the adaptive optimization algorithm itself has high computational efficiency, it can improve the generation and updating efficiency of commission calculation rules, thereby improving the response speed and flexibility of commission calculation.

[0105] II. Commission Calculation Method Based on Machine Learning and Corresponding Commission Payment Process

[0106] Please refer to Figure 3 , Figure 3 This is a schematic diagram illustrating another commission payment system according to an exemplary embodiment of this application.

[0107] like Figure 3 As shown, the aforementioned commission payment system may include a user interface for the administrator, a commission calculation component, and a commission payment component. The commission calculation and payment components can be deployed on a server, while the user interface can be provided to the administrator through a client. The server can correspond to a single physical host, a server cluster consisting of multiple independent physical hosts, or a virtual server or cloud server hosted by a host cluster. The client can correspond to terminal devices such as smartphones, tablets, laptops, and desktop computers. The client can access the server via any type of wired or wireless network.

[0108] The administrator can use the commission calculation and payment services provided by the aforementioned commission payment system through the user interface. Specifically, the administrator can initiate the commission calculation and payment process, input sales data corresponding to the seller, and input other influencing factors (such as promotion intensity, customer interaction intensity, market trends, etc.) to assist in the decision-making process for paying commissions to the seller. This data will then be provided to the commission calculation component, triggering the component to calculate commissions based on the sales data.

[0109] The commission calculation component described above can acquire sales data input by the administrator for commission calculation and calculate commission data based on this sales data (where commission data refers to the commission percentage or specific amount). Alternatively, the commission calculation component can also collect sales data for commission calculation independently and calculate commission data based on this sales data. For example, the commission calculation component can acquire sales data generated within a commission settlement cycle and calculate commission data based on this sales data for the commission that the administrator will pay to the seller at the end of the specified commission settlement cycle.

[0110] The aforementioned commission payment component allows the administrator to make commission payments to the seller through the accounts registered in the commission payment system by both the administrator and the seller. Specifically, the commission payment system can transfer the corresponding commission from the administrator's account to the seller's account based on the commission data calculated by the commission calculation component. For example, assuming the commission data represents a commission percentage, the specific commission amount can be calculated based on this percentage and the sales amount, and then transferred from the administrator's account to the seller's account; or, assuming the commission data represents a specific commission amount, the commission amount can be directly transferred from the administrator's account to the seller's account. The commission can be in the form of physical resources such as currency, stocks, bonds, bills, and accounts receivable, or it can be a virtual resource with specific value.

[0111] Furthermore, the aforementioned commission calculation components may include a data acquisition module, a contract management module, a model building module, a model management module, a feedback module, and a commission calculation module.

[0112] The aforementioned data acquisition module can be used to obtain sales data corresponding to the seller generated within a commission settlement cycle. For example, at the end of a commission settlement cycle, it can obtain the sales data statistically compiled within that cycle by the administrator through a user interface, or it can automatically collect the sales data generated within that cycle. Furthermore, this data acquisition module can also be used to obtain historical commission data corresponding to the seller from previous commission settlement cycles.

[0113] The aforementioned contract management module can be used to manage information related to contracts signed between the manager and the seller, such as information about the account used by the manager to pay commissions and information about the account used by the seller to receive commissions, thereby making the commission payment process transparent and automated.

[0114] The aforementioned model building module can optimize the commission prediction model by minimizing the difference between the commission data predicted by the commission prediction model based on historical commission data and sales data and the historical commission data. It can input several historical commission data samples and several historical sales data samples generated in a sales scenario into the commission prediction model for training, and obtain the trained commission prediction model.

[0115] The aforementioned model management module can be used to manage the trained commission prediction model and update it periodically. For example, it can periodically calculate metrics to indicate the model's performance and determine whether an update is needed based on these metrics. If so, the model parameters or input features can be adjusted to update the commission prediction model.

[0116] The commission calculation module described above can be used to input historical commission data and sales data corresponding to the seller into the trained commission prediction model for calculation, and the commission prediction model can then predict the commission data corresponding to the seller.

[0117] Please refer to point 4. Figure 4 This is a flowchart illustrating another commission payment method in an exemplary embodiment of this application.

