Intelligent order dispatching method and device and storage medium

Abstract

The invention discloses an intelligent order sending method, and relates to the technical field of multimedia application, and the method comprises the steps: determining a corresponding examination and approval task set according to the examination and approval authority of a current examination and approval person; sorting the approval tasks according to the priorities of the approval tasks in the approval task set, and distributing the approval tasks to the approval personnel in sequence; wherein the approval task is distributed when the working state of the approver is an idle state. According to the intelligent order sending method, the intelligent order sending device and the storage medium, through setting of the priority of the approval task and the approval authority of the approval personnel, the approval personnel meeting the approval requirements can be quickly positioned based on the current approval task priority; the order sending efficiency of the approval task is improved, and the technical effect of improving the approval efficiency is achieved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence application technology, and in particular to an intelligent dispatching method, device and storage medium. Background Art

[0002] For financial leasing business facing end consumers, business risk control approval and placement review is a very critical and high-frequency operation. The traditional method of actively claiming tasks and manually assisting in task allocation is highly dependent on manual operations, which requires high initiative and proficiency of the reviewers. Reviewers have the situation of independently selecting orders for review, and the response time is insufficient, which cannot support the rapidly growing business volume, and cannot flexibly match appropriate review tasks according to the level and expertise of the reviewers, thus failing to improve the efficiency of review.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide an intelligent dispatching method, device and storage medium, aiming to solve the technical problem of low efficiency of order review caused by insufficient response time of existing order review.

[0005] To achieve the above objectives, the present application proposes an intelligent dispatching method, which includes:

[0006] Determine the corresponding approval task set based on the approval authority of the current approver;

[0007] Sorting the approval tasks in the approval task set according to their priorities, and dispatching the approval tasks to the approval personnel in order;

[0008] Wherein, the approval task is dispatched when the working status of the approval personnel is idle.

[0009] In one embodiment, the step of determining the corresponding approval task set according to the approval authority of the current approver includes:

[0010] Determine the attribute parameters of the approval tasks that the approval personnel can handle based on their approval authority;

[0011] The corresponding approval task set is determined according to the approval task attribute parameters.

[0012] In one embodiment, after the step of sorting the approval tasks in the approval task set according to their priorities and dispatching the approval tasks to the approval personnel in sequence, the method further includes:

[0013] Counting the pending time of each approval task, and marking the target approval tasks whose pending time is greater than or equal to the preset approval time;

[0014] Submit the marked target approval task.

[0015] In one embodiment, the step of counting the pending time of each approval task and marking the target approval task whose pending time is greater than or equal to the preset approval time includes:

[0016] Determining the priority of each of the approval tasks;

[0017] The preset approval time corresponding to each approval task is determined according to the priority.

[0018] In one embodiment, the step of sorting the approval tasks in the approval task set according to their priorities and dispatching the approval tasks to the approval personnel in order includes:

[0019] Obtaining the corresponding weight value of each attribute parameter in the task information of the approval task;

[0020] The priority of the approval task is calculated according to the weight value.

[0021] In one embodiment, the intelligent dispatching method further includes:

[0022] Input the approval data in the approval pool into the approval task dispatching model, and determine the approver based on the data algorithm in the approval task dispatching model;

[0023] Output the list of reviewers of the review data to distribute the review task according to the list of reviewers.

[0024] In one embodiment, before the step of inputting the approval data in the approval pool into the approval task dispatching model, the method further includes:

[0025] Get historical approval data;

[0026] The approval task dispatching model is generated by training a data model using the historical approval data as a training sample, wherein a corresponding machine learning algorithm is selected according to the data features of the historical approval data, and the machine learning algorithm is used as the data algorithm of the approval task wholesale model.

[0027] The present application also proposes an intelligent dispatching method, which includes:

[0028] When an approval task enters the pool, the corresponding approval pool partition is determined according to the task information of the approval task;

[0029] Storing the approval task in the approval pool partition;

[0030] When it is determined that the approval personnel corresponding to the approval pool partition are idle, the approval tasks of the approval pool partition are dispatched to the approval personnel according to their priorities.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes an intelligent dispatching device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the intelligent dispatching method described above.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the intelligent dispatching method described above are implemented.

