Task processing method and device, computer equipment and storage medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to a task processing method and device, computer equipment and a storage medium, and the method comprises the steps: in a business processing flow, if business data meeting an interception condition is detected, constructing an auditing task based on the business data; recording task information of the auditing task into a specified task table, and screening out a to-be-distributed target task from the specified task table; obtaining multi-dimensional information of candidate auditing personnel, and obtaining task data of the target task; generating personnel weights of the candidate auditing personnel based on the multi-dimensional information; performing score generation processing on the multi-dimensional information, the task data and the personnel weight to obtain a comprehensive score of the candidate auditing personnel corresponding to the target task; and screening the target auditing personnel with the highest score from all the comprehensive scores, and allocating the target task to the target auditing personnel. The method can be applied to task processing scenes in the financial science and technology field and the medical field, and the accuracy and intelligence of task allocation processing are improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology and can be applied to fields such as fintech and digital healthcare, particularly to task processing methods, devices, computer equipment, and storage media. Background Technology

[0002] In traditional document review systems, task review operations dominate. For example, in the insurance quotation process, tasks such as reviewing insurance policies, endorsements, and vehicle inspections are required. However, current task allocation mainly relies on fixed rules, which has significant shortcomings in terms of accuracy and intelligence. Fixed rules typically allocate tasks based on simple, preset conditions, lacking the flexibility to adapt to complex business scenarios and dynamic changes, and making it difficult to accurately and intelligently allocate tasks according to actual circumstances. Specifically, the extensive allocation model corresponding to fixed rules easily leads to unreasonable task allocation, resulting in some processing personnel being overloaded while others are idle, affecting the overall review efficiency and quality.

[0003] For example, in credit insurance review within the financial sector, traditional fixed rules may allocate tasks solely based on the client's industry, neglecting crucial factors such as the client company's size and historical credit rating changes. Assigning review tasks to large companies in high-risk industries with good credit ratings to inexperienced reviewers could lead to inaccurate and inefficient reviews, increasing potential risks for the insurance company. Similarly, in medical insurance claims review within the healthcare sector, fixed rules may allocate tasks only based on the type of disease, without considering the complexity of the condition or the specificity of the treatment plan. For claims involving multiple rare diseases and complex treatment plans, assigning them to reviewers with insufficient knowledge of rare diseases may result in inaccurate assessments of the reasonableness and accuracy of the claim, impacting patient rights and the insurance company's service quality.

[0004] Therefore, there is an urgent need to provide an intelligent task allocation method and system to improve the accuracy and intelligence of task allocation and enhance the overall efficiency of the document review system. Summary of the Invention

[0005] The purpose of this application is to provide a task processing method, apparatus, computer device, and storage medium to solve the technical problem of low accuracy and intelligence in existing task allocation methods.

[0006] Firstly, a task processing method is provided, including:

[0007] In the business processing flow, if business data that meets the interception conditions is detected, a corresponding audit task is constructed based on the business data;

[0008] The task information of the audit task is recorded in a preset designated task table, and the target tasks to be assigned are filtered out from the designated task table.

[0009] Obtain multi-dimensional information of multiple pre-set candidate reviewers, and obtain task data for the target task;

[0010] Based on the multi-dimensional information, a personnel weight is generated for each of the candidate reviewers;

[0011] Based on a preset score analysis strategy, the multi-dimensional information, the task data, and the personnel weights are processed to generate scores, thereby obtaining the comprehensive score of each candidate reviewer corresponding to the target task.

[0012] Select the target reviewer with the highest score from all the comprehensive scores, and assign the target task to the target reviewer.

[0013] Secondly, a task processing apparatus is provided, comprising:

[0014] The detection module is used to construct a corresponding audit task based on business data that meets the interception conditions during the business processing flow.

[0015] The first processing module is used to record the task information of the review task into a preset designated task table, and to filter out the target tasks to be assigned from the designated task table.

[0016] The first acquisition module is used to acquire multi-dimensional information of multiple preset candidate reviewers, as well as to acquire task data of the target task;

[0017] The first generation module is used to generate the personnel weight of each of the candidate reviewers based on the multi-dimensional information;

[0018] The second processing module is used to perform score generation processing on the multi-dimensional information, the task data and the personnel weight based on a preset score analysis strategy, so as to obtain the comprehensive score of each candidate reviewer corresponding to the target task;

[0019] The allocation module is used to filter out the target reviewer with the highest score from all the comprehensive scores and assign the target task to the target reviewer.

[0020] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described task processing method.

[0021] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described task processing method.

[0022] In the above-mentioned task processing method, apparatus, computer equipment, and storage medium, firstly, in the business processing flow, if business data that meets the interception conditions is detected, a corresponding review task is constructed based on the business data; then, the task information of the review task is recorded in a preset designated task table, and target tasks to be assigned are filtered from the designated task table; next, multi-dimensional information of multiple preset candidate reviewers is obtained, as well as task data of the target task; subsequently, personnel weights of each candidate reviewer are generated based on the multi-dimensional information; further, based on a preset score analysis strategy, scores are generated from the multi-dimensional information, the task data, and the personnel weights to obtain a comprehensive score for each candidate reviewer corresponding to the target task; finally, the target reviewer with the highest score is selected from all the comprehensive scores, and the target task is assigned to the target reviewer. Based on the above automated processing flow, in the business processing flow of this application, if business data that meets the interception conditions is detected, an audit task will be constructed based on the business data. Then, the task information of the audit task will be recorded in a designated task table, and the target tasks to be assigned will be selected from the designated task table. After that, personnel weights will be generated based on the multi-dimensional information of multiple candidate auditors. Then, based on the use of a score analysis strategy, scores will be generated by processing the multi-dimensional information, the task data of the acquired target tasks, and the personnel weights to obtain the comprehensive score of each candidate auditor for the target task. Finally, the target auditor with the highest score will be selected from all the comprehensive scores, and the target task will be assigned to the target auditor. This can effectively improve the rationality, accuracy, and intelligence of task allocation. Attached Figure Description

[0023] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0025] Figure 2 This is a flowchart of an embodiment of the task processing method according to this application;

[0026] Figure 3This is a schematic diagram of the structure of one embodiment of the task processing apparatus according to this application;

[0027] Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0031] like Figure 1 As shown, system architecture 100 may include terminal device 101, network 102, and server 103. Terminal device 101 may be a laptop 1011, tablet 1012, or mobile phone 1013. Network 102 is used as a medium to provide a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0032] Users can use terminal device 101 to interact with server 103 via network 102 to receive or send messages, etc. Various communication client applications can be installed on terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0033] Terminal device 101 can be various electronic devices with a display screen and support web browsing. In addition to laptops 1011, tablets 1012, or mobile phones 1013, terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer, and a desktop computer, etc.