[0118] In this embodiment, the above-described commission payment method can be applied to, for example... Figure 3 The server shown is as follows. Figure 4 As shown, the commission payment method may include the following steps:

[0119] Step 402: According to the preset commission settlement cycle, periodically obtain the sales data corresponding to the seller and obtain the historical commission data corresponding to the seller.

[0120] In this embodiment, sales data corresponding to the seller can be periodically acquired according to a preset commission settlement cycle, along with historical commission data (where commission data refers to the commission percentage or specific amount) corresponding to the seller. This allows for subsequent calculation of commission data corresponding to the seller based on the sales data and the historical commission data. The commission data can then be used to determine the percentage or specific amount of commission paid by the management to the seller. For example, at the end of a commission settlement cycle, sales data statistically compiled within that cycle can be acquired by the management through a user interface, or sales data generated within that cycle can be collected automatically. Furthermore, historical commission data from several commission settlement cycles prior to this current cycle can be acquired.

[0121] It should be noted that the above commission settlement cycle can be set and adjusted according to actual circumstances and the needs of the management and sales parties; that is, the commission settlement cycle can be fixed or it can change according to actual circumstances and needs. For example, the commission settlement cycle can be shortened to one month after entering the peak sales period, and extended to one quarter after entering the sales slump, and so on.

[0122] In some embodiments, the sales data described above may include one or more of the following: sales amount; marketing activity data; competitor data; and seasonal data. Marketing activity data may further include numerical data such as promotion intensity and customer activity intensity; competitor data may further include numerical data such as competitor sales amount and competitor promotion intensity; and seasonal data may further include statistical data such as customer activity time distribution and purchase intention time distribution.

[0123] To ensure the integrity and accuracy of the data and guarantee the quality of the model input, in some embodiments, the aforementioned historical commission data and sales data can be cleaned first, that is, missing values ​​and outliers in the data can be processed, and the data can be standardized.

[0124] Step 404: Input the historical commission data and the sales data into the trained commission prediction model, and the commission prediction model predicts the commission data corresponding to the seller based on the historical commission data and the sales data.

[0125] To improve the accuracy and rationality of commission payments made by management to sellers, machine learning can be used to construct a commission prediction model to predict commission data. Specifically, in some embodiments, several historical commission data samples and several historical sales data samples can be obtained. The optimization objective is to minimize the difference between the commission data predicted by the commission prediction model based on the historical commission data and sales data and the historical commission data (i.e., the historical commission data used for prediction). The historical commission data samples and the historical sales data samples are then input into the constructed commission prediction model for training, resulting in the trained commission prediction model.

[0126] It should be noted that the degree of difference between the commission forecasting model and the historical commission data predicted based on historical commission and sales data can be measured using the residual sum of squares.

[0127] For a commission settlement cycle, historical commission data from several previous commission settlement cycles, as well as sales data generated within this commission settlement cycle, can all individually affect the commission data for that cycle. Therefore, to further improve the accuracy and rationality of commission payments made by management to sellers, in some embodiments, the aforementioned commission prediction model may include an autoregressive sub-model and a linear regression sub-model. The autoregressive sub-model can be used to predict new commission data based on historical commission data, and the linear regression sub-model can be used to predict commission data based on sales data. In this case, the output of the commission prediction model can be the sum of the outputs of the autoregressive sub-model and the linear regression sub-model.

[0128] When training the commission prediction model, the historical commission data samples can be input into the autoregressive sub-model for calculation, resulting in a portion of the commission data predicted by the autoregressive sub-model based on the historical commission data samples (referred to as the first commission data). Similarly, the historical sales data samples can be input into the linear regression sub-model for calculation, resulting in a portion of the commission data predicted by the linear regression sub-model based on the historical sales data samples (referred to as the second commission data). The sum of the first and second commission data can then be determined as the commission data predicted by the commission prediction model based on the historical commission data samples and the historical sales data samples. The degree of difference between the commission data predicted by the commission prediction model and the historical commission data samples is calculated, and the model parameters of the commission prediction model are adjusted based on this degree of difference to complete the training of the commission prediction model.

