Task right allocation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a task right and interest allocation method and device, electronic equipment and a storage medium, belongs to the technical field of artificial intelligence, and is suitable for financial science and technology business scenes and medical science and technology business scenes. The method comprises the steps of performing task efficiency prediction based on historical task data to obtain predicted task efficiency data; obtaining a target task progress of a target user; performing task achievement prediction on the target task progress according to the predicted task efficiency data to obtain a target task achievement condition of the target user; screening out a target right and interest distribution strategy from the candidate right and interest distribution strategies according to the target task achievement condition; and performing right and interest distribution on the target user based on the candidate right and interest information of the target right and interest distribution strategy. According to the embodiment of the invention, rights and interests are allocated to the target user based on the candidate rights and interests information of the target rights and interests allocation strategy, and the corresponding rights and interests information can be allocated according to the actual task completion condition of the user, so that the rationality of task rights and interests information allocation is ensured.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and is applicable to financial technology business scenarios and medical technology business scenarios, and in particular to a task rights and interests distribution method and device, electronic equipment and storage medium. Background Art

[0002] Traditional equity allocation methods typically use static task constraint rules to allocate equity based on task achievement. For example, in a financial scenario, insurance agents of different levels are assigned corresponding tiered equity information based on their renewal rate performance, using pre-set tiered equity rules. However, this method of allocating tiered equity information fails to flexibly account for the varying capabilities of different insurance agents, resulting in irrational equity distribution. Therefore, improving the rationality of equity information distribution has become a pressing issue. Summary of the Invention

[0003] The main purpose of the embodiments of the present application is to propose a task equity distribution method and device, an electronic device and a storage medium, aiming to improve the rationality of equity information distribution.

[0004] To achieve the above objectives, a first aspect of an embodiment of the present application provides a method for allocating task benefits, the method comprising:

[0005] In response to a target user's equity allocation request, obtaining a candidate equity allocation strategy and candidate equity information of the candidate equity allocation strategy;

[0006] Acquiring historical task data of the target user, and performing task effectiveness prediction based on the historical task data to obtain predicted task effectiveness data;

[0007] Obtain the target task progress of the target user;

[0008] Performing a task achievement prediction on the target task progress based on the predicted task effectiveness data to obtain the target task achievement status of the target user;

[0009] Filtering a target equity distribution strategy from the candidate equity distribution strategies based on the achievement of the target task;

[0010] Equity is allocated to the target user based on the candidate equity information of the target equity allocation strategy.

[0011] In some embodiments, screening out a target equity distribution strategy from the candidate equity distribution strategies based on the achievement of the target task includes:

[0012] Obtaining a target candidate equity allocation strategy based on the achievement of the target task;

[0013] Performing an equity strategy evaluation on the target candidate equity allocation strategy using a pre-trained reinforcement learning model to obtain a candidate equity strategy score;

[0014] The target candidate equity allocation strategies are screened based on the candidate equity strategy scores to obtain the target equity allocation strategy.

[0015] In some embodiments, performing an equity strategy evaluation on the target candidate equity allocation strategy using a pre-trained reinforcement learning model to obtain a candidate equity strategy score includes:

[0016] Obtaining the expected value of the equity strategy of the target candidate equity allocation strategy through the reinforcement learning model;

[0017] Obtaining an equity strategy discount factor and an equity strategy learning rate for the expected value of the equity strategy;

[0018] The target candidate equity allocation strategy is scored according to a preset reward function, the equity strategy discount factor, the equity strategy learning rate, and the equity strategy expected value to obtain the candidate equity strategy score.

[0019] In some embodiments, screening the target candidate equity allocation strategies based on the candidate equity strategy scores to obtain the target equity allocation strategy includes:

[0020] Preliminarily screening the target candidate equity allocation strategies based on the candidate equity strategy scores to obtain a preliminary equity allocation strategy;

[0021] Performing an update detection on the target task achievement status through the reinforcement learning model to obtain an updated task achievement status;

[0022] Updating the target candidate equity allocation strategy based on the achievement of the update task to obtain an updated candidate equity allocation strategy;

[0023] Performing an equity strategy update evaluation on the updated candidate equity allocation strategy to obtain an updated candidate equity strategy score;

[0024] The preliminary equity allocation strategy is updated based on the updated candidate equity strategy score and the updated candidate equity allocation strategy to obtain the target equity allocation strategy.

[0025] In some embodiments, if the historical task data includes historical user level data, historical operation behavior data of the historical user level data, and historical task progress of the historical user level data;

[0026] The performing of task effectiveness prediction based on the historical task data to obtain predicted task effectiveness data includes:

[0027] Performing feature extraction on the historical operation behavior data using a pre-trained task effectiveness prediction model to obtain historical operation behavior features, and performing feature extraction on the historical task progress to obtain historical task progress features;

[0028] Task effectiveness prediction is performed based on the historical operation behavior characteristics and the historical task progress characteristics to obtain the predicted task effectiveness data.

[0029] In some embodiments, the task effectiveness prediction model includes a decision classification tree and a decision regression tree;

[0030] The performing of task effectiveness prediction based on the historical operation behavior characteristics and the historical task progress characteristics to obtain the predicted task effectiveness data includes:

[0031] Fusing the historical operation behavior features with the historical task progress features to obtain fused historical task features;

[0032] The task achievement status is predicted by the fused historical task features through the decision classification tree to obtain the predicted task completion probability;

[0033] The task progress parameters are predicted based on the fused historical task features through the decision regression tree to obtain predicted task completion data;

[0034] The predicted task performance data is determined based on the predicted task completion probability and the predicted task completion data.