[0034] Server 103 can be a server that provides various services, such as a backend server that provides support for the pages displayed on terminal device 101.

[0035] It should be noted that the task processing method provided in the embodiments of this application is generally executed by a server / terminal device, and correspondingly, the task processing device is generally set in the server / terminal device.

[0036] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0037] Continue to refer to Figure 2 A flowchart illustrating an embodiment of the task processing method according to this application is shown. The order of steps in the flowchart can be changed, and some steps can be omitted, depending on different needs. The task processing method provided by this application embodiment can be applied to any scenario requiring task processing, and thus can be applied to products in these scenarios, such as task processing products in the financial insurance and medical fields. The task processing method includes the following steps:

[0038] Step S201: In the business processing flow, if business data that meets the interception conditions is detected, a corresponding audit task is constructed based on the business data.

[0039] In this embodiment, the task processing method runs on an electronic device (e.g., Figure 1The server / terminal device shown can acquire business data via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wide wireless band) connections, and other currently known or future-developed wireless connection methods. The executing entity of this application is specifically a task processing system, also known as a document review system, which can be simply referred to as the system. The aforementioned business processing flow may refer to the system's insurance application or quotation business process. The aforementioned business data may include insurance applications, quotations, and other data that need to be reviewed. When the system intercepts business data that needs to be reviewed, it will trigger a task generation mechanism. For example, if a customer submits an insurance application, after preliminary rule verification, the system determines that the insurance application needs to enter the document review stage, and at this time, a review task matching the insurance application will be generated.

[0040] This application can be applied to task processing scenarios in the fintech and healthcare sectors. For example, in an insurance application scenario within the financial insurance sector, the aforementioned review task could be a review task for large-sum insurance policies. The task description includes: if a customer applies for insurance coverage exceeding a certain limit (e.g., 5 million yuan), the system will automatically intercept and generate a review task. Reviewers must comprehensively examine the customer's financial situation, including income statements, asset lists, and tax records, to determine the customer's ability to pay high premiums. They must also investigate the customer's motivation for applying for insurance, identifying any moral hazard, such as insurance fraud through high-sum policies. Furthermore, the impact of this large-sum policy on the company's overall risk exposure needs to be assessed to determine whether to approve underwriting and whether additional risk control measures, such as reinsurance arrangements, are necessary.

[0041] Alternatively, in the context of digital healthcare pricing, the aforementioned review task could be a rare disease treatment insurance pricing review task. The task description includes: when a customer applies for a treatment insurance quote for a patient with a rare disease, the system intercepts and generates a review task. Reviewers need to collect detailed information about the rare disease, including its incidence rate, treatment methods, and treatment costs. Because treatments for rare diseases can be specialized and expensive, it's necessary to communicate with professional medical institutions or experts to understand the latest treatment advancements and costs. Based on this information, combined with the insurance company's pricing model and risk tolerance, a reasonable insurance pricing plan is developed for the patient, clearly defining insurance liability and the scope of compensation.

[0042] Step S202: Record the task information of the audit task into a preset designated task table, and filter out the target tasks to be assigned from the designated task table.

[0043] In this embodiment, after an audit task is generated, the system automatically collects all relevant information (task information) for this audit task and records it in a dedicated task table (i.e., the aforementioned designated task table, or Table A). This task information includes, but is not limited to, the task's unique identifier (AID) (used to accurately identify the task in the system), task name (e.g., "Insurance Application Audit Task - Customer Name - Order Number"), creation time (accurate to the second, recording the moment the task was generated), affiliated organization (clearly indicating which secondary or tertiary organization generated the task, such as "East China Branch - Shanghai Sub-branch"), business type (indicating whether it is an insurance policy, endorsement, or vehicle inspection business), auditor (initially may be empty, pending subsequent allocation), source (indicating which business link or system interface the task came from), and status (initially set to "pending allocation," etc.). Furthermore, subsequent steps will further filter out target tasks to be allocated from the aforementioned designated task table, i.e., tasks with a status of "pending allocation."

[0044] Furthermore, the system will query another table (Table B) specifically storing working time settings based on the organization information of the aforementioned review tasks. Table B records the review time range for each organization on different types of dates (weekdays, Saturdays / Sundays, and public holidays). For example, the review time for the "Shanghai Branch" is 9:00-19:00 on weekdays and 9:00-18:00 on weekends and public holidays. The system will compare the time of insurance application or quotation with the corresponding review time range for that organization. If the time of insurance application or quotation falls within the review time range set by that organization, the system will insert the relevant information for this task into the task table (Table C) that meets the financial services review time requirements. Table C contains information such as AID (associated with Table A), organization, business type, review time (recording the moment that meets the review time range), review speed (initially empty, to be calculated during subsequent review operations), and reviewer (initially may be empty). This process ensures that all tasks requiring review are accurately recorded, and only tasks that meet specific review time requirements will enter the subsequent monitoring process. By recording task information in detail in Table A, a comprehensive and accurate data source is provided for the entire monitoring system. The judgment of review time and the insertion of eligible task information into Table C ensure that the monitoring system can focus on tasks generated within the appropriate time frame, avoiding the processing of invalid tasks or tasks outside the monitoring time range, thus improving the efficiency and targeting of job monitoring.

