Multidimensional data and dynamic weight-based reward determination method and device

Abstract

The invention discloses a reward determination method and device based on multi-dimensional data and dynamic weight, and relates to the technical field of data processing. The method comprises the steps that basic information of a target object is acquired, and the basic information comprises workload information, performance information and basic reward information; predicting the basic information by using a reward prediction model to obtain a predicted reward, the reward prediction model being obtained by training a target model by using a basic information sample and a predicted reward sample; and determining a final reward of the target object based on the predicted reward. The workload information, the performance information and the basic reward information of the employees are predicted through the reward prediction model, so that the salary calculation can be differentially adjusted according to the specific performance and contribution of each employee, and the technical effect of more fair and personalized salary distribution according to the personal basic information is realized. The technical problem of poor salary calculation mode adaptability in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method and device for determining remuneration based on multi-dimensional data and dynamic weights. Background Art

[0002] In order to stabilize and motivate employees, enterprises usually need to pay salaries according to certain rules. Salary payment usually involves various factors such as the workload of employees, the results of performance evaluations, and the financial status of the company. In industries such as manufacturing, services, or the Internet, the workload and performance evaluation results of employees will fluctuate over time, and the financial status of the company may also fluctuate with the market.

[0003] Existing salary management systems usually adopt fixed salary, performance bonus, or simple piece-rate wage models, and have the following deficiencies: (1) Fixed salary model: It cannot reflect the actual workload of employees, resulting in employees who work more not getting more, affecting employees' enthusiasm; (2) Piece-rate wage model: Although it can reflect the workload, when the workload is low, the income of employees may be too low, affecting their living security and work enthusiasm; when the workload is too high, the company's costs may increase significantly, affecting the company's profits; (3) Lack of dynamic adjustment mechanism: Existing methods fail to comprehensively consider the balance among workload, company cost control, and employee security, resulting in unscientific salary distribution.

[0004] In response to the above problems, no effective solutions have been proposed yet. Summary of the Invention

[0005] Embodiments of the present invention provide a method and device for determining remuneration based on multi-dimensional data and dynamic weights, so as to at least solve the technical problem of poor adaptability of existing salary calculation methods.

[0006] According to one aspect of the embodiments of the present invention, a method for determining remuneration based on multi-dimensional data and dynamic weights is provided, including: obtaining basic information of a target object, where the basic information includes: workload information, performance information, and basic remuneration information; using a remuneration prediction model to predict the basic information to obtain a predicted remuneration, where the remuneration prediction model is obtained by training a target model using basic information samples and predicted remuneration samples; and determining the final remuneration of the target object based on the predicted remuneration.

[0007] Optionally, determining the final remuneration of the target object based on the predicted remuneration includes: obtaining remuneration plan information, where the remuneration plan information includes: cost control plan information and object incentive plan information; determining a remuneration adjustment coefficient based on the remuneration plan information; and determining the final remuneration based on the remuneration adjustment coefficient and the predicted remuneration.

[0008] Optionally, a reward prediction model is used to predict the basic information to obtain the predicted reward, including: using the reward prediction model to predict the basic information to obtain the first predicted reward; obtaining the basic guarantee reward; determining the additional reward for the target object based on the basic information; and obtaining the predicted reward based on the basic guarantee reward, the additional reward, the first predicted reward, and the reward adjustment coefficient.

[0009] Optionally, based on the predicted reward, the final reward for the target object is determined, including: obtaining the historical reward of the target object; determining the predicted reward level of the target object based on the historical reward and the predicted reward; determining the reward adjustment coefficient based on the predicted reward level; and determining the final reward based on the reward adjustment coefficient and the predicted reward.

[0010] Optionally, a reward prediction model is used to predict the basic information to obtain the predicted reward, including: obtaining a basic information sample; inputting the basic information sample into the target model to obtain an initial predicted reward value; training and optimizing the target model based on the initial predicted reward value and the predicted reward sample to obtain the reward prediction model; and using the reward prediction model to predict the basic information to obtain the predicted reward.

[0011] Optionally, inputting the basic information sample into the target model to obtain the initial predicted reward value includes: preprocessing the basic information to obtain the preprocessed basic information; obtaining the basic information weight coefficients of the target model, where the basic information weight coefficients include: workload weight coefficient, performance weight coefficient, and basic reward weight coefficient; and determining the initial predicted reward value based on the preprocessed basic information and the basic information weight coefficients.

[0012] Optionally, determining the initial predicted reward value based on the preprocessed basic information and the basic information weight coefficients includes: in response to the workload information satisfying the first preset condition, adjusting the workload weight coefficient to obtain the adjusted workload weight coefficient; in response to the performance information satisfying the second preset condition, adjusting the performance weight coefficient to obtain the adjusted performance weight coefficient; in response to the basic reward satisfying the third preset condition, adjusting the basic reward weight coefficient to obtain the adjusted basic reward weight coefficient; and determining the initial predicted reward value based on the workload information, the performance information, the basic reward information, and the adjusted workload weight coefficient, performance weight coefficient, and basic reward weight coefficient.