[0035] In some embodiments, performing task achievement prediction on the target task progress based on the predicted task effectiveness data to obtain the target task achievement status of the target user includes:

[0036] Obtaining the prediction task achievement status of the prediction task performance data;

[0037] Obtain the remaining time of the target task progress;

[0038] The target task achievement status is predicted based on the predicted task achievement status and the remaining task period to obtain the target task achievement status.

[0039] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a task equity distribution device, the device comprising:

[0040] A rights information acquisition module, configured to acquire candidate rights allocation strategies and candidate rights information of the candidate rights allocation strategies in response to a target user's rights allocation request;

[0041] A task effectiveness prediction module is used to obtain the historical task data of the target user and perform task effectiveness prediction based on the historical task data to obtain predicted task effectiveness data;

[0042] A target task progress module is used to obtain the target task progress of the target user;

[0043] A task achievement prediction module is used to predict the progress of the target task based on the predicted task effectiveness data, and obtain the target task achievement status of the target user;

[0044] An equity distribution strategy screening module is used to screen a target equity distribution strategy from the candidate equity distribution strategies according to the achievement of the target task;

[0045] The equity distribution module is configured to distribute equity to the target user based on the candidate equity information of the target equity distribution strategy.

[0046] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0047] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method of the above-mentioned first aspect.

[0048] The task equity distribution method and apparatus, electronic device, and storage medium proposed in the present application first obtain candidate equity distribution strategies and candidate equity information of the candidate equity distribution strategies in response to an equity distribution request from a target user, providing equity data support for subsequent task equity distribution. Furthermore, task performance prediction is performed on the target user's historical task data to obtain predicted task performance data. This data can be used to predict the user's future task performance based on the user's historical task performance, further providing data support for subsequent equity distribution. Secondly, task achievement prediction is performed on the target task progress based on the predicted task performance data to obtain a target task achievement status. This can accurately identify the user's current task performance and provide real-time data support for subsequent equity distribution. Finally, a target equity distribution strategy is selected from the candidate equity distribution strategies based on the target task achievement status, ensuring that the equity distribution strategy matches the user's actual task achievement status to improve the rationality of equity distribution. Equity is then distributed to the target user based on the candidate equity information of the target equity distribution strategy. Accordingly, corresponding equity information can be allocated based on the user's actual task completion status, thereby ensuring the rationality of task equity information distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flowchart of the task equity allocation method provided in an embodiment of the present application;

[0050] Figure 2 yes Figure 1 Flowchart of step S102 in FIG.

[0051] Figure 3 yes Figure 2 Flowchart of step S202 in FIG.

[0052] Figure 4 yes Figure 1 Flowchart of step S104 in FIG.

[0053] Figure 5 yes Figure 1 Flowchart of step S105 in FIG.

[0054] Figure 6 yes Figure 5 Flowchart of step S502 in FIG.

[0055] Figure 7 yes Figure 5 Flowchart of step S503 in FIG.

[0056] Figure 8 This is a structural diagram of the task equity distribution device provided in an embodiment of the present application;

[0057] Figure 9This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0059] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0061] First, let’s analyze some of the terms used in this application:

[0062] Artificial intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. A branch of computer science, AI seeks to understand the essence of intelligence and create new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thinking. It also encompasses theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0063] The embodiments of the present application provide a task equity distribution method and device, an electronic device, and a storage medium, aiming to improve the rationality of equity information distribution.

[0064] The task equity distribution method and device, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the task equity distribution method in the embodiments of the present application is described.

[0065] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0066] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0067] The task equity distribution method provided in the embodiment of the present application relates to the field of artificial intelligence technology. The task equity distribution method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the task equity distribution method, etc., but is not limited to the above forms.

[0068] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0069] Figure 1 This is an optional flowchart of the task equity allocation method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0070] Step S101 : in response to a target user's equity allocation request, obtaining candidate equity allocation strategies and candidate equity information of the candidate equity allocation strategies.

[0071] Step S102 : Obtain historical task data of the target user, and perform task effectiveness prediction based on the historical task data to obtain predicted task effectiveness data.

[0072] Step S103: Obtain the target task progress of the target user.

[0073] Step S104 , predicting the target task progress based on the predicted task effectiveness data, and obtaining the target task achievement status of the target user.

[0074] Step S105 : Filtering the target equity distribution strategy from the candidate equity distribution strategies according to the target task achievement status.

[0075] Step S106: Allocate equity to the target user based on the candidate equity information of the target equity allocation strategy.

[0076] In steps S101 to S106 of the embodiment of the present application, first, by responding to the target user's equity allocation request, candidate equity allocation strategies and candidate equity information of the candidate equity allocation strategies are obtained, providing equity data support for subsequent task equity allocation. Task performance prediction is performed on the target user's historical task data to obtain predicted task performance data. Based on the user's historical task execution, the user's future task execution can be predicted, further providing data support for subsequent equity allocation. Secondly, task achievement prediction is performed on the target task progress based on the predicted task performance data to obtain the target task achievement status. This can accurately identify the user's current task execution status and provide real-time data basis for subsequent equity allocation. Finally, the target equity allocation strategy is screened from the candidate equity allocation strategies based on the target task achievement status, ensuring that the equity allocation strategy matches the user's actual task achievement status to improve the rationality of equity allocation. Equity is allocated to the target user based on the candidate equity information of the target equity allocation strategy, and corresponding equity information can be allocated based on the user's actual task completion status, thereby ensuring the rationality of task equity information distribution.

[0077] In step S101 of some embodiments, specifically, the equity distribution strategy refers to a task incentive plan set according to the task completion status of the target user, and the equity distribution strategy is used to determine a set of plans for distributing equity information to users.