[0045] Step S203: Obtain multi-dimensional information of multiple preset candidate reviewers, and obtain task data of the target task.

[0046] In this embodiment, data on multiple candidate reviewers across various dimensions can be collected from human resource management systems, performance evaluation systems, and other sources. For example, data on candidate reviewers' professional field matching, workload, historical performance indicators, and urgency suitability can be collected, processed, and cleaned to ensure the accuracy and consistency of the multi-dimensional information. Furthermore, for the target task, task data such as task type, difficulty, and urgency can be extracted from the task management system. For example, the task type could be insurance application, approval, or vehicle inspection; the difficulty can be assessed based on the task's complexity and the amount involved; and the urgency can be determined based on business rules or customer requirements.

[0047] Step S204: Generate the personnel weight of each of the candidate reviewers based on the multi-dimensional information.

[0048] In this embodiment, the specific implementation process of generating the personnel weights of each candidate reviewer based on the multi-dimensional information will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0049] Step S205: Based on a preset score analysis strategy, perform score generation processing on the multi-dimensional information, the task data, and the personnel weights to obtain the comprehensive score of each candidate reviewer corresponding to the target task.

[0050] In this embodiment, the above-mentioned process of generating scores for the multi-dimensional information, the task data, and the personnel weights based on a preset score analysis strategy to obtain the comprehensive score of each candidate reviewer corresponding to the target task will be described in more detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0051] Step S206: Select the target reviewer with the highest score from all the comprehensive scores, and assign the target task to the target reviewer.

[0052] In this embodiment, the target reviewer with the highest score can be selected by comparing the comprehensive scores of each candidate reviewer for the target task, and then the target task can be assigned to the target reviewer to ensure the rationality, accuracy and efficiency of the target task assignment.

[0053] This application firstly, in the business processing flow, if business data that meets the interception conditions is detected, a corresponding review task is constructed based on the business data; then, the task information of the review task is recorded in a preset designated task table, and target tasks to be assigned are filtered from the designated task table; next, multi-dimensional information of multiple preset candidate reviewers is obtained, as well as task data of the target task; subsequently, personnel weights of each candidate reviewer are generated based on the multi-dimensional information; further, based on a preset score analysis strategy, scores are generated from the multi-dimensional information, the task data, and the personnel weights to obtain a comprehensive score for each candidate reviewer corresponding to the target task; finally, the target reviewer with the highest score is selected from all the comprehensive scores, and the target task is assigned to the target reviewer. Based on the above automated processing flow, in the business processing flow of this application, if business data that meets the interception conditions is detected, an audit task will be constructed based on the business data. Then, the task information of the audit task will be recorded in a designated task table, and the target tasks to be assigned will be selected from the designated task table. After that, personnel weights will be generated based on the multi-dimensional information of multiple candidate auditors. Then, based on the use of a score analysis strategy, scores will be generated by processing the multi-dimensional information, the task data of the acquired target tasks, and the personnel weights to obtain the comprehensive score of each candidate auditor for the target task. Finally, the target auditor with the highest score will be selected from all the comprehensive scores, and the target task will be assigned to the target auditor. This can effectively improve the rationality, accuracy, and intelligence of task allocation.

[0054] In some alternative implementations, step S205 includes the following steps:

[0055] Invoke the pre-built score prediction model.

[0056] In this embodiment, the model construction process of the above-mentioned score prediction model includes: I. Feature Engineering. 1) Feature Collection and Organization. First, relevant features of reviewers and tasks are collected from multiple data sources. For reviewers, information such as professional domain codes, workload values, historical performance indicators, and urgency adaptation values ​​are obtained from the human resource management system; for tasks, features such as task type, difficulty, and urgency are obtained from the task management system; then, the collected features are organized and cleaned to remove duplicate, missing, and abnormal data. For example, for missing professional domain codes, they can be supplemented based on the reviewer's work experience and training records; for abnormal workload values, such as negative numbers or values ​​exceeding the reasonable range, they are corrected or deleted; 2) Feature Coding and Standardization. Categorical features are coded. For example, task types are coded into different values, such as insurance application task coded as 1, approval task coded as 2, and vehicle inspection task coded as 3. One-hot encoding or label encoding methods can be used, and an appropriate encoding method is selected according to the characteristics of the features and the requirements of the model. And, numerical features are standardized. Because the value ranges of different features may vary significantly—for example, workload might be the number of specific tasks, while historical performance indicators might be scores from 0 to 100—standardization is necessary to bring all features to a uniform scale. Common standardization methods include Z-score standardization and Min-Max standardization. 3) Feature selection and combination. Analyze the correlation between each feature and the task allocation results (reviewers). Correlation analysis, chi-square tests, and other methods can be used to screen features that are strongly correlated with the task allocation results. For example, if the domain-specific coding is found to have a low correlation with the task allocation results, it can be considered for removal from the feature set. Furthermore, try combining features to create more meaningful features. For example, combine task difficulty and urgency into a new feature to represent the overall complexity of the task. Feature combination can improve the model's performance and generalization ability.