[0129] In some embodiments, the above commission prediction model may include the following formula:

[0130]

[0131] in, This represents the commission data predicted by the above commission prediction model for the t-th commission settlement period; This represents the first commission data for the t-th commission settlement period predicted by the above autoregressive sub-model. β represents the second commission data predicted by the linear regression sub-model for the t-th commission settlement period; p represents the base commission data; p represents the number of historical commission data. Y represents the coefficient of historical commission data for the ti-th commission settlement period; t-i Represents the historical commission data for the ti-th commission settlement period; q represents the number of sales indicators in the sales data; θ j X represents the coefficient of the j-th sales indicator; j,tThis represents the j-th sales indicator generated within the t-th commission settlement period.

[0132] It should be noted that the above autoregressive sub-model may also include an error adjustment term, that is, the autoregressive sub-model may include the following formula:

[0133]

[0134] Where ∈ represents the error adjustment term.

[0135] The aforementioned sales indicators can be derived from various types of data in the sales data. For example, sales indicators can be sales amount, promotion intensity, customer interaction intensity, etc.; they can also be indicators used to indicate the season, with a value of 1 representing spring, a value of 2 representing summer, a value of 3 representing autumn, and a value of 4 representing winter.

[0136] It should be noted that in the commission prediction model shown in the formula above, β, θ j These are adjustable model parameters, where p and q reflect the number of input features of the model.

[0137] Furthermore, the optimization objective of the above commission prediction model can be expressed as the following formula:

[0138]

[0139] in, Y represents the commission data predicted by the above commission prediction model for the t-th commission settlement period; t Y represents the commission data for the t-th commission settlement period, and N represents the number of model predictions. During training, Y... t and Y t-i This can be derived from the historical commission data sample mentioned above, X j,t This data can be derived from the aforementioned historical sales data sample.

[0140] Having obtained the aforementioned historical commission data and sales data, the historical commission data and sales data can be input into the trained commission prediction model, which will then predict the commission data corresponding to the seller based on the historical commission data and sales data.

[0141] It should be noted that a universally applicable commission prediction model can be obtained through training without distinguishing between sales scenarios.

[0142] Alternatively, to introduce a more diversified and personalized commission calculation mechanism, thereby improving the accuracy and rationality of commission payments from management to sellers, different sales scenarios can be defined. For each sales scenario, a commission prediction model can be trained based on historical commission data and historical sales data generated within that scenario. In this case, the sales scenario corresponding to the aforementioned sales data can be determined first, and then the commission prediction model corresponding to that sales scenario can be obtained. The historical commission data and the sales data can then be input into the trained commission prediction model corresponding to that sales scenario, allowing the model to predict the commission data corresponding to the seller based on the historical commission data and the sales data.

[0143] To ensure timely adjustments to the commission tiers and align them with the actual needs of both management and sales, some embodiments may incorporate a feedback mechanism. This mechanism allows for adjustments to the commission calculation rules based on feedback from both management and sales. Specifically, once commission data is determined from sales data, the actual commission paid by management to sales can be obtained in real-time. This commission data, along with the sales data, can then be used as new samples. These new samples are then input into the commission prediction model for further training, resulting in a fully trained commission prediction model.

[0144] To further improve the accuracy and rationality of commission payments made by the management to sellers, in some embodiments, metrics indicating the performance of the commission prediction model can be calculated periodically according to a preset model update cycle, and the need to update the commission prediction model can be determined based on these metrics. These metrics may include accuracy, precision, and recall. When a metric fails to reach a standard threshold, the commission prediction model is considered to need an update. If an update is determined, the model parameters or input features of the commission prediction model can be adjusted to achieve the update.

[0145] Specifically, in some embodiments, the model parameters of the commission prediction model can be adjusted to update the commission prediction model. For example, the commission prediction model can be retrained, and the retrained commission prediction model can be used as the updated commission prediction model. That is, several historical commission data samples and several historical sales data samples can be reacquired, and the historical commission data samples and historical sales data samples can be input into the commission prediction model for retraining, with the optimization objective of minimizing the difference between the commission data predicted by the commission prediction model based on the historical commission data and sales data and the historical commission data, to obtain the retrained commission prediction model, which can then be used to update the commission prediction model.