[0078] Specifically, the equity distribution strategy may include but is not limited to the equity plan for the user completing a task for the first time, the equity plan for the user completing tasks of the corresponding level for the first time in a row, the equity plan for the user completing tasks of the corresponding level for the first time in a row in the first year, the equity plan for blind box lotteries, and the level supplementary equity plan for users who have not completed tasks of the corresponding level.

[0079] Specifically, the candidate rights and interests information refers to the rights and interests information contained in each rights and interests distribution strategy. The candidate rights and interests information may include but is not limited to gift certificates (such as shopping cards, online platform monthly cards, commission coupons, etc.), services (such as accompanying doctors, family doctors, physical examination cards, green passes, outpatient packages, etc.) bonuses and task resources (such as high-quality customer or patient contact lists, training resources, etc.).

[0080] For example, in a financial application scenario, in response to an equity distribution application submitted by an insurance agent or person in charge, multiple equity distribution incentive plans (such as the equity plan for the user's first completion of a task, the equity plan for the user's first consecutive completion of tasks of the corresponding level, etc.) are retrieved from the insurance agent database, and candidate equity information such as bonuses, training resources or gift certificates corresponding to the equity distribution incentive plan is extracted.

[0081] For example, in a medical application scenario, in response to a rights distribution application submitted by medical staff or department heads, multiple rights distribution incentive plans (such as a performance plan for medical staff completing a designated operation for the first time, a rights plan for achieving the corresponding nursing quality level for the first time continuously, etc.) are retrieved from the medical staff database, and candidate rights information such as bonuses, training resources or gift certificates corresponding to the rights distribution incentive plan is extracted.

[0082] In this embodiment, by responding to the target user's equity distribution request, obtaining candidate equity distribution strategies and candidate equity information of the candidate equity distribution strategies, it is possible to provide a variety of equity information options for subsequent equity distribution, thereby ensuring the diversity and flexibility of equity distribution.

[0083] In step S102 of some embodiments, specifically, the historical task data may include but is not limited to historical user level data, historical operation behavior data of historical user level data, historical task progress, historical product data and user capability data, etc., and the historical task data is dynamically changing data based on time series.

[0084] For example, in a financial application scenario, historical user level data can be the agent level of an insurance agent, which can range from 1 to 40 levels from junior to senior (each level is divided by virtual resources, such as 3 diamond points for one level), historical operation behavior data can be the frequency and method of the insurance agent's contact with customers, historical task progress can be the insurance agent's historical task completion status, such as the insurance agent's monthly insurance sales, quarterly insurance sales, annual insurance sales, customer satisfaction and customer renewal rate, etc., historical product data can be the market popularity of insurance products, the market supply and demand trends of insurance products, etc., and user capability data can be user training records, user skill assessment data, etc.

[0085] For example, in medical application scenarios, historical task data may include the professional title level of medical staff (such as from junior to director, each level is divided by skill points), historical operation behavior data may be the work behavior data of medical staff (such as the number of patients treated and the types and quantities of therapeutic drugs used, etc.), historical task progress may be the monthly surgical volume, monthly drug usage, annual scientific research progress, patient satisfaction and recovery rate of medical staff, etc., historical product data may be the market popularity and supply and demand trends of medical drugs or medical devices, and user ability data may be the training records and skill assessment data of medical staff, etc.

[0086] See also Figure 2 In some embodiments, if the historical task data includes historical user level data, historical operation behavior data of the historical user level data, and historical task progress of the historical user level data, step S102 includes but is not limited to steps S201 to S202:

[0087] Step S201 , extracting features from historical operation behavior data using a pre-trained task effectiveness prediction model to obtain historical operation behavior features, and extracting features from historical task progress to obtain historical task progress features.

[0088] Step S202 : performing task effectiveness prediction based on historical operation behavior characteristics and historical task progress characteristics to obtain predicted task effectiveness data.

[0089] In step S201 of some embodiments, specifically, the task effectiveness prediction model may be a random forest model, which is used to predict the performance of the target user in future tasks.

[0090] Specifically, historical operation behavior characteristics may include the frequency of users contacting customers, the method of following up with customers, etc.; historical task progress characteristics may include the completion status of the user's current task, such as the number of completed orders or sales.

[0091] Specifically, the time series features of the historical operation behavior data and the historical task progress can be extracted respectively through a preset sliding window.

[0092] For example, in financial and medical application scenarios, the timestamps of historical operational behavior data and historical task progress are obtained. With 30 days as the time unit, the sliding window function is used to calculate the mean, maximum value, rate of change and other statistics within each window. This is used to calculate the daily number of customer visits and policy submissions by insurance agents, and then calculate the daily number of surgeries performed by medical staff, the number of patients treated, the types and quantities of drugs used, and other operational behavior data. Dynamic window features such as the average daily number of visits in the past 30 days and the average weekly number of new policy submissions are generated.

[0093] Furthermore, by segmenting the historical operation behavior features and the historical task progress respectively, the historical behavior token and the historical task progress token can be obtained, and the historical behavior token and the historical task progress token can be word-embedded to extract the semantic features of the historical operation behavior features and the historical task progress.

[0094] For example, in financial application scenarios, the historical operational behavior text features of monthly insurance sales, quarterly insurance sales, and annual insurance sales are extracted based on the historical operational behavior data of insurance agents. The historical task progress text features of insurance product renewal rates and premium amounts are extracted based on the historical task progress of insurance agents.

[0095] For example, in medical application scenarios, the historical operational behavior text features of medical staff, such as monthly surgical volume, monthly drug usage, and monthly nursing task completion rate, are extracted based on their historical operational behavior data. The historical task progress text features of medical staff, such as patient recovery rate and treatment cost amount, are extracted based on their historical task progress.