[0013] According to another aspect of the embodiments of the present invention, there is also provided a reward determination device based on multi-dimensional data and dynamic weights, including: an acquisition module, configured to acquire basic information of a target object, where the basic information includes: workload information, performance information, and basic reward information; a prediction module, configured to use a reward prediction model to predict the basic information to obtain a predicted reward, where the reward prediction model is obtained by training a target model using basic information samples and predicted reward samples; and a determination module, configured to determine the final reward of the target object based on the predicted reward.

[0014] According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored executable program, and when the executable program runs, it controls the device where the computer-readable storage medium is located to execute the methods in various embodiments of the present invention.

[0015] According to another aspect of the embodiments of the present invention, there is also provided a computer program product, including a computer program, where the computer program implements the methods in various embodiments of the present invention when executed by a processor.

[0016] According to another aspect of the embodiments of the present invention, there is also provided a computer program product, including a non-volatile computer-readable storage medium, where the non-volatile computer-readable storage medium stores a computer program, and the computer program implements the methods in various embodiments of the present invention when executed by a processor.

[0017] In the embodiments of the present invention, by using a reward prediction model to predict the workload information, performance information, and basic reward information of employees, the salary calculation can be differentially adjusted according to the specific performance and contributions of each employee, thereby achieving the technical effect of more fair and personalized salary distribution based on personal basic information, and further solving the technical problem of poor adaptability of the existing salary calculation method. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0019] Figure 1 is a flowchart of an optional reward determination method based on multi-dimensional data and dynamic weights according to an embodiment of the present invention;

[0020] Figure 2 is a flowchart of an optional reward determination method based on multi-dimensional data and dynamic weights according to an embodiment of the present invention;

[0021] Figure 3It is a structural block diagram of an optional reward determination device based on multi-dimensional data and dynamic weights according to an embodiment of the present invention. Detailed implementation manners

[0022] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to an embodiment of the present invention, an embodiment of a reward determination method based on multi-dimensional data and dynamic weights is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that here.

[0025] Embodiments of the method can be executed in an electronic device including a memory and a processor or a similar computing device. Taking running on an electronic device as an example, the electronic device may include one or more processors (the processor may include, but is not limited to, a processing device such as a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Digital Signal Processing (DSP) chip, a MicroController Unit (MCU), a Field Programmable Gate Array (FPGA), a Neural-network Processor Unit (NPU), a Tensor Processing Unit (TPU), an Artificial Intelligence (AI) type processor, etc.) and a memory for storing data. Optionally, the above-mentioned electronic device may further include a transmission device for communication functions, an input / output device, and a display device. Those of ordinary skill in the art can understand that the above structural description is only illustrative and does not limit the structure of the above-mentioned electronic device. For example, the electronic device may further include more or fewer components than the above structural description, or have a configuration different from the above structural description.

[0026] The memory can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the reward determination method based on multi-dimensional data and dynamic weights in the embodiments of the present invention. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, implements the above-mentioned reward determination method based on multi-dimensional data and dynamic weights. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, a flash memory, or other non-volatile solid-state memories. In some instances, the memory may further include a memory remotely set relative to the processor, and these remote memories can be connected to the mobile terminal through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0027] The transmission device is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of a mobile terminal. In one example, the transmission device includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] The display device can be, for example, a touch-screen liquid crystal display (Liquid Crustal Display, LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display enables a user to interact with the user interface of the mobile terminal. In some embodiments, the above-mentioned mobile terminal has a graphical user interface (Graphical User Interface, GUI), and the user can perform human-computer interaction with the GUI through finger contacts and / or gestures on the touch-sensitive surface. The human-computer interaction function here optionally includes the following interactions: creating web pages, drawing, word processing, creating electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music, and / or web browsing, etc. The executable instructions for performing the above human-computer interaction functions are configured / stored in a computer program product or readable storage medium executable by one or more processors.

[0029] Figure 1 is a method according to an embodiment of the present invention, as Figure 1 shown, the method includes the following steps:

[0030] Step S102, obtain the basic information of the target object, where the basic information includes: workload information, performance information, and basic remuneration information.

[0031] Step S104, use the remuneration prediction model to predict the basic information to obtain the predicted remuneration, where the remuneration prediction model is obtained by training a target model using basic information samples and predicted remuneration samples.

[0032] Step S106, determine the final remuneration of the target object based on the predicted remuneration.

[0033] In step S102, obtain the basic information of employees from the enterprise management system. The basic information includes, but is not limited to, workload information (quantitative work data such as the number of tasks completed by employees, working hours, etc.), performance information (performance indicators such as the work quality score of employees, customer satisfaction, etc.), and basic remuneration information (the existing basic salary level of employees). These information are important bases for salary calculation, and all the collected data will be preprocessed to ensure the uniformity of data format and the absence of outliers for subsequent calculation and analysis.