[0057] II. Model Training. 1) Data Partitioning. Divide the collected historical task assignment data into training, validation, and test sets. Typically, the training set is used for model training, the validation set for adjusting model parameters, and the test set for evaluating the final model performance. A random partitioning method can be used, such as dividing the training, validation, and test sets in a 70%, 15%, and 15% ratio. Ensure the data partitioning is reasonable, meaning the data distribution of the training, validation, and test sets is similar to avoid inaccurate model performance evaluation due to imbalanced data distribution. 2) Model Parameter Tuning. Train the random forest model using the training set. During training, evaluate the model's performance using cross-validation. For example, use K-fold cross-validation, dividing the training set into K subsets, using K-1 subsets for training each time, and validating the remaining subset, repeating K times, and calculating the average performance index. Adjust the model parameters based on the cross-validation results. The main parameters of the random forest model include the number of decision trees (n_estimator s), maximum depth (max_depth), and minimum sample split (min_samples_split). By adjusting these parameters, the optimal model configuration is found to improve the model's accuracy and generalization ability. 3) Model performance evaluation. The model with adjusted parameters is evaluated using a validation set. Precision, recall, F1 score, and other metrics are calculated to analyze the model's performance across different categories. If the model performs poorly in certain categories, the reasons can be further analyzed, such as data imbalance or inappropriate feature selection, and corresponding measures can be taken to improve it. If the model performance meets the requirements, the model is finally evaluated using a test set. The test set data has never been used during model training and parameter tuning, and can more realistically reflect the model's performance. If the model still performs well on the test set, it indicates that the model has good generalization ability and can be used in practical applications. The trained random forest model is then used as the final score prediction model.

[0058] Based on the scoring prediction model, the multi-dimensional information and the task data are predicted and processed to obtain the suitability score of each candidate reviewer for the target task.

[0059] In this embodiment, the specific implementation process of predicting and processing the multi-dimensional information and the task data based on the score prediction model to obtain the suitability score of each candidate reviewer for the target task will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0060] Call the preset comprehensive score calculation formula and obtain the preset dynamic weight.

[0061] In this embodiment, the formula for calculating the comprehensive score specifically includes: Comprehensive Score = Dynamic Weight × Personnel Weight + (1 - Dynamic Weight) × Suitability Score. The value of the dynamic weight is not specifically limited and can be set according to actual business needs (the importance of personnel weight and the importance of suitability score), for example, it can be set to 0.5.

[0062] The dynamic weight, the personnel weight, and the suitability score are calculated based on the comprehensive score calculation formula to obtain the corresponding first calculation result.

[0063] In this embodiment, the dynamic weights, personnel weights, and suitability scores can be substituted into the corresponding positions in the comprehensive score calculation formula to obtain the corresponding first calculation result. For example, for reviewer A and task 1, the comprehensive score is 0.5 × 0.755 + (1 - 0.5 × 0.85) = 0.8025.

[0064] Based on the first calculation result, a comprehensive score is generated for each of the candidate reviewers corresponding to the target task.

[0065] In this embodiment, the generated first calculation result can be used as the comprehensive score of each of the above-mentioned candidate reviewers for the target task.

[0066] This application utilizes a pre-built score prediction model; then, based on the score prediction model, it performs prediction processing on the multi-dimensional information and task data to obtain the suitability score of each candidate reviewer for the target task; subsequently, it calls a preset comprehensive score calculation formula and obtains preset dynamic weights; subsequently, it calculates the dynamic weights, personnel weights, and suitability scores based on the comprehensive score calculation formula to obtain the corresponding first calculation result; finally, it generates the comprehensive score of each candidate reviewer for the target task based on the first calculation result. Based on the above processing flow, this application, by using a score prediction model to predict multi-dimensional information and task data to obtain the suitability score of each candidate reviewer for the target task, and then using the comprehensive score calculation formula to calculate the dynamic weights, personnel weights, and suitability scores, can efficiently and accurately calculate the comprehensive score of each candidate reviewer for the target task, improving the calculation efficiency of the comprehensive score of each candidate reviewer and ensuring the accuracy of the obtained comprehensive score data.

[0067] In some optional implementations of this embodiment, the step of performing prediction processing on the multi-dimensional information and the task data based on the score prediction model to obtain the suitability score of each candidate reviewer for the target task includes the following steps:

[0068] Feature extraction is performed on the multi-dimensional information and the task data to obtain the corresponding initial features.

[0069] In this embodiment, feature extraction is performed on the above-mentioned multi-dimensional information to obtain personnel characteristics such as task type, difficulty, and urgency. Feature extraction is also performed on the above-mentioned task data to obtain task characteristics such as professional domain coding, workload value, and historical performance indicators. The obtained personnel characteristics and task characteristics are then integrated to obtain the corresponding initial features.

[0070] The initial features are preprocessed to obtain the corresponding target features.

[0071] In this embodiment, the preprocessing includes operations such as encoding and standardization to ensure that the features are consistent with the features used during model training.

[0072] The target features are predicted based on the score prediction model to obtain the corresponding prediction results.

[0073] In this embodiment, the preprocessed target features are input into the trained score prediction model. The model predicts the suitability of each candidate reviewer for the target task to be assigned based on the input features, and outputs the suitability score for each candidate reviewer. For example, for task 1, the model predicts that reviewer A has a suitability score of 0.85, reviewer B has a suitability score of 0.72, and reviewer C has a suitability score of 0.68.

[0074] Based on the prediction results, a suitability score is generated for each of the candidate reviewers corresponding to the target task.

[0075] In this embodiment, the generated prediction results can be used as the suitability scores of each of the aforementioned candidate reviewers for the target task.

[0076] This application extracts features from the multi-dimensional information and task data to obtain corresponding initial features; then preprocesses the initial features to obtain corresponding target features; subsequently, it uses the score prediction model to predict the target features to obtain corresponding prediction results; and finally, it generates suitability scores for each candidate reviewer corresponding to the target task based on the prediction results. Based on the above processing flow, this application obtains corresponding initial features by extracting features from multi-dimensional information and task data, preprocesses the initial features to obtain target features, and then uses the score prediction model to predict the target features. This enables efficient and accurate generation of suitability scores for each candidate reviewer corresponding to the target task, improving the efficiency of suitability score generation and ensuring the accuracy of the obtained suitability scores.

[0077] In some optional implementations, the multi-dimensional information includes at least professional domain matching degree, workload value, historical performance indicators, and urgency adaptation value; step S206 includes the following steps:

[0078] The multi-dimensional information is standardized to obtain the corresponding target multi-dimensional information.