[0096] Furthermore, the time series features of the historical operation behavior features and the text features of the historical operation behavior are spliced ​​together to obtain the historical operation behavior features, and the time series features of the historical task progress and the text features of the historical task progress are spliced ​​together to obtain the historical task progress features.

[0097] In this embodiment, feature extraction is performed on historical operation behavior data through a pre-trained task performance prediction model to obtain historical operation behavior features, and feature extraction is performed on historical task progress to obtain historical task progress features. This can capture the short-term change trend of the user's work mode and provide more timely data support for performance prediction.

[0098] See also Figure 3 In some embodiments, the task effectiveness prediction model includes a decision classification tree and a decision regression tree, and step S202 includes but is not limited to steps S301 to S304:

[0099] Step S301 , fusing historical operation behavior features with historical task progress features to obtain fused historical task features.

[0100] Step S302: predicting the task achievement status by integrating historical task features through a decision classification tree to obtain a predicted task completion probability.

[0101] Step S303: predicting task progress parameters based on the fused historical task features through a decision regression tree to obtain predicted task completion data.

[0102] Step S304 : determining predicted task effectiveness data based on the predicted task completion probability and the predicted task completion data.

[0103] In step S301 of some embodiments, the task performance prediction model specifically includes at least two decision classification trees and at least two decision regression trees. A decision classification tree is a tree-like model used for classification tasks that divides input data into different categories through a series of decision rules, such as predicting whether a target user can complete a task on time. A decision regression tree is a tree-like model used for regression tasks that evaluates a user's specific progress in completing a task by predicting continuous values, such as the estimated time to complete a task.

[0104] Specifically, the historical operation behavior characteristics are spliced ​​with the historical task progress characteristics to obtain the fused historical task characteristics.

[0105] For example, in financial application scenarios, the frequency of insurance agents contacting customers and the speed of completing orders are combined to form a more comprehensive feature set to describe the insurance agents' overall performance in past tasks. In medical application scenarios, the number of completed surgeries and the amount of treatment costs are combined to form a more comprehensive feature set to describe the overall performance of medical staff in past tasks.

[0106] In this embodiment, by integrating historical operation behavior features with historical task progress features, more comprehensive historical task execution characteristics of the user can be provided for subsequent task performance prediction, which helps to improve the accuracy of subsequent task performance prediction.

[0107] In step S302 of some embodiments, specifically, each decision classification tree votes on the possibility of the user completing the task based on the integrated historical task features, and the voting results of the decision classification tree are counted to represent the proportion of the user's task completion, and the probability value of the predicted task completion is output.

[0108] For example, in financial and medical application scenarios, each decision classification tree will judge whether the agent can complete the task on time based on the fused features (such as the frequency of contacting customers and the speed of completing orders, or the number of completed surgeries and the amount of treatment costs). If there are a total of 100 decision classification trees, and 82 decision classification trees indicate that the agent can complete the sales task or that the medical staff can complete the surgery task or the treatment cost task, then the predicted probability of task completion is 82%.

[0109] In this embodiment, the task achievement status is predicted by integrating historical task features through a decision classification tree to obtain a predicted task completion probability, which can effectively predict the possibility that the user can complete the task on time.

[0110] In step S303 of some embodiments, specifically, each decision regression tree will integrate historical task features to calculate the specific sales volume or specific treatment costs that the user may complete, and calculate the confidence interval of the standard deviation of the specific sales volume or specific treatment costs predicted by all decision regression trees to determine the predicted task completion data.

[0111] For example, in a financial application scenario, each decision regression tree will determine whether the agent can complete the sales amount based on the fused features (such as the user's sales amount). If there are a total of 100 decision regression trees, and the predicted confidence interval of the sales amount that can be completed is 5,000 to 6,000 yuan, then the predicted task completion data is 5,000 to 6,000 yuan.

[0112] For example, in medical application scenarios, for the prediction of treatment cost, each decision regression tree will also be evaluated based on the fused features (such as patient treatment costs). If there are a total of 100 decision regression trees, and the confidence interval of the predicted treatment surgery cost corresponding to the treatment disease is 40,000 to 50,000 yuan per patient, then the prediction task completion data is that the treatment surgery cost for each patient is between 40,000 and 50,000 yuan.

[0113] In step S304 of some embodiments, specifically, the predicted task effectiveness data is used to represent the performance of tasks that the target user may complete in the future.

[0114] For example, insurance agents have a high probability (82%) of completing tasks on time, and the estimated sales volume of the tasks they can complete is 5,000 to 6,000 yuan. This process is achieved through comprehensive data analysis.

[0115] In this embodiment, the predicted task performance data is determined based on the predicted task completion probability and the predicted task completion data, which can provide users with a comprehensive task performance evaluation, help users better understand their performance in future tasks, and facilitate subsequent improvement in the accuracy of task equity distribution.

[0116] Through steps S301 to S304, by fusing historical operation behavior characteristics and historical task progress characteristics, and using decision classification trees and decision regression trees to predict task completion status and specific data that can be completed, it is possible to combine historical data to predict the user's future task completion status, which helps to more accurately evaluate the user's work ability and potential, facilitates the subsequent formulation of a more reasonable equity distribution strategy, and thus helps to optimize the agent's resource allocation.

[0117] Through steps S201 to S202, feature extraction and task performance prediction are performed through the pre-trained task performance prediction model, which can provide users with accurate task performance evaluation, so as to identify high-potential users and users in need of assistance in advance, and provide scientific decision-making support for subsequent differentiated equity points.

[0118] In step S103 of some embodiments, specifically, the target task progress refers to the proportional relationship between the part of the task that the user has currently completed and the overall task.

[0119] Specifically, since the sales of different products vary between the off-season and the peak season, the measurement dimensions of the target tasks can be quarterly, monthly, specific days or specific hours, which are not limited here.