[0034] In step S104, establish a remuneration prediction model using historical data and machine learning algorithms. This model is trained based on a large number of basic information samples and predicted remuneration samples to accurately predict the predicted remuneration of employees. The training process of the remuneration prediction model includes, but is not limited to, data preprocessing, feature engineering, model selection and parameter tuning, verification and testing, etc., to ensure the accuracy and generalization ability of the model. Through the remuneration prediction model, personalized salary calculation can be carried out according to the specific performance and workload of employees, which is more fair and reasonable and has a stronger incentive effect. In addition, the remuneration prediction model established using machine learning has high accuracy and stability and can better adapt to market changes and the company's operation needs.

[0035] In step S106, determine the final remuneration of employees according to the predicted remuneration and the result of dynamic weight adjustment. This step ensures the fairness and reasonableness of the salary, while considering the workload, performance of employees and the company's cost control objectives.

[0036] Based on steps S102 - S106, predict the workload information, performance information and basic remuneration information of employees through the remuneration prediction model, so that salary calculation can be differentially adjusted according to the specific performance and contributions of each employee, thereby realizing a more fair and personalized salary distribution. Combining the company's operation status and market changes, dynamically adjust the weights of workload, performance and basic salary to ensure that the salary calculation not only reflects the immediate performance of employees, but also takes into account the company's cost control and long-term development needs, making the salary payment mechanism more flexible and adaptable. Using the dynamic weight adjustment mechanism and the remuneration prediction model, while controlling the company's costs, it is possible to reasonably motivate employees to improve work efficiency and satisfaction, achieving a balance between the company's interests and employees' interests and solving the technical problem of poor adaptability of the existing salary calculation methods.

[0037] As an optional implementation method, based on the predicted remuneration, determine the final remuneration of the target object, including:

[0038] Step S201, obtain the remuneration plan information, and the remuneration plan information includes: cost control plan information and object incentive plan information.

[0039] Step S202: Determine the compensation adjustment coefficient based on the compensation plan information.

[0040] Step S203: Determine the final compensation based on the compensation adjustment coefficient and the predicted compensation.

[0041] In step S201, the cost control plan information includes the company's cost budget, financial goals, and cost control strategies. These information are used to guide the consideration of costs in the salary calculation process to ensure that the salary payment matches the company's financial situation. The object incentive plan information refers to setting different incentive plans according to the company's incentive policies and goals, such as the reward strategy for high-performance employees and the incentive measures for newly promoted employees, etc., which are used to guide the incentive part in the salary calculation process. This information can be obtained from the company's financial and human resource management systems and can also be updated in real time according to the company's development goals and market changes.

[0042] In step S202, according to the cost control plan information, if the company's goal is to strictly control costs, the adjustment coefficient can be set lower to reduce the salary increase; on the contrary, if the company's financial situation is good, a higher adjustment coefficient can be set to increase employees' salaries. According to the object incentive plan information, if the company hopes to focus on motivating a certain type of employee (such as high-performance employees), the incentive adjustment coefficient for this type of employee will be increased accordingly, and vice versa. The determination of the compensation adjustment coefficient needs to consider factors such as the company's overall financial situation, industry characteristics, employee types, and incentive policies to achieve a balance between cost control and employee motivation.

[0043] In step S203, the predicted compensation is obtained through the compensation prediction model in step S104, and the compensation adjustment coefficient is set based on the cost control and object incentive plan information determined in step S202. In this way, it can be ensured that the payment of the final compensation takes into account both the employees' personal abilities and contributions and reflects the company's financial strategies and incentive policies, thus better achieving the salary management goal of fairness, efficiency, and in line with the company's development.

[0044] Based on steps S201 - S203, the combination of financial strategies and salary management is strengthened, making the salary calculation more in line with the company's cost control goals, enhancing the responsiveness of salary calculation to employee incentive strategies, flexibly adjusting according to different employee types and incentive needs, and promoting employees' positive performance. By dynamically adjusting the compensation adjustment coefficient, the salary management becomes more flexible and can quickly adapt to market changes and company operation needs. These effects together promote the fair incentive culture within the enterprise, optimize the allocation of financial resources, and contribute to improving employee satisfaction and enterprise competitiveness.

[0045] Optionally, use the compensation prediction model to predict the basic information to obtain the predicted compensation, including:

[0046] Step S211: Use the reward prediction model to predict the basic information and obtain the first predicted reward.

[0047] Step S212: Obtain the basic guarantee reward.

[0048] Step S213: Based on the basic information, determine the additional reward for the target object.

[0049] Step S214: Based on the basic guarantee reward, additional reward, first predicted reward, and reward adjustment coefficient, obtain the predicted reward.

[0050] In step S211, based on the reward prediction model established with historical data and machine learning algorithms, a comprehensive analysis is performed on the employee's current workload information, performance information, and basic salary information to obtain the first predicted reward. This step ensures that the salary calculation can be accurately predicted based on the employee's current performance.