[0079] In this embodiment, since the information of each dimension may have different dimensions and value ranges, it is necessary to standardize the above-mentioned multi-dimensional information. For example, for the professional field matching score, if its value range is 0-1, while the workload value may be the specific number of tasks, the workload value needs to be normalized so that it is also within the range of 0-1.

[0080] Obtain the information weights corresponding to the multi-dimensional information of the target.

[0081] In this embodiment, the specific implementation process of obtaining the information weights corresponding to the multi-dimensional information of the target will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0082] Call the preset personnel weight calculation formula.

[0083] In this embodiment, the specific formula for calculating the personnel weight can be a weighted summation formula, that is, calculating the comprehensive weight (i.e., personnel weight) of the candidate reviewers based on the information weight assigned to each dimension. The weighted summation formula uses a weighted average method to multiply the score of each dimension's information by its corresponding information weight, and then sums all the results to obtain the personnel weight of the corresponding candidate reviewers.

[0084] Based on the personnel weight calculation formula, the target multi-dimensional information and the information weight are calculated and processed to obtain the corresponding second calculation result.

[0085] In this embodiment, the calculation is performed by substituting the aforementioned multi-dimensional information and information weights of the target into the corresponding positions in the aforementioned personnel weight calculation formula. For example, if reviewer A scores 0.8 in professional domain matching, 0.6 in workload, 0.9 in historical performance, and 0.7 in urgency suitability, with a current professional domain matching weight of 0.3, a workload weight of 0.2, a historical performance weight of 0.25, and an urgency weight of 0.25, then their overall personnel weight is 0.3×0.8+0.2×0.6+0.25×0.9+0.25×0.7=0.755.

[0086] Based on the second calculation result, the personnel weight of each of the candidate reviewers is generated.

[0087] In this embodiment, the calculated second result can be used as the personnel weight of each of the above-mentioned candidate reviewers.

[0088] This application standardizes the multi-dimensional information to obtain corresponding target multi-dimensional information; then, it obtains the information weights corresponding to the target multi-dimensional information; subsequently, it calls a preset personnel weight calculation formula; and calculates the target multi-dimensional information and the information weights based on the personnel weight calculation formula to obtain a corresponding second calculation result; subsequently, it generates the personnel weights of each candidate reviewer based on the second calculation result. Based on the above processing flow, this application obtains target multi-dimensional information by standardizing the multi-dimensional information and obtaining the information weights corresponding to the target multi-dimensional information. Then, it calculates the target multi-dimensional information and the information weights based on the personnel weight calculation formula, thereby achieving efficient and accurate generation of personnel weights for each candidate reviewer, improving the generation efficiency of candidate reviewer personnel weights, and ensuring the accuracy of the obtained personnel weight data.

[0089] In some optional implementations, obtaining the information weights corresponding to the multi-dimensional information of the target includes the following steps:

[0090] Real-time information on factors affecting weight adjustments is collected based on pre-set data monitoring tools.

[0091] In this embodiment, a real-time data monitoring tool is pre-established to monitor various real-time situations affecting weight adjustments. For example, the task management system obtains information such as the number of tasks to be assigned and the distribution of urgency levels in real time; the human resources management system obtains data such as the workload and leave status of reviewers in real time. Monitoring indicators and thresholds are set. For example, when the proportion of urgent tasks among the tasks to be assigned exceeds 30%, the weight adjustment mechanism for the urgency dimension is triggered; when the average workload of reviewers exceeds 80%, the weight adjustment process for the workload dimension is initiated.

[0092] Obtain information on business changes.

[0093] In this embodiment, information on business changes is collected and analyzed regularly. For example, the impact of market dynamics, policy and regulatory changes, and adjustments to company business strategies on task allocation is monitored. If the company launches a new insurance product, it may lead to an increase in related review tasks, requiring a reassessment of the weighting of professional domain matching and workload dimensions. Furthermore, a business change feedback mechanism is established. Frontline reviewers and business department personnel are encouraged to promptly report business changes to ensure that weight adjustments respond promptly to business needs.

[0094] Obtain the initial information weights corresponding to the multi-dimensional information.

[0095] In this embodiment, an initial information weight is assigned to each dimension in advance based on the experience of business experts and the actual business situation. For example, the initial information weight corresponding to the professional field matching degree is set to 0.3, the initial information weight corresponding to the workload is set to 0.2, the initial information weight corresponding to the historical performance is set to 0.25, and the initial information weight corresponding to the urgency level is set to 0.25.

[0096] Based on the real-time situation information and the business change information, the initial information weights are adjusted to obtain the corresponding information weights.

[0097] In this embodiment, the initial information weights of each dimension are dynamically adjusted based on real-time situation information and business change information to obtain the final information weights. For example, during peak business periods, the weight of the workload dimension can be appropriately increased to ensure a balanced allocation of tasks; when there are a large number of urgent tasks, the weight of the urgency dimension can be increased accordingly.

[0098] Specifically, based on real-time monitoring and business change analysis, clear weight adjustment rules are formulated. For example, during peak business periods, the weight of the workload dimension is increased by 20%; when the proportion of urgent tasks exceeds a threshold, the weight of the urgency dimension is increased by 15%. Then, the magnitude and range of the weight adjustment are determined. To avoid excessively frequent or large adjustments, the magnitude of each adjustment is limited, for example, each adjustment cannot exceed 30% of the initial weight. Simultaneously, the range after the weight adjustment is specified to ensure that the weights of each dimension remain within a reasonable range. Then, when the weight adjustment conditions are met, the weight adjustment operation is executed automatically or manually according to the established rules. For example, if the system automatically detects that the proportion of urgent tasks exceeds a threshold, the system automatically adjusts the weight of the urgency dimension from 0.25 to 0.2875 (an increase of 15%). In addition, information such as the time, reason, and weight values ​​before and after each weight adjustment is recorded. These records will help in subsequent evaluation and optimization of the weight adjustment mechanism.