[0146] Alternatively, in some embodiments, the input features of the commission prediction model can be adjusted to update the commission prediction model. For example, an input feature selection algorithm can be used to select input features for the commission prediction model, and the input features of the commission prediction model can be adjusted according to the selected input features to update the commission prediction model.

[0147] In some embodiments, the input feature selection algorithm described above may include a stepwise regression algorithm or a LASSO (Least Absolute Shrinkage and Selection Operator) regression algorithm.

[0148] Stepwise regression and LASSO regression are two methods for selecting the set of predictor variables in a model, where the variables are the model's input features. Stepwise regression is a statistical method that constructs a regression model by iteratively adding or removing predictor variables. It decides whether to retain a predictor variable in the model based on specific criteria (such as AIC, BIC, or p-value). Stepwise regression has three main forms: forward selection (starting with no predictor variables and adding the predictor variable that improves the model most in each iteration until no more variables can significantly improve the model), backward elimination (starting with all possible predictor variables and removing the predictor variable that contributes the least to the model in each iteration until all remaining variables contribute significantly to the model), and bidirectional elimination (both adding and removing variables in each iteration). LASSO regression performs variable selection and regularization while estimating model parameters. It effectively excludes these corresponding predictor variables from the model by adding a penalty term (i.e., L1 regularization) to the loss function, causing some coefficients to shrink to zero.

[0149] Step 406: Transfer the commission specified in the commission data from the administrator's account to the seller's account.

[0150] In this embodiment, once the commission data corresponding to the aforementioned seller is determined, the commission indicated by that commission data can be transferred from the administrator's account to the seller's account, completing the commission payment for the current commission settlement cycle. For example, assuming the commission data represents a commission percentage, the specific commission amount can be calculated based on that percentage and the sales amount in the aforementioned sales data, and that commission amount can be transferred from the administrator's account to the seller's account; alternatively, assuming the commission data represents a specific commission amount, that commission amount can be directly transferred from the administrator's account to the seller's account. The commission can be in the form of physical resources such as currency, stocks, bonds, notes, and accounts receivable in the real world, or it can be a virtual resource with specific value.

[0151] In the above technical solution, after obtaining the sales data corresponding to the seller according to the commission settlement cycle and obtaining the historical commission data corresponding to the seller, the historical commission data and the sales data can be input into the trained commission prediction model. The commission prediction model predicts the commission data corresponding to the seller based on the historical commission data and the sales data, so that the commission specified by the commission data can be transferred from the manager's account to the seller's account.

[0152] By using the above method to build a commission prediction model through machine learning, and then using this model to determine the commission corresponding to the sales data, the accuracy and reasonableness of the determined commission can be guaranteed, thereby providing a more accurate and reasonable commission settlement service.

[0153] Corresponding to the embodiments of the methods described above, this application also provides embodiments of the apparatus.

[0154] Please refer to Figure 5 , Figure 5 This is a schematic diagram illustrating the structure of a device according to an exemplary embodiment of this application. At the hardware level, the device includes a processor 502, an internal bus 504, a network interface 506, memory 508, and non-volatile memory 510, and may also include other necessary hardware. One or more embodiments of this application can be implemented in software, for example, the processor 502 reads the corresponding computer program from the non-volatile memory 510 into memory 508 and then runs it. Of course, besides software implementation, one or more embodiments of this application do not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution entity of the following processing flow is not limited to individual logic modules, but can also be hardware or logic devices.

[0155] Please refer to Figure 6 , Figure 6This is a block diagram illustrating a commission payment device in an exemplary embodiment of this application.

[0156] The aforementioned commission payment device can be applied to Figure 5 The apparatus shown is used to implement the technical solution of this application. The apparatus includes:

[0157] The acquisition module 602 periodically acquires sales data corresponding to the seller according to a preset commission settlement cycle;

[0158] The matching module 604 determines the sales scenario corresponding to the sales data and obtains the commission calculation rule corresponding to the sales scenario; wherein, the commission calculation rule is based on an adaptive optimization algorithm, which optimizes the calculation for several historical commission data samples and several historical sales data samples generated in the sales scenario, and obtains the commission calculation rule with the highest matching degree to the sales scenario.