[0051] In step S212, the basic guarantee reward is the minimum salary level set by the company for employees, ensuring that employees can still obtain income to maintain their lives even in the case of low business volume or poor performance. The specific value of obtaining the basic guarantee reward is usually based on company policies, industry standards, and laws and regulations.

[0052] In step S213, the additional reward is the reward paid additionally according to the employee's excellent performance, special contributions, or specific company reward policies. By analyzing the basic information, such as the excellent performance in the current period, the special projects completed, or the significant improvement in the company's benefits, it is determined whether to give and how much additional reward.

[0053] In step S214, the final predicted reward is comprehensively calculated based on the basic guarantee reward (as the lower limit of salary calculation to ensure income stability), the first predicted reward (reflecting the salary level of the employee's current performance), the additional reward (used to motivate the employee's special contributions), and the reward adjustment coefficient (dynamically adjusted according to the company's cost control plan and object incentive plan to ensure that the salary calculation matches the company's strategy). Considering the first predicted reward, basic guarantee reward, and additional reward comprehensively, the salary calculation more comprehensively reflects the employee's personal value and contributions, avoiding unfair phenomena caused by a single indicator.

[0054] It should be noted that in this embodiment, the workload information is D1, the performance information is D2, the basic reward information is D3, the workload information weight coefficient is W1, the performance information weight coefficient is W2, the basic reward information weight coefficient is W3, the first predicted reward is C, the basic guarantee reward is B, the additional reward is C. The reward adjustment coefficient is α, and the predicted reward is S, where:

[0055] C = W1 * D1 + W2 * D2 + W3 * D3;

[0056] S = A + B + C * α.

[0057] Based on steps S211 - S214, through detailed salary composition analysis and adjustment, the company can manage salaries more precisely, give reasonable compensation to employees with different performances and contributions, and improve management efficiency and employee satisfaction. In addition, this calculation method is more scientific and reasonable, which not only reflects the value of employees but also takes into account the company's costs and compliance requirements, helping to create a harmonious labor - management relationship and enhance the company's overall competitiveness.

[0058] Optionally, based on the predicted compensation, determine the final compensation of the target object, including:

[0059] Step S221, obtain the historical compensation of the target object.

[0060] Step S222, based on the historical compensation and the predicted compensation, determine the predicted compensation level of the target object.

[0061] Step S223, based on the predicted compensation level, determine the compensation adjustment coefficient.

[0062] Step S224, based on the compensation adjustment coefficient and the predicted compensation, determine the final compensation.

[0063] In step S221, optionally, obtain the actual compensation data of the target object in the past period from the company's human resource management system or financial database, such as the monthly salary records in the past year. These data will be used as reference data for analyzing the long - term performance trend of employees and determining their compensation levels.

[0064] In step S222, the main purpose is to ensure that the employee's salary fluctuates within a reasonable range and avoid large fluctuations in income caused by abnormal fluctuations in the workload or performance of the current month. The specific approach is as follows:

[0065] Analyze the historical compensation trend: Determine the average value and fluctuation range of the employee's historical compensation, and use this as a benchmark to compare with the predicted compensation.

[0066] Combine cost control and incentive plans: Based on the company's cost control objectives and incentive policies, set corresponding adjustment coefficients for different predicted compensation levels. For example, for employees whose predicted compensation is significantly lower than the historical average level, the adjustment coefficient can be appropriately increased to ensure that their income is not lower than the minimum guarantee line under cost control; while for employees whose predicted compensation is much higher than the historical average level, the adjustment coefficient can be appropriately reduced to avoid out - of - control company costs.

[0067] In step S223, according to the predicted compensation level determined in step S222, look up the pre-set compensation adjustment coefficient table of the company. Each level corresponds to one or a group of adjustment coefficients. The setting of the adjustment coefficients needs to fully consider the balance between the company's financial health and employee motivation. For example, for employees with a relatively low predicted compensation level, the adjustment coefficient can be set higher to ensure that their income does not decrease excessively, while providing necessary motivation; for employees with a relatively high predicted compensation level, the adjustment coefficient can be set lower to prevent the cost pressure caused by overly high salary levels.

[0068] In step S224, the calculation of the final compensation combines the predicted compensation and the adjustment coefficient determined based on the predicted compensation level, ensuring the rationality of the salary and the effectiveness of employee motivation.

[0069] Based on steps S221 - S224, it effectively avoids the phenomenon that employees' income is abnormally low due to short-term workload or performance fluctuations, provides employees with a more stable income expectation, enhances job security and stability. It meets the company's cost control objectives and incentive policies, reasonably adjusts the salary level of employees, not only avoids excessive cost growth but also ensures the maintenance of the employee incentive mechanism, achieving the balance between the company's financial health and employee enthusiasm. The setting of the predicted compensation level makes the salary calculation consider not only the monthly work performance but also the historical performance of employees, ensuring the fairness of salary distribution and reducing the salary unfairness phenomenon caused by single prediction results.

[0070] Optionally, use the compensation prediction model to predict the basic information to obtain the predicted compensation, including:

[0071] Step S231, obtain the basic information sample.