[0033] One or more technical solutions proposed in this application have at least the following technical effects:

[0034] In the technical solution of the present application, a corresponding approval task set is determined according to the approval authority of the current approval officer; the approval tasks in the approval task set are sorted according to their priorities, and the approval tasks are dispatched to the approval officers in sequence; wherein, the approval tasks are dispatched when the working status of the approval officers is idle. The present application sets the priority of the approval tasks and the approval authority of the approval officers, and can quickly locate the approval officers who meet the approval requirements based on the current approval task priority, thereby improving the dispatching efficiency of the approval tasks and achieving the technical effect of improving the approval efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0037] Figure 1 A flowchart of the first embodiment of the intelligent dispatching method of the present application is provided;

[0038] Figure 2 A flowchart of the second embodiment of the intelligent dispatching method of the present application is provided;

[0039] Figure 3A flowchart of the third embodiment of the intelligent dispatching method of the present application is provided;

[0040] Figure 4 A flowchart of the fourth embodiment of the intelligent dispatching method of the present application is provided;

[0041] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the intelligent dispatching method in the embodiment of the present application.

[0042] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0044] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0045] The main solution of the embodiment of the present application is: determine the corresponding approval task set according to the approval authority of the current approval personnel; sort the approval tasks in the approval task set according to their priority, and dispatch the approval tasks to the approval personnel in sequence; wherein, the approval task is dispatched when the working status of the approval personnel is idle.

[0046] Since the existing method of actively claiming tasks and manually assisting in assigning tasks is highly dependent on manual operations, it requires a high level of initiative and proficiency from the reviewers. Reviewers may select and review orders on their own, and the response time is insufficient, which cannot support the rapidly growing business volume. In addition, it is impossible to flexibly match the appropriate review tasks according to the reviewer's level and expertise, thus failing to improve the efficiency of review.

[0047] The present application provides a solution, which determines the corresponding approval task set according to the approval authority of the current approval personnel; sorts the approval tasks in the approval task set according to the priority, and dispatches the approval tasks to the approval personnel in sequence; wherein, the approval tasks are dispatched when the working status of the approval personnel is idle. The present application can quickly locate the approval personnel who meet the approval requirements based on the current approval task priority by setting the approval task priority and the approval authority of the approval personnel, thereby improving the dispatching efficiency of the approval tasks and achieving the technical effect of improving the approval efficiency.

[0048] Based on this, the embodiment of the present application provides an intelligent dispatching method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the intelligent dispatching method of the present application.

[0049] In this embodiment, the intelligent dispatching method includes steps S10 to S20:

[0050] Step S10, determining the corresponding approval task set according to the approval authority of the current approver;

[0051] Step S20, sorting the approval tasks in the approval task set according to their priorities, and dispatching the approval tasks to the approval personnel in sequence; wherein the approval tasks are dispatched when the approval personnel's working status is idle.

[0052] In this embodiment, after the approval task is reported from the relevant approval system or approval platform, it enters the approval pool for distribution and processing. The approval pool is essentially a data pool for temporarily storing approval tasks, which can be represented in the form of a data list and sorted according to the pending time of the approval tasks.

[0053] According to the approval tasks currently available in the approval pool, the approval tasks are dispatched to the corresponding approval personnel for processing. To improve the approval efficiency of approval tasks, approval tasks are only dispatched to approval personnel whose current working status is idle. Among them, the approval personnel, as professional reviewers who handle approval tasks, can set the current working status according to the working situation during their work. The working status may include idle status, non-idle status, leave status, etc., which can be used to determine whether the current approval task can be approved.

[0054] Based on this, when dispatching the approval tasks in the approval pool to the approval personnel, the approval personnel whose current working status is idle are determined. In the current approval process, the approval personnel include one or more, so the approval personnel whose current working status is idle also include one or more. In this way, the approval tasks are dispatched according to the idle approval personnel who have been determined to be able to handle the approval tasks.

[0055] Furthermore, the working status of the approving personnel involves the scheduling of approval tasks. In order to immediately realize the dispatch of the approval tasks, it is necessary to monitor the working status of the approving personnel in real time to immediately find the idle approving personnel to dispatch the approval tasks. After the approval task is dispatched to the corresponding approving personnel, the working status of the approving personnel will be set to the working status, etc.