[0159] The calculation module 606 determines the commission data corresponding to the seller according to the commission calculation rules;

[0160] The payment module 608 transfers the commission specified in the commission data from the administrator's account to the seller's account.

[0161] In some embodiments, the apparatus further includes a generation module for:

[0162] Obtain several historical commission data samples and several historical sales data samples generated in the aforementioned sales scenario;

[0163] Based on the aforementioned adaptive optimization algorithm, with the optimization objective of maximizing the matching degree between commission data and sales data generated in the sales scenario, iterative optimization calculations are performed on the historical commission data samples and the historical sales data samples to obtain the commission calculation rule with the highest matching degree with the sales scenario.

[0164] In some embodiments, sales data includes sales metrics; the sales metrics include multiple sales metric ranges; the commission calculation rules include the correspondence between each of the multiple sales metric ranges and the commission data;

[0165] The step of determining the commission data corresponding to the seller according to the commission calculation rules includes:

[0166] According to the commission calculation rules, the sales indicator range to which the sales indicator corresponding to the seller belongs is determined, and the commission data corresponding to the sales indicator range is determined as the commission data corresponding to the seller.

[0167] In some embodiments, the generation module is further configured to:

[0168] According to the preset rule update cycle, several historical commission data samples and several historical sales data samples generated in the sales scenario are periodically obtained. With the optimization goal of maximizing the matching degree of commission data with the sales data generated in the sales scenario, the historical commission data samples and the historical sales data samples are iteratively optimized and calculated again to obtain the commission calculation rule with the highest matching degree with the sales scenario.

[0169] In some embodiments, the adaptive optimization algorithm is a genetic algorithm;

[0170] The adaptive optimization algorithm, with the optimization objective of maximizing the matching degree between commission data and sales data generated in the sales scenario, iteratively optimizes the historical commission data samples and the historical sales data samples to obtain the commission calculation rule with the highest matching degree to the sales scenario, including:

[0171] The following steps are performed iteratively until the commission data with the highest matching degree relative to the sales scenario is generated, and a commission calculation rule with the highest matching degree to the sales scenario is generated based on the commission data:

[0172] Calculate the matching score of commission data relative to the historical sales data sample generated in the sales scenario; wherein, the initial commission data is the historical commission data sample;

[0173] Select the preset number of commission data with the highest matching degree;

[0174] The selected commission data is combined and processed to generate new commission data.

[0175] In some embodiments, the matching degree of commission data relative to the historical sales data sample generated in the sales scenario includes: a weighted sum of a first score obtained by quantifying the management's satisfaction and a second score obtained by quantifying the salesperson's satisfaction;

[0176] Wherein, the manager's satisfaction is the manager's satisfaction with the commission data when the historical sales data sample was generated in the sales scenario; the seller's satisfaction is the seller's satisfaction with the commission data when the historical sales data sample was generated in the sales scenario.

[0177] In some embodiments, the sales data includes one or more of the following: sales amount; marketing activity data; competitor data; seasonal data.

[0178] Please refer to Figure 7 , Figure 7This is a block diagram illustrating another commission payment device in an exemplary embodiment of this application.

[0179] The aforementioned commission payment device can be applied to Figure 5 The apparatus shown is used to implement the technical solution of this application. The apparatus includes:

[0180] The acquisition module 702 periodically acquires sales data corresponding to the seller according to a preset commission settlement cycle, and also acquires historical commission data corresponding to the seller.

[0181] The calculation module 704 inputs the historical commission data and the sales data into the trained commission prediction model, and the commission prediction model predicts the commission data corresponding to the seller based on the historical commission data and the sales data.

[0182] Payment module 706 transfers the commission specified in the commission data from the administrator's account to the seller's account.

[0183] In some embodiments, the apparatus further includes a training module for:

[0184] Obtain several historical commission data samples and several historical sales data samples;

[0185] With the optimization objective of minimizing the difference between the commission prediction model based on historical commission data and sales data and the historical commission data, the historical commission data samples and the historical sales data samples are input into the commission prediction model for training, resulting in the trained commission prediction model.