[0072] Step S232, input the basic information sample into the target model to obtain the initial value of the predicted compensation.

[0073] Step S233, based on the initial value of the predicted compensation and the predicted compensation sample, train and optimize the target model to obtain the compensation prediction model.

[0074] Step S234, use the compensation prediction model to predict the basic information to obtain the predicted compensation.

[0075] In step S231, obtain a large number of employees' basic information samples from the company's internal system, including but not limited to workload data, performance scores, basic salary levels and other information. These samples need to cover employees in different positions, with different workloads and different performance performances to ensure the comprehensiveness and accuracy of model training.

[0076] In step S232, a large number of basic information samples of employees are obtained from the company's internal system, including but not limited to workload data, performance ratings, basic salary levels, and other information. These samples should cover employees in different positions, with different workloads and different performance levels to ensure the comprehensiveness and accuracy of model training.

[0077] In step S233, the initial predicted compensation value is compared with the actual historical salary data of employees (predicted compensation samples), and through an error feedback mechanism, the parameters of the model are adjusted to minimize the prediction error. This process may require multiple iterative trainings until the prediction accuracy of the model reaches the expected level. During the training process, technical means such as cross-validation and regularization can be adopted to prevent the model from overfitting and ensure the generalization ability of the model to new data.

[0078] In step S234, the optimized compensation prediction model will be used to predict the salary of employees under the new basic information. The latest basic information such as workload data, performance ratings, and basic salary levels is input into the optimized compensation prediction model, and the model will output a more accurate predicted compensation as the basis for salary calculation.

[0079] Based on steps S231 and S234, the continuous model training and optimization process improves the accuracy of predicted compensation, making the salary calculation more in line with the actual performance and contributions of employees, and avoiding unfair phenomena caused by prediction errors. The optimized compensation prediction model can achieve automated salary prediction, reduce manual intervention, improve the efficiency of salary management, and also reduce human errors. By providing more accurate salary predictions, the system can provide data support for the company's decision-making level to help them better formulate salary policies and cost control strategies to adapt to market changes and enterprise development needs.

[0080] Optionally, the basic information samples are input into the target model to obtain the initial predicted compensation value, including:

[0081] Step S241, preprocess the basic information to obtain the preprocessed basic information.

[0082] Step S242, obtain the basic information weight coefficients of the target model, where the basic information weight coefficients include: workload weight coefficient, performance weight coefficient, and basic compensation weight coefficient;

[0083] Step S243, determine the initial predicted compensation value based on the preprocessed basic information and the basic information weight coefficients.

[0084] In step S241, the preprocessing is a process of cleaning, formatting, and standardizing basic information such as the obtained workload data, performance data, and basic salary data to ensure data quality. The preprocessing steps may include removing outliers, filling in missing data, data normalization, etc. Through preprocessing, the noise and biases in the original data can be eliminated, improving the accuracy of subsequent model predictions.

[0085] In step S242, the basic information weight coefficients reflect the relative importance of workload, performance, and basic compensation in the compensation prediction model. These weight coefficients may be preset according to the company's salary policy, industry standards, and job characteristics. The weight coefficients include: workload weight coefficient (reflecting the proportion of workload in the first predicted compensation), performance weight coefficient (reflecting the proportion of performance score in the first predicted compensation), and basic compensation weight coefficient (reflecting the proportion of basic salary in the first predicted compensation). The setting of the weight coefficients needs to ensure that the sum is 1 to maintain the balance of the calculation. The introduction of the weight coefficients enables the model to more accurately reflect the actual contributions of employees and the company's emphasis on different factors, improving the accuracy and fairness of the predicted compensation.

[0086] In step S243, the initial predicted compensation comprehensively considers the employee's workload, performance performance, and basic salary. At the same time, the use of weight coefficients enables the calculation result to reflect the company's emphasis on different factors. The predicted compensation based on the weight coefficients can more precisely match the efforts and performance of employees, thereby optimizing the incentive effect and stimulating the enthusiasm and creativity of employees.

[0087] Based on steps S241 - S243, the introduction of weight coefficients enables the model to more accurately reflect the actual contributions of employees and the company's emphasis on different factors. Such a setting not only improves the scientificity and efficiency of salary management but also ensures the fairness and reasonableness of salary calculation, contributing to the establishment of a stable and harmonious labor - management relationship and promoting the long - term development of the enterprise and the improvement of its industry competitiveness.

[0088] Optionally, based on the preprocessed basic information and basic information weight coefficients, determining the initial predicted compensation includes:

[0089] Step S251, in response to the workload information satisfying the first preset condition, adjusting the workload weight coefficient to obtain an adjusted workload weight coefficient.

[0090] Step S252, in response to the performance information satisfying the second preset condition, adjusting the performance weight coefficient to obtain an adjusted performance weight coefficient.

[0091] Step S253, in response to the basic compensation satisfying the third preset condition, adjusting the basic compensation weight coefficient to obtain an adjusted basic compensation weight coefficient.