[0099] This application collects real-time information affecting weight adjustment using a preset data monitoring tool; then acquires business change information; subsequently, it obtains initial information weights corresponding to the multi-dimensional information; and finally, based on the real-time information and the business change information, it adjusts the initial information weights to obtain the corresponding information weights. Based on this processing flow, this application, by using a data monitoring tool to collect real-time information affecting weight adjustment, then acquiring business change information and initial information weights corresponding to multi-dimensional information, and then adjusting the initial information weights based on the real-time information and business change information, can efficiently and accurately construct the information weights of the target multi-dimensional information, improving the intelligence and accuracy of the generated target multi-dimensional information information weights.

[0100] In some optional implementations of this embodiment, after step S206, the electronic device may further perform the following steps:

[0101] After completing the processing of the target task, task processing data corresponding to the target task is collected.

[0102] In this embodiment, the aforementioned task processing data refers to the relevant data that needs to be collected corresponding to the relevant task indicators.

[0103] Obtain the preset indicator calculation strategy.

[0104] In this embodiment, the above-mentioned indicator calculation strategy includes the calculation strategy for indicators corresponding to review operation volume, application / approval volume, return rate, timely completion rate, and review timeliness. Specifically, the indicator calculation strategy includes: Review operation volume: For each reviewer group, the number of tasks in that group is counted, which is the review operation volume of that reviewer. For example, if a reviewer group has 10 task records, then the review operation volume of that reviewer is 10 times. Application / approval volume: Calculated based on business type and task information. For insurance application and approval business, the application / approval volume is obtained by deduplicating "insurance application / approval application + business type". For example, if there are 5 insurance application task records and 3 approval task records, but 2 of the insurance application tasks are for the same application, after deduplication, the application / approval volume is 5 (number of deduplicated insurance applications) + 3 (number of approvals) = 8. Return rate: The number of tasks issued is counted according to the task processing type, and then the number of tasks issued is divided by the review operation volume to obtain the return rate. For example, if an auditor performs 20 review operations, including 5 issuances, then the return rate = 5 / 20 = 25%. Timely Completion Rate: The system determines whether each task is completed within the specified time based on the time requirements set by the management platform. It counts the number of tasks completed on time (timely completed orders), and then divides this number by the total number of submitted orders to obtain the timely completion rate. For example, if the total number of submitted orders is 30 and the number of timely completed orders is 25, then the timely completion rate = 25 / 30 ≈ 83.33%. Review Timeliness: Based on the working hours set by the management platform, the review timeliness of non-overnight orders is calculated. The formula is: Total time spent by all tasks leaving the platform during this period / Total number of orders during this period. For example, if 10 non-overnight orders leave the platform between 9:00 AM and 7:00 PM on a weekday, and the total time spent by these tasks leaving the platform is 50 hours, then the review timeliness = 50 / 10 = 5 hours / order.

[0105] The task processing data is processed based on the aforementioned indicator calculation strategy to obtain the corresponding indicator data.

[0106] In this embodiment, based on the above indicator calculation strategy, the collected task processing data related to the indicator calculation of the target task are calculated and processed, and the generated calculation results are used as the corresponding indicator data.

[0107] Based on the aforementioned indicator data, corresponding statistical reports are generated.

[0108] In this embodiment, the aforementioned indicator data can be filled into a preset statistical report template to generate a corresponding data statistical report. The content of the statistical report template is not specifically limited and can be set according to actual data statistical needs.

[0109] The data statistical reports are stored and displayed.

[0110] In this embodiment, the aforementioned data statistical reports can be stored using any of the following methods: local database, local disk, cloud server, and blockchain. Furthermore, the data statistical reports can be displayed and processed through a system page, providing administrators with comprehensive and intuitive statistical reports for review.

[0111] After completing the processing of the target task, this application collects task processing data corresponding to the target task; then obtains a preset indicator calculation strategy; and calculates and processes the task processing data based on the indicator calculation strategy to obtain corresponding indicator data; subsequently, it generates corresponding data statistical reports based on the indicator data; and then stores and displays the data statistical reports. Based on the above processing flow, after completing the processing of the target task, this application collects task processing data corresponding to the target task, and then calculates and processes the task processing data based on the indicator calculation strategy to obtain indicator data, thereby improving the calculation efficiency and accuracy of indicator data. Furthermore, it intelligently generates data statistical reports based on the indicator data, and stores and displays the data statistical reports, improving the generation efficiency and data security of data statistical reports, and providing relevant personnel with comprehensive and intuitive statistical reports, which is beneficial to improving the work efficiency and user experience of relevant personnel.

[0112] In some optional implementations of this embodiment, after step S206, the electronic device may further perform the following steps:

[0113] Determine whether the task review result corresponding to the target task has been received from the target reviewer.

[0114] In this embodiment, after a target task is assigned to a target reviewer, the reviewer field in the designated task table is updated to the corresponding reviewer information, and the task status is updated to "Under Review". Furthermore, after logging into the review page, the target reviewer will see a list of tasks assigned to them for review (including the target task). When the target reviewer performs a review operation on the target task, such as clicking the "Approve" button to indicate agreement to pass the review, clicking the "Distribute" button to indicate that the target task needs to be returned to relevant personnel for modification or supplementary information, or clicking the "Modify Vehicle Inspection Conclusion" button to adjust the conclusion of the vehicle inspection, the review operation is triggered, and a task review result corresponding to the review operation is generated.

[0115] If so, retrieve the initial review status of the target task from the specified task table.

[0116] In this embodiment, the initial review status of the aforementioned target task is "under review".

[0117] The initial review status of the target task in the specified task table is updated based on the task review results.

[0118] In this embodiment, the system updates the review status and review time of the target task in the designated task table based on the AID of the target task operated by the reviewer. For example, if the reviewer clicks the "Approved" button, the task status of the target task in the designated task table is updated to "Approved," and the review time is recorded as the current time when the reviewer clicked the button. If the reviewer clicks the "Issue" button, the task status in the designated task table is updated to "Issue," and the review time is also recorded as the current time. Simultaneously, the system also updates the review status and review time of the target task in table C based on the AID of the target task operated by the reviewer.