[0120] For example, in a financial application scenario, an insurance agent's current level is 3, and he needs to complete 3 policies, each with a premium of 2,000 yuan, or complete policies with premiums of more than 6,000 yuan. If the user has completed two policies with a premium of 2,500 yuan that month, the premium difference is 1,000, and the target task progress is 83%.

[0121] For example, in a medical application scenario, a medical staff member with the rank of associate chief physician needs to complete 10 operations, and the treatment cost of each operation is more than 20,000 yuan, or complete operations with a treatment cost of more than 200,000 yuan. If the medical staff has completed 6 operations with a treatment cost of 30,000 yuan in that month, the treatment cost difference is 20,000 yuan, and the target task progress is 90%.

[0122] In this embodiment, by obtaining the target task progress of the target user, the user's progress in the current task can be grasped in real time, providing accurate task completion time and progress information for subsequent task achievement prediction.

[0123] See also Figure 4 In some embodiments, step S104 includes but is not limited to steps S401 to S403:

[0124] Step S401: Obtain the predicted task achievement status of the predicted task performance data.

[0125] Step S402: Obtain the remaining time period of the target task progress.

[0126] Step S403 , predicting the target task progress based on the predicted task achievement status and the remaining task period, and obtaining the target task achievement status.

[0127] In step S401 of some embodiments, specifically, predicting the task achievement status refers to the possibility of the user completing the task.

[0128] For example, in financial application scenarios, the predicted task achievement of an insurance agent can be the probability of completing a sales task (such as an 80% probability of completing the task within the next month); in medical application scenarios, the predicted task achievement of medical staff can be the probability of completing the number of surgeries.

[0129] In step S402 of some embodiments, specifically, the remaining task period refers to the time range remaining for the user to complete the current task, which is usually expressed in time units such as days and hours.

[0130] For example, in a financial application scenario, if an insurance agent has completed 60% of their sales task on the 20th of this month, the remaining task period is 10 days; in a medical application scenario, if medical staff have completed 60% of their surgical task on the 20th of this month, the remaining task period is also 10 days.

[0131] In step S403 of some embodiments, specifically, the target task achievement status refers to the possibility and progress of the user completing the current task, and the target task achievement status includes unachieved tasks, normally achieved tasks, generally achieved tasks, supplemented achieved tasks, and manually adjusted achieved tasks. Among them, normally achieved tasks refer to the user's normal completion of task requirements based on personal ability; generally achieved tasks refer to the cumulative achievement of n times the monthly achievement requirements in n consecutive months when the general calculation is effective, and then it is deemed that n consecutive months have successfully achieved the requirements; supplemented achieved tasks refer to the user's ability to supplement excess virtual resources (such as diamond points) under the general calculation rules and continuous achievement rules when the current task requirements are not met; manually adjusted achieved tasks refer to the manual adjustment of the user's level in cases of key user complaints, star reduction caused by non-user reasons, and extension of the record date.

[0132] For example, in financial and medical application scenarios, by combining the predicted 80% completion of the task and the remaining 10 days, the possibility and progress of insurance agents or medical staff completing the remaining 40% of the task within the next 10 days can be predicted.

[0133] In this embodiment, the target task progress is predicted based on the predicted task completion status and the remaining task period, which can provide users with a comprehensive and specific task completion progress prediction, which is helpful for subsequently distributing differentiated rights and interests to users.

[0134] Through steps S401 to S403, by obtaining the predicted task completion status and the remaining task period, and combining this information to predict the task completion progress, it is possible to provide the user with an accurate and specific task completion progress assessment, and subsequently adjust the user's task rights and interests distribution strategy in a timely manner to enhance the user's work enthusiasm.

[0135] See also Figure 5 In some embodiments, step S105 includes but is not limited to steps S501 to S503:

[0136] Step S501: Obtain target candidate equity distribution strategies based on target task achievement status.

[0137] Step S502 : Perform equity strategy evaluation on the target candidate equity allocation strategy using a pre-trained reinforcement learning model to obtain a candidate equity strategy score.

[0138] Step S503 : Screen the target candidate equity allocation strategies based on the candidate equity strategy scores to obtain the target equity allocation strategy.

[0139] In step S501 of some embodiments, specifically, the candidate equity distribution strategy refers to an equity distribution plan that matches the target task achievement and is applicable to the user.

[0140] Specifically, the target candidate equity allocation strategy refers to a set of applicable equity incentive plans that are preliminarily screened based on the user's current level, amount, and current task completion status.

[0141] For example, in financial and medical application scenarios, if insurance agents or medical staff are close to meeting normal task completion conditions but face risks, candidate equity distribution strategies that include elements such as sprint rewards and special coaching can be screened out as target candidate equity distribution strategies.

[0142] In this embodiment, by obtaining the target candidate equity allocation strategy based on the target task achievement status, it is possible to ensure that the equity allocation of subsequent tasks focuses on the most relevant candidate equity allocation strategy, avoiding the waste of computing resources caused by the full strategy evaluation and improving the efficiency of the equity allocation of subsequent tasks.

[0143] See also Figure 6 In some embodiments, step S502 includes but is not limited to steps S601 to S603:

[0144] Step S601: obtaining the expected value of the equity strategy of the target candidate equity allocation strategy through a reinforcement learning model.

[0145] Step S602 : Obtain the equity strategy discount factor and the equity strategy learning rate of the expected value of the equity strategy.

[0146] Step S603 , performing an equity strategy score on the target candidate equity allocation strategy according to a preset reward function, an equity strategy discount factor, an equity strategy learning rate, and an equity strategy expected value, to obtain a candidate equity strategy score.