[0092] Step S254: Determine the initial predicted compensation value based on the workload information, performance information, basic compensation information, and the adjusted workload weight coefficient, performance weight coefficient, and basic compensation weight coefficient.

[0093] In step S251, when the workload information (such as the number of tasks completed, working hours, etc.) meets a specific first preset condition, the workload weight coefficient will be adjusted. For example, if the workload in a certain month significantly increases, the first preset condition can be "the workload information exceeds 120% of the historical average level", and at this time, the workload weight coefficient will be increased to motivate employees to further improve the workload while ensuring the company's cost control.

[0094] In step S252, when the performance information (such as performance scores, customer feedback, etc.) meets the second preset condition, the performance weight coefficient is adjusted. Assuming the second preset condition is "the performance information is lower than 80% of the historical average level", at this time, the performance weight coefficient will be decreased to encourage employees to improve work quality while avoiding additional costs for the company due to poor performance.

[0095] In step S253, when the basic compensation information meets the third preset condition, the basic compensation weight coefficient is adjusted. Assuming the third preset condition is "the basic compensation information is lower than the local minimum wage standard", at this time, the basic compensation weight coefficient will be increased to ensure the minimum living guarantee of employees while demonstrating the company's social responsibility.

[0096] In step S254, based on the real-time adjusted weight coefficients, the compensation prediction model can more accurately reflect the actual performance of employees and the company's needs, improve the accuracy of predicted compensation, and reduce human intervention and misjudgment.

[0097] Based on steps S251 - 254, by dynamically adjusting the weight coefficients, the salary calculation can respond in real time to changes in workload, performance, and basic compensation, improve the flexibility and adaptability of salary management, and ensure the coordination between the company's strategy and the actual situation. This mechanism ensures that the salary payment matches the company's costs and financial situation by timely adjusting the weight coefficients, avoids financial burdens caused by excessive incentives or insufficient basic guarantees, and realizes the maximization of cost - effectiveness. This implementation method not only improves the intelligence and automation level of salary management but also ensures the fairness and reasonableness of salary calculation, helps to promote the harmonious relationship between the company and employees, and enhances the company's competitiveness and industry influence.

[0098] Figure 2 It is a flowchart of another XX according to one embodiment of the present invention, as Figure 2 shown, and the method includes the following steps:

[0099] Step S201: Obtain the compensation plan information, which includes cost control plan information and object incentive plan information.

[0100] Step S202: Determine the compensation adjustment coefficient based on the compensation plan information.

[0101] Step S203: Determine the final compensation based on the compensation adjustment coefficient and the predicted compensation.

[0102] Step S211: Use the compensation prediction model to predict the basic information and obtain the first predicted compensation.

[0103] Step S212: Obtain the basic guaranteed compensation.

[0104] Step S213: Determine the additional bonus compensation for the target object based on the basic information.

[0105] Step S214: Obtain the predicted compensation based on the basic guaranteed compensation, additional bonus compensation, first predicted compensation, and compensation adjustment coefficient.

[0106] Step S221: Obtain the historical compensation of the target object.

[0107] Step S222: Determine the predicted compensation level of the target object based on the historical compensation and the predicted compensation.

[0108] Step S223: Determine the compensation adjustment coefficient based on the predicted compensation level.

[0109] Step S224: Determine the final compensation based on the compensation adjustment coefficient and the predicted compensation.

[0110] Step S231: Obtain the basic information sample.

[0111] Step S232: Input the basic information sample into the target model to obtain the initial value of the predicted compensation.

[0112] Step S233: Train and optimize the target model based on the initial value of the predicted compensation and the predicted compensation sample to obtain the compensation prediction model.

[0113] Step S234: Use the compensation prediction model to predict the basic information and obtain the predicted compensation.

[0114] Step S241: Preprocess the basic information to obtain the preprocessed basic information.

[0115] Step S242: Obtain the basic information weight coefficients of the target model, where the basic information weight coefficients include workload weight coefficient, performance weight coefficient, and basic compensation weight coefficient;

[0116] Step S243: Determine the initial predicted reward value based on the preprocessed basic information and the basic information weight coefficient.

[0117] Step S251: In response to the workload information satisfying the first preset condition, adjust the workload weight coefficient to obtain the adjusted workload weight coefficient.

[0118] Step S252: In response to the performance information satisfying the second preset condition, adjust the performance weight coefficient to obtain the adjusted performance weight coefficient.

[0119] Step S253: In response to the basic reward satisfying the third preset condition, adjust the basic reward weight coefficient to obtain the adjusted basic reward weight coefficient.

[0120] Step S254: Determine the initial predicted reward value based on the workload information, performance information, basic reward information, and the adjusted workload weight coefficient, performance weight coefficient, and basic reward weight coefficient.