[0186] In some embodiments, the commission prediction model includes an autoregressive sub-model and a linear regression sub-model;

[0187] The step of optimizing the commission prediction model by minimizing the difference between the predicted commission data and the historical commission data, based on historical commission data and sales data, involves inputting samples of historical commission data and historical sales data into the commission prediction model for training, resulting in a trained commission prediction model.

[0188] The historical commission data sample is input into the autoregressive sub-model for calculation to obtain the first commission data predicted by the autoregressive sub-model based on the historical commission data sample.

[0189] The historical sales data sample is input into the linear regression sub-model for calculation, and the second commission data predicted by the linear regression model based on the historical sales data sample is obtained.

[0190] The sum of the first commission data and the second commission data is determined as the commission data predicted by the commission prediction model based on the historical commission data sample and the historical sales data sample. The degree of difference between the commission data predicted by the commission prediction model and the historical commission data sample is calculated, so as to adjust the model parameters of the commission prediction model according to the degree of difference, and complete the training of the commission prediction model.

[0191] In some embodiments, the commission prediction model includes the following formula:

[0192] Y t =Y t1 +Y t2 ;

[0193]

[0194] Among them, Y t Y represents the commission data predicted by the commission prediction model for the t-th commission settlement period; t1 Y represents the first commission data for the t-th commission settlement period predicted by the autoregressive sub-model; t2 β represents the second commission data predicted by the linear regression sub-model for the t-th commission settlement period; p represents the base commission data; p represents the number of historical commission data. Y represents the coefficient of historical commission data for the ti-th commission settlement period; t-i Represents the historical commission data for the ti-th commission settlement period; q represents the number of sales indicators in the sales data; θ j X represents the coefficient of the j-th sales indicator; j,t This represents the j-th sales indicator generated within the t-th commission settlement period.

[0195] In some embodiments, the training module is further configured to:

[0196] According to the preset model update cycle, the indicators used to indicate the model performance of the commission prediction model are calculated periodically, and it is determined whether the commission prediction model needs to be updated based on the indicators.

[0197] If it is determined that the commission prediction model needs to be updated, the model parameters or input features of the commission prediction model are adjusted to update the commission prediction model.

[0198] In some embodiments, adjusting the model parameters of the commission prediction model to update the commission prediction model includes:

[0199] Reacquire several historical commission data samples and several historical sales data samples;

[0200] With the optimization objective of minimizing the difference between the commission prediction model based on historical commission data and sales data and the historical commission data, the historical commission data samples and the historical sales data samples are input into the commission prediction model for retraining to obtain the retrained commission prediction model, which is then used to update the commission prediction model.

[0201] In some embodiments, adjusting the input features of the commission prediction model to update the commission prediction model includes:

[0202] Based on the input feature selection algorithm, input features are selected for the commission prediction model, and the input features of the commission prediction model are adjusted according to the selected input features to update the commission prediction model.

[0203] In some embodiments, the input feature selection algorithm includes a stepwise regression algorithm or a LASSO regression algorithm.

[0204] In some embodiments, the sales data includes one or more of the following: sales amount; marketing activity data; competitor data; seasonal data.

[0205] For the device embodiments, they basically correspond to the method embodiments; therefore, relevant details can be found in the descriptions of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the technical solution of this application according to actual needs.

[0206] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. A typical implementation device is a computer, which can take the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email sending and receiving device, game console, tablet computer, wearable device, or any combination of these devices.

[0207] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0208] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0209] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0210] It should be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0211] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of this application. In some cases, the actions or steps described in this application may be performed in a different order than those shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0212] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a,” “the,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. The term “and / or” refers to and includes any or all possible combinations of one or more associated listed items.

[0213] The terms "an embodiment," "some embodiments," "example," "specific example," or "one implementation," as used in one or more embodiments of this application, refer to specific features or characteristics described in connection with that embodiment, which are included in at least one embodiment of this application. Illustrative descriptions of these terms do not necessarily refer to the same embodiment. Furthermore, the described specific features or characteristics may be combined in a suitable manner in one or more embodiments of this application. In addition, different embodiments and specific features or characteristics from different embodiments may be combined without contradiction.