[0147] In step S601 of some embodiments, specifically, the expected value of the equity strategy refers to the expected long-term benefit value that the equity allocation strategy may bring in the future.

[0148] Specifically, the reinforcement learning model can be a DQN (Deep Q-Network), which is used to decide whether to use the target candidate equity allocation strategy. Furthermore, DQN evaluates the possible use of the target candidate equity allocation strategy based on the encoded retrieval information of the current state and selects the corresponding target candidate equity allocation strategy. It evaluates the potential value of different target candidate equity allocation strategies and selects the optimal target candidate equity allocation strategy to maximize the expected reward of future retrieval.

[0149] For example, in financial and medical application scenarios, when evaluating a tiered new order reward strategy, DQN considers factors such as the insurance agent's historical performance, the quality of customer resources, or the medical staff's historical performance, the difficulty of patient treatment, and other factors to predict the cumulative value improvement that the strategy may bring over the next three assessment cycles.

[0150] In this embodiment, the expected value of the equity strategy of the target candidate equity allocation strategy is obtained through the reinforcement learning model, which can establish a quantitative estimation mechanism for the effect of the equity allocation strategy, provide a basic value reference for subsequent equity strategy scoring, and enable the model to distinguish between superficial incentive effects and substantial long-term value, which helps to dynamically allocate corresponding equity allocation strategies to different users in the future, thereby improving the flexibility of task equity allocation.

[0151] In step S602 of some embodiments, specifically, the equity strategy discount factor is used to measure the current value of the future benefits of the target candidate equity allocation strategy, and is usually used to consider the impact of time value.

[0152] Specifically, the equity policy learning rate refers to the speed at which DQN accepts new information, which affects the adjustment range of DQN's evaluation of the target candidate equity allocation strategy.

[0153] In step S603 of some embodiments, specifically, the reward function is a standard used in reinforcement learning to measure the target candidate equity distribution strategy.

[0154] Specifically, the reward function design includes multiple indicators such as task goal achievement, cost-benefit ratio, and agent satisfaction. The specific scoring process first standardizes each dimension and then performs a weighted synthesis according to the preset weights.

[0155] Specifically, if the user's performance improves after using the target candidate equity allocation strategy, positive rewards will be given; if the user still has difficulties in business development after using the target candidate equity allocation strategy, positive business development support will be given; if the target production capacity is too high and there is spare capacity, the user will be given task guidance.

[0156] For example, in financial application scenarios, for renewal and maintenance incentive strategies, the expected value of the strategy, the matching degree with insurance agents, the implementation cost-benefit ratio and other factors are comprehensively calculated to finally generate a comprehensive score.

[0157] In this embodiment, the target candidate equity allocation strategy is scored based on the preset reward function, equity strategy discount factor, equity strategy learning rate and equity strategy expected value. A standardized strategy value evaluation framework can be established, which enables equity strategy schemes of different natures to be compared on a unified dimension, solving the standardization problem of hybrid strategy selection and further helping to improve the rationality of equity allocation in subsequent tasks.

[0158] Through steps S601 to S603, the expected value of the equity strategy is obtained through the reinforcement learning model, and the target candidate equity allocation strategy is scored in combination with the equity strategy discount factor, equity strategy learning rate and reward function. This can scientifically and accurately evaluate the potential value of each equity allocation strategy, thereby selecting the target candidate equity allocation strategy suitable for each user and improving the rationality of task equity allocation.

[0159] See also Figure 7 In some embodiments, step S503 includes but is not limited to steps S701 to S705:

[0160] Step S701 : Preliminarily screen the target candidate equity allocation strategies based on the candidate equity strategy scores to obtain a preliminary equity allocation strategy.

[0161] Step S702: Update and detect the target task achievement status through the reinforcement learning model to obtain the updated task achievement status.

[0162] Step S703: updating the target candidate equity allocation strategy based on the completion of the update task to obtain an updated candidate equity allocation strategy.

[0163] Step S704 : performing an equity strategy update evaluation on the updated candidate equity allocation strategy to obtain an updated candidate equity strategy score.

[0164] Step S705 : updating the preliminary equity allocation strategy based on the updated candidate equity strategy scores and the updated candidate equity allocation strategies to obtain a target equity allocation strategy.

[0165] In step S701 of some embodiments, specifically, the preliminary equity allocation strategy refers to an equity allocation strategy obtained after preliminary screening, which is a set of high-quality equity strategies selected based on the scores of candidate equity strategies.

[0166] Specifically, according to the score of each candidate equity allocation strategy, screening is performed according to preset screening rules (such as selecting the top strategies with the highest scores).

[0167] For example, in financial and medical application scenarios, the three equity incentive plans with the highest scores are selected based on the initial score, such as bonuses for achieving level tasks, additional training opportunities, and shopping cards.

[0168] In this embodiment, the target candidate equity allocation strategies are preliminarily screened based on the candidate equity strategy scores to obtain preliminary equity allocation strategies, which can screen out appropriate equity allocation strategies for different users and improve the rationality of task equity allocation.

[0169] In step S702 of some embodiments, specifically, updating the task achievement status refers to the latest status obtained after re-testing the target task achievement status through the reinforcement learning model, reflecting the latest progress of the user's task completion.

[0170] Specifically, the reinforcement learning model will re-evaluate the achievement of the target task based on the latest task data (such as the user's task progress this week, the possibility of the user completing the task this week, etc.).

[0171] For example, in financial and medical application scenarios, if an insurance agent or medical staff estimates time to update, DQN updates the task completion status to the expected task completion status within the next week.

[0172] In this embodiment, the target task achievement status is updated and detected through the reinforcement learning model to obtain the updated task achievement status, which can timely reflect the latest progress of the user's task completion and provide a basis for subsequent equity strategy adjustments.