[0121] Based on the above steps S201 to S254, in the embodiments of the present invention, by combining the cost control plan and the object incentive plan, the parameters for salary calculation are dynamically adjusted, achieving the balance between cost control and the incentive mechanism. Through the dynamic adjustment of the weight coefficients and the setting of additional rewards, the salary payment can be more personalized, accurately matching the actual performance of employees and the company's needs, achieving the purpose of improving the intelligent level of salary management, thereby achieving the technical effect of ensuring the fairness and reasonableness of salary calculation, and further solving the technical problem of poor adaptability of the existing salary calculation methods.

[0122] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that makes a contribution to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0123] In an embodiment of the present invention, there is also provided a reward determination device based on multi-dimensional data and dynamic weights. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0124] Figure 3 is a structural block diagram of a reward determination device based on multi-dimensional data and dynamic weights according to an embodiment of the present invention. As Figure 3 shown, the device includes:

[0125] An acquisition module 301, configured to acquire basic information of a target object, where the basic information includes: workload information, performance information, and basic reward information;

[0126] A prediction module 302, configured to predict the basic information by using a reward prediction model to obtain a predicted reward, where the reward prediction model is obtained by training a target model with basic information samples and predicted reward samples;

[0127] A determination module 303, configured to determine the final reward of the target object based on the predicted reward.

[0128] Optionally, the determination module 303 is further configured to determine the final reward of the target object based on the predicted reward, including: acquiring reward plan information, where the reward plan information includes: cost control plan information and object incentive plan information; determining a reward adjustment coefficient based on the reward plan information; and determining the final reward based on the reward adjustment coefficient and the predicted reward.

[0129] Optionally, the prediction module 302 is further configured to predict the basic information by using a reward prediction model to obtain a predicted reward, including: predicting the basic information by using the reward prediction model to obtain a first predicted reward; acquiring a basic guarantee reward; determining an additional reward for the target object based on the basic information; and obtaining the predicted reward based on the basic guarantee reward, the additional reward, the first predicted reward, and the reward adjustment coefficient.

[0130] Optionally, the prediction module 302 is further configured to determine the final reward of the target object based on the predicted reward, including: acquiring the historical reward of the target object; determining the predicted reward level of the target object based on the historical reward and the predicted reward; determining the reward adjustment coefficient based on the predicted reward level; and determining the final reward based on the reward adjustment coefficient and the predicted reward.

[0131] Optionally, the prediction module 302 is further configured to predict the basic information using a reward prediction model to obtain a predicted reward, including: obtaining a basic information sample; inputting the basic information sample into a target model to obtain an initial predicted reward value; training and optimizing the target model based on the initial predicted reward value and a predicted reward sample to obtain a reward prediction model; and predicting the basic information using the reward prediction model to obtain a predicted reward.

[0132] Optionally, the prediction module 302 is further configured to input the basic information sample into the target model to obtain an initial predicted reward value, including: preprocessing the basic information to obtain preprocessed basic information; obtaining basic information weight coefficients of the target model, where the basic information weight coefficients include: a workload weight coefficient, a performance weight coefficient, and a basic reward weight coefficient; and determining the initial predicted reward value based on the preprocessed basic information and the basic information weight coefficients.

[0133] Optionally, the prediction module 302 is further configured to determine the initial predicted reward value based on the preprocessed basic information and the basic information weight coefficients, including: in response to the workload information satisfying a first preset condition, adjusting the workload weight coefficient to obtain an adjusted workload weight coefficient; in response to the performance information satisfying a second preset condition, adjusting the performance weight coefficient to obtain an adjusted performance weight coefficient; in response to the basic reward satisfying a third preset condition, adjusting the basic reward weight coefficient to obtain an adjusted basic reward weight coefficient; and determining the initial predicted reward value based on the workload information, the performance information, the basic reward information, and the adjusted workload weight coefficient, performance weight coefficient, and basic reward weight coefficient.

[0134] It should be noted that the above-mentioned various modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited thereto: the above-mentioned modules are all located in the same processor; or, the above-mentioned various modules are separately located in different processors in any combination form.

[0135] According to one embodiment of the present invention, there is also provided an electronic device, including: a memory storing an executable program; and a processor configured to run the program, where when the program runs, it executes the above-mentioned reward determination method based on multi-dimensional data and dynamic weights.

[0136] Optionally, in this embodiment, the above-mentioned processor can be set to execute the following steps through a computer program:

[0137] Step S102, obtaining basic information of a target object, where the basic information includes: workload information, performance information, and basic reward information.

[0138] Step S104, use the reward prediction model to predict the basic information to obtain the predicted reward, where the reward prediction model is obtained by training a target model using basic information samples and predicted reward samples.

[0139] Step S106, determine the final reward of the target object based on the predicted reward.

[0140] According to one embodiment of the present invention, there is also provided a computer-readable storage medium, which includes a stored executable program. When the executable program runs, it controls the device where the storage medium is located to execute the above-mentioned reward determination method based on multi-dimensional data and dynamic weights.

[0141] Optionally, in this embodiment, the above storage medium can be set to store a computer program for executing the following steps:

[0142] Step S102, obtain the basic information of the target object, where the basic information includes: workload information, performance information, and basic reward information.