[0214] It should be understood that although the terms first, second, third, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of one or more embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0215] The above description is merely a preferred embodiment of one or more embodiments of this application and is not intended to limit the scope of one or more embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this application should be included within the protection scope of one or more embodiments of this application.

[0216] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

Claims

1. A commission payment method, the method comprising: According to the preset commission settlement cycle, regularly obtain the sales data corresponding to the seller; Determine the sales scenario corresponding to the sales data, and obtain the commission calculation rules corresponding to the sales scenario; The commission data corresponding to the seller is determined according to the commission calculation rules. The commission specified in the commission data is transferred from the administrator's account to the seller's account; The method further includes: Obtain several historical commission data samples and several historical sales data samples generated in the aforementioned sales scenario; Based on a genetic algorithm, the following steps are executed iteratively until the commission data with the highest matching degree relative to the sales scenario is generated, and the commission calculation rule with the highest matching degree to the sales scenario is generated based on the commission data: Calculate the matching score of commission data relative to the historical sales data sample generated in the sales scenario; wherein, the initial commission data is the historical commission data sample; Select the preset number of commission data with the highest matching degree; The selected commission data is combined and processed to generate new commission data.

2. The method according to claim 1, wherein the sales data includes sales indicators; the sales indicators include multiple sales indicator ranges; and the commission calculation rules include the correspondence between each of the multiple sales indicator ranges and the commission data. The step of determining the commission data corresponding to the seller according to the commission calculation rules includes: According to the commission calculation rules, the sales indicator range to which the sales indicator corresponding to the seller belongs is determined, and the commission data corresponding to the sales indicator range is determined as the commission data corresponding to the seller.

3. The method according to claim 1, further comprising: According to the preset rule update cycle, several historical commission data samples and several historical sales data samples generated in the sales scenario are periodically obtained. With the optimization goal of maximizing the matching degree of commission data with the sales data generated in the sales scenario, the historical commission data samples and the historical sales data samples are iteratively optimized and calculated again to obtain the commission calculation rule with the highest matching degree with the sales scenario.

4. The method according to claim 1, wherein the matching degree of commission data relative to the historical sales data sample generated in the sales scenario includes: The weighted sum of the first score obtained by quantifying management satisfaction and the second score obtained by quantifying sales satisfaction; Wherein, the manager's satisfaction is the manager's satisfaction with the commission data when the historical sales data sample was generated in the sales scenario; the seller's satisfaction is the seller's satisfaction with the commission data when the historical sales data sample was generated in the sales scenario.

5. The method of claim 1, wherein the sales data includes one or more of the following: sales amount; marketing activity data; competitor data; seasonal data.

6. A commission payment method, the method comprising: According to the preset commission settlement cycle, periodically obtain the sales data corresponding to the seller, and obtain the historical commission data corresponding to the seller; The historical commission data and the sales data are input into the trained commission prediction model, which then predicts the commission data corresponding to the seller based on the historical commission data and the sales data; wherein, the commission prediction model includes an autoregressive sub-model and a linear regression sub-model. The commission specified in the commission data is transferred from the administrator's account to the seller's account; The method further includes: Obtain several historical commission data samples and several historical sales data samples; The historical commission data sample is input into the autoregressive sub-model for calculation to obtain the first commission data predicted by the autoregressive sub-model based on the historical commission data sample. The historical sales data sample is input into the linear regression sub-model for calculation, and the second commission data predicted by the linear regression model based on the historical sales data sample is obtained. The sum of the first commission data and the second commission data is determined as the commission data predicted by the commission prediction model based on the historical commission data sample and the historical sales data sample. The degree of difference between the commission data predicted by the commission prediction model and the historical commission data sample is calculated, so as to adjust the model parameters of the commission prediction model according to the degree of difference, and complete the training of the commission prediction model.