[0119] This system records the progress of task reviews in real time. A task allocation mechanism associates tasks with reviewers, ensuring each task has a clearly defined responsible party. All actions performed by reviewers on the review page are promptly reflected in the system, updating review status and time information in Tables A and C, providing accurate data for subsequent statistical calculations. This allows administrators to monitor the review status of each task at any time and understand the dynamic changes throughout the entire review process.

[0120] This application determines whether it has received a task review result corresponding to the target task from the target reviewer; if so, it retrieves the initial review status of the target task from the designated task table; subsequently, it updates the initial review status of the target task in the designated task table based on the task review result. Based on this processing flow, when this application receives a task review result corresponding to the target task from the target reviewer, it first retrieves the initial review status of the target task from the designated task table, and then updates the initial review status of the target task in the designated task table based on the use of the task review result. This provides accurate data for subsequent statistical processing. In this way, managers can understand the review status of each task at any time and grasp the dynamic changes of the entire review process.

[0121] In some optional implementations, the system page offers various filtering dimensions for administrators to choose from, such as reviewer, organization, and business type. Administrators can select one or more dimensions for combined filtering based on their needs. For example, if an administrator wants to understand the insurance policy business reviewed by a specific reviewer within a certain period, they can select the specific reviewer as the reviewer dimension and "insurance policy" as the business type dimension, while also setting other filtering conditions such as time range. Furthermore, the system provides data query and grouping functions: the system queries data from table C based on the filtering conditions set by the administrator. If the reviewer dimension is selected for filtering, the system will perform a group by operation on the query results according to the reviewer field, grouping the task data of the same reviewer together. This yields the task data set corresponding to each reviewer.

[0122] In some alternative implementations, the user information obtained is subject to user consent and complies with relevant laws and policies.

[0123] Furthermore, any software tools or components not belonging to our company that appear in the embodiments of this application are merely illustrative examples and do not represent actual use.

[0124] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0125] It should be emphasized that, to further ensure the privacy and security of the aforementioned objectives, these objectives can also be stored in a node of a blockchain.

[0126] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0127] The embodiments of this 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 that knowledge to obtain optimal results.

[0128] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0129] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0130] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0131] Further reference Figure 3 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of a task processing device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0132] like Figure 3 As shown, the task processing device 300 described in this embodiment includes: a detection module 301, a first processing module 302, a first acquisition module 303, a first generation module 304, a second processing module 305, and an allocation module 306. Wherein:

[0133] The detection module 301 is used to construct a corresponding audit task based on the business data if business data that meets the interception conditions is detected in the business processing flow.

[0134] The first processing module 302 is used to record the task information of the review task into a preset designated task table, and to filter out the target tasks to be assigned from the designated task table.

[0135] The first acquisition module 303 is used to acquire multi-dimensional information of multiple preset candidate reviewers, and to acquire task data of the target task;

[0136] The first generation module 304 is used to generate the personnel weight of each of the candidate reviewers based on the multi-dimensional information;

[0137] The second processing module 305 is used to perform score generation processing on the multi-dimensional information, the task data and the personnel weight based on a preset score analysis strategy, so as to obtain the comprehensive score of each candidate reviewer corresponding to the target task.

[0138] The allocation module 306 is used to filter out the target reviewer with the highest score from all the comprehensive scores and assign the target task to the target reviewer.

[0139] In some optional implementations of this embodiment, the second processing module 305 includes:

[0140] The first calling submodule is used to call the pre-built score prediction model;

[0141] The prediction submodule is used to perform prediction processing on the multi-dimensional information and the task data based on the score prediction model to obtain the suitability score of each candidate reviewer for the target task.

[0142] The second calling submodule is used to call the preset comprehensive score calculation formula and obtain the preset dynamic weight;

[0143] The first calculation submodule is used to calculate and process the dynamic weight, the personnel weight and the suitability score based on the comprehensive score calculation formula to obtain the corresponding first calculation result;

[0144] The first generation submodule is used to generate a comprehensive score for each of the candidate reviewers corresponding to the target task based on the first calculation result.

[0145] In some optional implementations of this embodiment, the prediction submodule includes:

[0146] An extraction unit is used to extract features from the multi-dimensional information and the task data to obtain corresponding initial features;

[0147] The preprocessing unit is used to preprocess the initial features to obtain the corresponding target features;

[0148] The prediction unit is used to perform prediction processing on the target features based on the score prediction model to obtain the corresponding prediction results;

[0149] The generation unit is used to generate a suitability score for each of the candidate reviewers corresponding to the target task based on the prediction results.

[0150] In some optional implementations of this embodiment, the multi-dimensional information includes at least professional field matching degree, workload value, historical performance indicators, and urgency adaptation value; the first generation module 304 includes:

[0151] The processing submodule is used to standardize the multi-dimensional information to obtain the corresponding target multi-dimensional information.

[0152] The acquisition submodule is used to acquire the information weights corresponding to the multi-dimensional information of the target.

[0153] The third submodule is used to call the preset personnel weight calculation formula;

[0154] The second calculation submodule is used to calculate and process the target multi-dimensional information and the information weight based on the personnel weight calculation formula to obtain the corresponding second calculation result;

[0155] The second generation submodule is used to generate the personnel weight of each of the candidate reviewers based on the second calculation result.

[0156] In some optional implementations of this embodiment, the acquisition submodule includes:

[0157] The data acquisition unit is used to collect real-time information on factors affecting weight adjustment based on preset data monitoring tools.

[0158] The first acquisition unit is used to acquire business change information;

[0159] The second acquisition unit is used to acquire the initial information weights corresponding to the multi-dimensional information;

[0160] The adjustment unit is used to adjust the initial information weights based on the real-time situation information and the business change information to obtain the corresponding information weights.