[0143] Step S104, use the reward prediction model to predict the basic information to obtain the predicted reward, where the reward prediction model is obtained by training a target model using basic information samples and predicted reward samples.

[0144] Step S106, determine the final reward of the target object based on the predicted reward.

[0145] Optionally, in this embodiment, the above storage medium may include, but is not limited to: USB flash drive, read-only memory (ROM for short), random access memory (RAM for short), mobile hard disk, magnetic disk, or optical disc, etc., various media that can store computer programs.

[0146] According to one embodiment of the present invention, there is also provided a computer program product, including a computer program, which implements the above-mentioned reward determination method based on multi-dimensional data and dynamic weights when executed by a processor.

[0147] Optionally, in this embodiment, the above computer program product can be set to execute a computer program for the following steps:

[0148] Step S102, obtain the basic information of the target object, where the basic information includes: workload information, performance information, and basic reward information.

[0149] Step S104, use the reward prediction model to predict the basic information to obtain the predicted reward, where the reward prediction model is obtained by training the target model using the basic information samples and the predicted reward samples.

[0150] Step S106, determine the final reward of the target object based on the predicted reward.

[0151] In the above embodiments of the present invention, the descriptions of the respective embodiments have their own emphases. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0152] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units can be a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the units or modules can be in electrical or other forms.

[0153] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0155] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0156] The foregoing is only the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for determining remuneration based on multidimensional data and dynamic weights, characterized in that: include: Obtaining basic information of the target object, wherein the basic information includes: workload information, performance information and basic remuneration information; Predicting the basic information using a reward prediction model to obtain a predicted reward, wherein the reward prediction model is obtained by training a target model using basic information samples and predicted reward samples; Based on the predicted remuneration, a final remuneration of the target object is determined.

2. The method according to claim 1, characterized in that Determining the final reward of the target object based on the predicted reward includes: Acquire compensation plan information, the compensation plan information including: cost control plan information and object incentive plan information; Determining a compensation adjustment factor based on the compensation plan information; The final remuneration is determined based on the remuneration adjustment factor and the predicted remuneration.

3. The method according to claim 2, characterized in that The basic information is predicted using a reward prediction model to obtain a predicted reward, including: Using the reward prediction model to predict the basic information, to obtain a first predicted reward; Get basic guaranteed remuneration; Based on the basic information, determining the additional reward remuneration for the target object; The predicted remuneration is obtained based on the basic guaranteed remuneration, the additional incentive remuneration, the first predicted remuneration and the remuneration adjustment coefficient.

4. The method according to any one of claims 1 to 3, characterized in that Determining the final reward of the target object based on the predicted reward includes: Obtaining historical compensation of the target object; Determining a predicted reward level of the target object based on the historical rewards and the predicted rewards; Determining a remuneration adjustment factor based on the predicted remuneration level; The final remuneration is determined based on the remuneration adjustment factor and the predicted remuneration.

5. The method according to claim 1, characterized in that: Using the reward prediction model to predict the basic information to obtain the predicted reward includes: Obtaining the basic information sample; Inputting the basic information sample into the target model to obtain an initial value of the predicted reward; Based on the predicted reward initial value and the predicted reward sample, training and optimizing the target model to obtain the reward prediction model; The basic information is predicted using the reward prediction model to obtain the predicted reward.

6. The method according to claim 5, characterized in that Inputting the basic information sample into the target model to obtain the predicted reward initial value includes: Preprocessing the basic information to obtain the preprocessed basic information; Obtaining basic information weight coefficients of the target model, wherein the basic information weight coefficients include: workload weight coefficient, performance weight coefficient and basic remuneration weight coefficient; The predicted reward initial value is determined based on the pre-processed basic information and the basic information weight coefficient.

7. The method according to claim 6, characterized in that Determining the predicted reward initial value based on the pre-processed basic information and the basic information weight coefficient includes: In response to the workload information satisfying a first preset condition, adjusting the workload weight coefficient to obtain the adjusted workload weight coefficient; In response to the performance information satisfying a second preset condition, adjusting the performance weight coefficient to obtain the adjusted performance weight coefficient; In response to the basic remuneration satisfying a third preset condition, adjusting the basic remuneration weight coefficient to obtain the adjusted basic remuneration weight coefficient; The predicted remuneration initial value is determined based on the workload information, the performance information, the basic remuneration information and the adjusted workload weight coefficient, the performance weight coefficient and the basic remuneration weight coefficient.

8. A reward determination device based on multi-dimensional data and dynamic weights, characterized in that: include: An acquisition module, used to acquire basic information of the target object, wherein the basic information includes: workload information, performance information and basic remuneration information; A prediction module, used to predict the basic information using a reward prediction model to obtain a predicted reward, wherein the reward prediction model is obtained by training a target model using basic information samples and predicted reward samples; A determination module is used to determine a final reward of the target object based on the predicted reward.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images