[0056] Since each approval task has different approval information, in order to improve the processing speed of the approval task, the difficult approval task can be assigned to the approval personnel who meet the approval requirements. In this embodiment, the approval personnel's compliance with the relevant approval requirements is characterized by the setting of approval authority. Therefore, the approval tasks that the approval personnel can handle can be divided by setting the approval authority of the approval personnel, that is, the step of determining the corresponding approval task set according to the approval authority of the approval personnel includes:

[0057] Determine the attribute parameters of the approval tasks that the approval personnel can handle based on their approval authority;

[0058] The corresponding approval task set is determined according to the approval task attribute parameters.

[0059] After determining the approval personnel whose current working status is idle, the approval authority of the approval personnel is determined. The approval authority is pre-configured authority information used to determine the approval tasks that can be processed by the approval personnel. Therefore, based on the approval authority possessed by the approval personnel, the attribute parameters of the approval tasks that can be processed based on the approval authority are determined. In this embodiment, the attribute parameters of the approval tasks can be characterized as parameter information that requires a high level of proficiency in processing, such as the confidentiality of the approval tasks, the approval amount, the approval type, etc. In addition, the attribute parameters of the approval tasks can also be converted into the approval authority of the approval personnel to configure the approval authority.

[0060] As shown above, after determining the approval authority of the approving personnel, the corresponding approval task attribute parameters to be processed are determined based on the approval authority. After that, the corresponding approval task is determined based on the determined approval task attribute parameters. Due to the number of approval tasks to be approved in the approval pool, the corresponding approval tasks that meet the approval task attribute parameters may include multiple. After determining the corresponding approval task attribute parameters that can be processed according to the approval authority of the current approving personnel, the approval tasks that meet the approval task attribute parameters are screened in the approval pool. Among them, the approval tasks that can be determined may include one or more. In order to avoid repeated screening processes to increase the burden on the server, an approval task set is generated according to the current screening process to divide the approval tasks that meet the approval task attribute parameters. The approval task set can be achieved by marking the approval tasks corresponding to the approval task attribute parameters, or registering the relevant information of the approval tasks.

[0061] In this way, according to the determined approval task set that meets the approval authority of the approval personnel, the approval tasks in the approval task set are distributed to the approval personnel. In order to further improve the processing efficiency of the approval tasks, the approval tasks in the approval task set are distributed to the approval personnel in order according to the priority of each approval task. That is, the steps of sorting the approval tasks in the approval task set according to the priority and distributing the approval tasks to the approval personnel in order include:

[0062] Obtaining the corresponding weight value of each attribute parameter in the task information of the approval task;

[0063] The priority of the approval task is calculated according to the weight value.

[0064] According to the approval tasks included in the generated approval task set, when determining the priority of the approval task by using the preset priority rule, the determination is made by using the calculation process set in the priority rule. The priority involves the dispatching order of the approval task during the approval process. Therefore, in order to adapt the dispatching order, the priority of the task information is determined by using the preset priority rule, because the task information includes relevant parameter information based on the approval task. Moreover, the preset priority rule is calculated by calculating the attribute parameters contained in the task information.

[0065] The pre-set priority rules include setting of weight values ​​corresponding to attribute parameters. Therefore, when the task information of the approval task contains multiple attribute parameters, the priority of the approval task is calculated using the set weight values ​​corresponding to each attribute parameter. The task information includes but is not limited to relevant attribute parameter information based on the approval type, approval amount, approval task source, confidentiality level, etc. of the approval task that can be used to determine the approval order.

[0066] In addition, after the corresponding approval task set is divided based on the approval authority of the approval personnel, there may be multiple approval personnel with the same approval authority, that is, each approval task set corresponds to one or more approval personnel who can handle each approval task in the approval task set. Based on this, the approval tasks can be dispatched one by one to the corresponding approval personnel in order according to the priority of each approval task in the approval task set for processing, and the working status of each approval personnel can be monitored in real time, so as to schedule the dispatch of approval tasks in real time according to the working status of the approval personnel.

[0067] Based on the approval task dispatching process shown above, it is essentially a dispatching process based on the approval authority possessed by the approval personnel. Therefore, a new approval personnel authority management process can be established based on the current approval task approval requirements. In the approval personnel authority management process, multiple approval authority levels are set. In the approval authority levels, hierarchical division can be performed based on the parameter options of each approval task attribute parameter, that is, different approval authority levels, with the authority level as the identifier, have different numbers of parameter option settings for approval task attribute parameters, so as to realize approval authority of different levels. Moreover, in the attribute level, objective factors such as the working years and work experience of the approval personnel can also be limited. Based on the established approval personnel authority management process, different approval authorities are configured for the approval personnel, so that the approval personnel have the ability to approve various types of approval tasks.