[0173] In step S703 of some embodiments, specifically, the updated candidate equity distribution strategy refers to a set of equity distribution strategies adjusted according to the achievement of the update task.

[0174] For example, in financial and medical application scenarios, if the updated task completion status shows that insurance agents or medical staff can double the task completion by completing the task, the equity incentive plan can be adjusted to a double task completion incentive strategy, a double bonus incentive strategy, and a high-quality user list strategy.

[0175] In this embodiment, the target candidate equity allocation strategy is updated based on the completion of the update task to obtain an updated candidate equity allocation strategy. The equity allocation strategy can be dynamically adjusted according to the latest task progress to ensure the real-time and effectiveness of the equity strategy.

[0176] In step S704 of some embodiments, specifically, the updated candidate equity strategy score is a new score obtained by evaluating the updated candidate equity allocation strategy through a reinforcement learning model.

[0177] Specifically, DQN is used to evaluate the potential value of updating candidate equity allocation strategies for improving agent performance and give a specific score.

[0178] In this embodiment, by performing an equity strategy update evaluation on the updated candidate equity allocation strategy, the equity incentive effect of the updated candidate equity allocation strategy can be quantified, thereby improving the accuracy of task equity allocation.

[0179] In step S705 of some embodiments, specifically, the target equity distribution strategy refers to the equity distribution strategy that is finally determined and most suitable for the user.

[0180] For example, in financial and medical application scenarios, if the updated candidate equity strategy scores show that an equity incentive plan with an increased bonus amount is more effective, the equity incentive plan will be included in the final target equity distribution strategy.

[0181] In this embodiment, the preliminary equity allocation strategy is updated based on the updated candidate equity strategy scores and the updated candidate equity allocation strategy, which can ensure that the equity allocation strategy finally selected is the best, maximize the possibility of users completing tasks, and further improve the accuracy of task equity allocation.

[0182] Through steps S701 to S705, by dynamically updating the target task achievement status and the equity distribution strategy, and combining the reinforcement learning model to evaluate the updated equity distribution strategy, it is possible to adjust the equity distribution strategy in real time to highly match the current task progress of different users, realize the dynamic task progress changes of users, and reasonably distribute task equity.

[0183] Through steps S501 to S503, by combining the target task achievement status and the evaluation of the reinforcement learning model, the equity distribution strategy that best suits the user can be accurately screened out, thereby improving the rationality of task equity distribution.

[0184] In step S106 of some embodiments, specifically, the candidate equity information corresponding to the screened target equity distribution strategy may be used as the target equity information.

[0185] For example, in a financial application scenario, if the target benefit allocation strategy is to give additional bonuses, the target benefit information extracted from the target benefit allocation strategy is the bonus amount (such as 1,000 yuan) and allocated to the insurance agent. If the target benefit allocation strategy is a benefit plan for the user to complete the corresponding level tasks for the first time in the first year, the target benefit information extracted from the target benefit allocation strategy is a 1,000 yuan shopping card and a list of high-quality customer contacts and allocated to the insurance agent.

[0186] For example, in a medical application scenario, if the target benefit allocation strategy is to give additional bonuses, the target benefit information extracted from the target benefit allocation strategy is the bonus amount (such as 2,000 yuan) allocated to medical staff. If the target benefit allocation strategy is a benefit plan for users to complete tasks of the corresponding level for the first time in the first year, the target benefit information extracted from the target benefit allocation strategy is a 1,000 yuan shopping card, a contact list of patients with the types of diseases that medical staff are good at treating, and the working hours and duration allocated to medical staff.

[0187] Specifically, the target users are allocated equity based on the candidate equity information of the target equity allocation strategy, which solves the problem of being unable to flexibly allocate equity according to the differences in the capabilities of different users and improves the rationality of task equity allocation.

[0188] The embodiment of the present application first obtains candidate equity allocation strategies and candidate equity information of the candidate equity allocation strategies in response to the equity allocation request of the target user, providing equity data support for subsequent task equity allocation, and obtains predicted task efficiency data by performing task efficiency prediction on the historical task data of the target user. Based on the user's historical task execution, the user's future task execution can be predicted, further providing data support for subsequent equity allocation; secondly, task achievement prediction is performed on the target task progress based on the predicted task efficiency data to obtain the target task achievement status, which can accurately identify the user's current task execution status and provide real-time data basis for subsequent equity allocation; finally, the target equity allocation strategy is screened out from the candidate equity allocation strategies based on the target task achievement status, ensuring that the equity allocation strategy matches the user's actual task achievement status to improve the rationality of equity allocation, and equity allocation is performed on the target user based on the candidate equity information of the target equity allocation strategy, which can allocate corresponding equity information based on the user's actual task completion status, thereby ensuring the rationality of task equity information allocation.

[0189] See also Figure 8The present application also provides a task equity distribution device that can implement the above-mentioned task equity distribution method. The device includes:

[0190] A rights information acquisition module, configured to obtain candidate rights allocation strategies and candidate rights information of the candidate rights allocation strategies in response to a target user's rights allocation request;

[0191] The task effectiveness prediction module is used to obtain the historical task data of the target user and perform task effectiveness prediction based on the historical task data to obtain predicted task effectiveness data;

[0192] Target task progress module, used to obtain the target task progress of the target user;

[0193] The task achievement prediction module is used to predict the progress of the target task based on the predicted task effectiveness data and obtain the target task achievement status of the target user;

[0194] The equity distribution strategy screening module is used to screen the target equity distribution strategy from the candidate equity distribution strategies based on the achievement of the target task;

[0195] The equity allocation module is used to allocate equity to target users based on the candidate equity information of the target equity allocation strategy.