7. The method according to claim 6, wherein the commission prediction model comprises the following formula: ； ； ； in, This indicates that the commission prediction model predicts the first... Commission data for each commission settlement cycle; This indicates that the autoregressive sub-model predicts the first... First commission data for each commission settlement cycle; This indicates that the linear regression sub-model predicts the first... Second commission data for each commission settlement cycle; This represents the basic commission data; This indicates the number of historical commission data points; Indicates the first Coefficients of historical commission data for each commission settlement cycle; Indicates the first Historical commission data for each commission settlement cycle; This indicates the number of sales metrics in the sales data; Indicates the first The coefficient of each sales indicator; Indicates the first The first commission settlement period generated within the first commission settlement cycle Sales targets.

8. The method according to claim 6, further comprising: According to the preset model update cycle, the indicators used to indicate the model performance of the commission prediction model are calculated periodically, and it is determined whether the commission prediction model needs to be updated based on the indicators. If it is determined that the commission prediction model needs to be updated, the model parameters or input features of the commission prediction model are adjusted to update the commission prediction model.

9. The method according to claim 8, wherein adjusting the model parameters of the commission prediction model to update the commission prediction model includes: Reacquire several historical commission data samples and several historical sales data samples; With the optimization objective of minimizing the difference between the commission prediction model based on historical commission data and sales data and the historical commission data, the historical commission data samples and the historical sales data samples are input into the commission prediction model for retraining to obtain the retrained commission prediction model, which is then used to update the commission prediction model.

10. The method according to claim 8, wherein adjusting the input features of the commission prediction model to update the commission prediction model includes: Based on the input feature selection algorithm, input features are selected for the commission prediction model, and the input features of the commission prediction model are adjusted according to the selected input features to update the commission prediction model.

11. The method according to claim 10, wherein the input feature selection algorithm includes a stepwise regression algorithm or a LASSO regression algorithm.

12. The method of claim 6, wherein the sales data includes one or more of the following: sales amount; marketing activity data; competitor data; seasonal data.

13. A commission payment device, the device comprising: The acquisition module periodically acquires sales data corresponding to the seller according to a preset commission settlement cycle; The matching module determines the sales scenario corresponding to the sales data and obtains the commission calculation rules corresponding to the sales scenario. The calculation module determines the commission data corresponding to the seller according to the commission calculation rules; The payment module transfers the commission specified in the commission data from the administrator's account to the seller's account; The generation module acquires several historical commission data samples and several historical sales data samples generated in the sales scenario; based on a genetic algorithm, iteratively executes the following steps until the commission data with the highest matching degree relative to the sales scenario is generated, and a commission calculation rule with the highest matching degree relative to the sales scenario is generated based on the commission data: calculating the matching degree score of the commission data relative to the historical sales data samples generated in the sales scenario; wherein, the initial commission data is the historical commission data samples; selecting a preset number of commission data with the highest matching degree; and combining the selected commission data to generate new commission data.

14. A commission payment device, the device comprising: The acquisition module periodically acquires sales data corresponding to the seller according to a preset commission settlement cycle, and also acquires historical commission data corresponding to the seller. The calculation module inputs the historical commission data and the sales data into the trained commission prediction model, which then predicts the commission data corresponding to the seller based on the historical commission data and the sales data. The commission prediction model includes an autoregressive sub-model and a linear regression sub-model. The payment module transfers the commission specified in the commission data from the administrator's account to the seller's account; The training module acquires several historical commission data samples and several historical sales data samples; it inputs the historical commission data samples into the autoregressive sub-model for calculation to obtain the first commission data predicted by the autoregressive sub-model based on the historical commission data samples; it inputs the historical sales data samples into the linear regression sub-model for calculation to obtain the second commission data predicted by the linear regression sub-model based on the historical sales data samples; the sum of the first commission data and the second commission data is determined as the commission data predicted by the commission prediction model based on the historical commission data samples and the historical sales data samples, and the degree of difference between the commission data predicted by the commission prediction model and the historical commission data samples is calculated, so as to adjust the model parameters of the commission prediction model according to the degree of difference, thereby completing the training of the commission prediction model.

15. An electronic device comprising: processor; Memory used to store processor-executable instructions; The processor implements the method as described in any one of claims 1 to 12 by executing the executable instructions.

16. A computer-readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 12.

Images