[0161] In some optional implementations of this embodiment, the task processing device further includes:

[0162] The acquisition module is used to acquire task processing data corresponding to the target task after completing the processing of the target task;

[0163] The second acquisition module is used to acquire the preset indicator calculation strategy;

[0164] The calculation module is used to perform calculations on the task processing data based on the indicator calculation strategy to obtain the corresponding indicator data.

[0165] The second generation module is used to generate corresponding data statistical reports based on the indicator data;

[0166] The third processing module is used to store and display the data statistical reports. In some optional implementations of this embodiment, the task processing device further includes:

[0167] The judgment module is used to determine whether the task review result corresponding to the target task has been received from the target reviewer.

[0168] The third acquisition module is used to, if so, acquire the initial review status of the target task from the specified task table;

[0169] The update module is used to update the initial review status of the target task in the specified task table based on the task review result.

[0170] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0171] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0172] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0173] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for task processing methods. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0174] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, for example, to execute computer-readable instructions of the task processing method.

[0175] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0176] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the task processing method described above.

[0177] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0178] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A task processing method, characterized in that, Includes the following steps: In the business processing flow, if business data that meets the interception conditions is detected, a corresponding audit task is constructed based on the business data; The task information of the audit task is recorded in a preset designated task table, and the target tasks to be assigned are filtered out from the designated task table. Obtain multi-dimensional information of multiple pre-set candidate reviewers, and obtain task data for the target task; Based on the multi-dimensional information, a personnel weight is generated for each of the candidate reviewers; Based on a preset score analysis strategy, the multi-dimensional information, the task data, and the personnel weights are processed to generate scores, thereby obtaining the comprehensive score of each candidate reviewer corresponding to the target task. Select the target reviewer with the highest score from all the comprehensive scores, and assign the target task to the target reviewer.

2. The task processing method according to claim 1, characterized in that, The step of generating scores for each candidate reviewer corresponding to the target task by processing the multi-dimensional information, the task data, and the personnel weights based on a preset score analysis strategy, specifically includes: Invoke the pre-built score prediction model; Based on the score prediction model, the multi-dimensional information and the task data are predicted and processed to obtain the suitability score of each candidate reviewer for the target task. Call the preset comprehensive score calculation formula and obtain the preset dynamic weight; Based on the comprehensive score calculation formula, the dynamic weight, the personnel weight, and the suitability score are calculated and processed to obtain the corresponding first calculation result; Based on the first calculation result, a comprehensive score is generated for each of the candidate reviewers corresponding to the target task.

3. The task processing method according to claim 2, characterized in that, The step of performing prediction processing on the multi-dimensional information and the task data based on the score prediction model to obtain the suitability score of each candidate reviewer for the target task specifically includes: Feature extraction is performed on the multi-dimensional information and the task data to obtain the corresponding initial features; The initial features are preprocessed to obtain the corresponding target features; Based on the score prediction model, the target features are predicted to obtain the corresponding prediction results; Based on the prediction results, a suitability score is generated for each of the candidate reviewers corresponding to the target task.

4. The task processing method according to claim 1, characterized in that, The multi-dimensional information includes at least professional field matching degree, workload value, historical performance indicators, and urgency adaptation value; the step of generating the personnel weight of each candidate reviewer based on the multi-dimensional information specifically includes: The multi-dimensional information is standardized to obtain the corresponding target multi-dimensional information; Obtain the information weights corresponding to the multi-dimensional information of the target; Call the preset personnel weight calculation formula; Based on the personnel weight calculation formula, the target multi-dimensional information and the information weight are calculated and processed to obtain the corresponding second calculation result; Based on the second calculation result, the personnel weight of each of the candidate reviewers is generated.

5. The task processing method according to claim 4, characterized in that, The step of obtaining the information weights corresponding to the multi-dimensional information of the target specifically includes: Real-time information on factors affecting weight adjustments is collected based on pre-set data monitoring tools; Obtain information on business changes; Obtain the initial information weights corresponding to the multi-dimensional information; Based on the real-time situation information and the business change information, the initial information weights are adjusted to obtain the corresponding information weights.

6. The task processing method according to claim 1, characterized in that, After the step of selecting the target reviewer with the highest score from all the comprehensive scores and assigning the target task to the target reviewer, the method further includes: After completing the processing of the target task, collect the task processing data corresponding to the target task; Obtain the preset indicator calculation strategy; The task processing data is calculated and processed based on the aforementioned indicator calculation strategy to obtain the corresponding indicator data. Generate corresponding data statistics reports based on the aforementioned indicator data; The data statistical reports are stored and displayed.

7. The task processing method according to claim 1, characterized in that, After the step of selecting the target reviewer with the highest score from all the comprehensive scores and assigning the target task to the target reviewer, the method further includes: Determine whether the task review result corresponding to the target task has been received from the target reviewer; If so, retrieve the initial review status of the target task from the specified task table; The initial review status of the target task in the specified task table is updated based on the task review results.

8. A task processing device, characterized in that, include: The detection module is used to construct a corresponding audit task based on business data that meets the interception conditions during the business processing flow. The first processing module is used to record the task information of the review task into a preset designated task table, and to filter out the target tasks to be assigned from the designated task table. The first acquisition module is used to acquire multi-dimensional information of multiple preset candidate reviewers, as well as to acquire task data of the target task; The first generation module is used to generate the personnel weight of each of the candidate reviewers based on the multi-dimensional information; The second processing module is used to perform score generation processing on the multi-dimensional information, the task data and the personnel weight based on a preset score analysis strategy, so as to obtain the comprehensive score of each candidate reviewer corresponding to the target task; The allocation module is used to filter out the target reviewer with the highest score from all the comprehensive scores and assign the target task to the target reviewer.

9. A computer device, characterized in that, The method includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the task processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the task processing method as described in any one of claims 1 to 7.

Images