[0196] The specific implementation of the task equity distribution device is basically the same as the specific embodiment of the above-mentioned task equity distribution method, and will not be repeated here.

[0197] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-described task equity allocation method when executing the computer program. The electronic device can be any smart terminal, including a tablet computer and an in-vehicle computer.

[0198] See also Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0199] The processor 901 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0200] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store the processing system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called by the processor 901 to execute the task equity distribution method of the embodiments of this application;

[0201] Input / output interface 903, used to implement information input and output;

[0202] Communication interface 904, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0203] Bus 905 , which transmits information between various components of the device (e.g., processor 901 , memory 902 , input / output interface 903 , and communication interface 904 );

[0204] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0205] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned task equity distribution method.

[0206] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0207] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0208] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0209] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0210] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0211] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0212] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0213] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0214] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0215] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0216] If 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 application, 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, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0217] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A task equity distribution method, characterized in that: The method comprises: In response to a target user's equity allocation request, obtaining a candidate equity allocation strategy and candidate equity information of the candidate equity allocation strategy; Acquiring historical task data of the target user, and performing task effectiveness prediction based on the historical task data to obtain predicted task effectiveness data; Obtain the target task progress of the target user; Performing a task achievement prediction on the target task progress based on the predicted task effectiveness data to obtain the target task achievement status of the target user; Filtering a target equity distribution strategy from the candidate equity distribution strategies based on the achievement of the target task; Equity is allocated to the target user based on the candidate equity information of the target equity allocation strategy.

2. The method according to claim 1, characterized in that The step of selecting a target equity distribution strategy from the candidate equity distribution strategies based on the achievement of the target task includes: Obtaining a target candidate equity allocation strategy based on the achievement of the target task; Performing an equity strategy evaluation on the target candidate equity allocation strategy using a pre-trained reinforcement learning model to obtain a candidate equity strategy score; The target candidate equity allocation strategies are screened based on the candidate equity strategy scores to obtain the target equity allocation strategy.

3. The method according to claim 2, characterized in that The target candidate equity allocation strategy is evaluated using the pre-trained reinforcement learning model to obtain a candidate equity strategy score, including: Obtaining the expected value of the equity strategy of the target candidate equity allocation strategy through the reinforcement learning model; Obtaining an equity strategy discount factor and an equity strategy learning rate for the expected value of the equity strategy; The target candidate equity allocation strategy is scored according to a preset reward function, the equity strategy discount factor, the equity strategy learning rate, and the equity strategy expected value to obtain the candidate equity strategy score.

4. The method according to claim 3, characterized in that The screening of the target candidate equity allocation strategies based on the candidate equity strategy scores to obtain the target equity allocation strategy includes: Preliminarily screening the target candidate equity allocation strategies based on the candidate equity strategy scores to obtain a preliminary equity allocation strategy; Performing an update detection on the target task achievement status through the reinforcement learning model to obtain an updated task achievement status; Updating the target candidate equity allocation strategy based on the achievement of the update task to obtain an updated candidate equity allocation strategy; Performing an equity strategy update evaluation on the updated candidate equity allocation strategy to obtain an updated candidate equity strategy score; The preliminary equity allocation strategy is updated based on the updated candidate equity strategy score and the updated candidate equity allocation strategy to obtain the target equity allocation strategy.

5. The method according to claim 1, wherein If the historical task data includes historical user level data, historical operation behavior data of the historical user level data, and historical task progress of the historical user level data; The performing of task effectiveness prediction based on the historical task data to obtain predicted task effectiveness data includes: Performing feature extraction on the historical operation behavior data using a pre-trained task effectiveness prediction model to obtain historical operation behavior features, and performing feature extraction on the historical task progress to obtain historical task progress features; Task effectiveness prediction is performed based on the historical operation behavior characteristics and the historical task progress characteristics to obtain the predicted task effectiveness data.

6. The method according to claim 5, characterized in that The task effectiveness prediction model includes a decision classification tree and a decision regression tree; The performing of task effectiveness prediction based on the historical operation behavior characteristics and the historical task progress characteristics to obtain the predicted task effectiveness data includes: Fusing the historical operation behavior features with the historical task progress features to obtain fused historical task features; The task achievement status is predicted by the fused historical task features through the decision classification tree to obtain the predicted task completion probability; The task progress parameters are predicted based on the fused historical task features through the decision regression tree to obtain predicted task completion data; The predicted task performance data is determined based on the predicted task completion probability and the predicted task completion data.

7. The method according to any one of claims 1 to 6, characterized in that The step of performing task achievement prediction on the target task progress based on the predicted task effectiveness data to obtain the target task achievement status of the target user includes: Obtaining the prediction task achievement status of the prediction task performance data; Obtain the remaining time of the target task progress; The target task achievement status is predicted based on the predicted task achievement status and the remaining task period to obtain the target task achievement status.

8. A task rights distribution device, characterized in that: The device comprises: A rights information acquisition module, configured to acquire candidate rights allocation strategies and candidate rights information of the candidate rights allocation strategies in response to a target user's rights allocation request; A task effectiveness prediction module is used to obtain the historical task data of the target user and perform task effectiveness prediction based on the historical task data to obtain predicted task effectiveness data; A target task progress module is used to obtain the target task progress of the target user; A task achievement prediction module is used to predict the progress of the target task based on the predicted task effectiveness data, and obtain the target task achievement status of the target user; An equity distribution strategy screening module is used to screen a target equity distribution strategy from the candidate equity distribution strategies according to the achievement of the target task; The equity distribution module is configured to distribute equity to the target user based on the candidate equity information of the target equity distribution strategy.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the task equity distribution method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the task equity distribution method according to any one of claims 1 to 7 is implemented.

Images