[0068] In this embodiment, this application can quickly locate the approval personnel who meet the approval requirements based on the current approval task priority through the approval task priority and the approval authority setting of the approval personnel, thereby improving the dispatching efficiency of the approval tasks and achieving the technical effect of improving the approval efficiency.

[0069] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 After step S20, the intelligent dispatching method further includes steps S30 to S40:

[0070] Step S30, counting the waiting time for each approval task, and marking the target approval tasks whose waiting time is greater than or equal to the preset approval time;

[0071] Step S40: reporting the marked target approval task.

[0072] In this embodiment, after the approval task enters the pool, the waiting time of the approval task is counted, and the waiting time can also be used to represent the waiting time of the approval task in the approval process. That is, after the approval task enters the pool, it needs to be approved through the dispatching process. Based on this, in order to avoid the approval timeout caused by the approval waiting time of the approval task being too long, the waiting time of the approval task is registered after the approval task enters the pool.

[0073] Since the dispatching process of the approval task after entering the pool will be integrated into the corresponding approval task set according to the approval authority of the approver, and the dispatching process in the approval task set needs to be processed in order based on the priority of each approval task, this process can also be considered as a more accurate approval waiting time. Therefore, considering the data classification action of the approval task set, the waiting time can be registered after the approval task is added to each approval task set.

[0074] Alternatively, the purpose of the approval task entering the approval pool is to be dispatched to each approval personnel for processing. Therefore, the waiting time of the approval task can also be counted after the approval task enters the pool.

[0075] According to the above registration, based on the time process of the approval task waiting for the dispatch order to be processed, considering the different urgency of different approval tasks, in order to screen more urgent approval tasks, a preset approval time for determining whether each approval task has timed out can be set based on the priority of each approval task. That is, the step of counting the waiting time of each approval task and marking the target approval task whose waiting time is greater than or equal to the preset approval time includes:

[0076] Determining the priority of each of the approval tasks;

[0077] The preset approval time corresponding to each approval task is determined according to the priority.

[0078] According to the currently counted approval time of each approval task, the corresponding preset approval time is obtained according to the priority of each approval task in the current approval task set. The preset approval time is one or more, and is set according to one or more levels of the priority. That is, each priority level corresponds to a preset approval time. It can be understood that the higher the priority, the shorter the corresponding preset approval time is, so as to improve the processing speed of the approval task with a high priority.

[0079] Therefore, after obtaining the corresponding preset approval time based on the priority of each approval task, the registered approval time is compared with the corresponding preset approval time, and the target approval task whose approval time is greater than or equal to the corresponding preset approval time is marked according to the comparison result. In addition, the marked target approval task is reported to the manual dispatching office for manual dispatching to avoid approval task timeout.

[0080] In this embodiment, by registering the waiting time for approval of the approval task, it is used to determine whether the approval processing of the approval task has timed out, thereby avoiding low processing efficiency caused by approval order timeout and improving the processing efficiency of the approval task.

[0081] The present application also provides an intelligent dispatching method. Figure 3 , Figure 3 This is a flow chart of the third embodiment of the intelligent dispatching method of the present application. In this embodiment, the intelligent dispatching method includes steps S50 to S60:

[0082] Step S50: input the approval data in the approval pool into the approval task dispatching model, and determine the approver by the data algorithm in the approval task dispatching model;

[0083] Step S60: output the list of approvers of the approval data, so as to distribute the approval task according to the list of approvers.

[0084] In this embodiment, the approval orders in the pool are distributed by setting an approval task dispatching model. After the approval task is in the pool, the approval task is input as input data into the approval task dispatching model, and the list of approval personnel who process the approval data is output after calculation by the approval task dispatching model. Furthermore, the approval task can be dispatched to the corresponding approval personnel through the list of approval personnel. In this embodiment, the list of approval personnel includes one or more approval personnel, and the approval personnel registered in the list of approval personnel are all personnel with the approval ability to process the approval data. In addition, the approval personnel are arranged in order of priority in the list of approval personnel according to the approval ability of each approval personnel, and the determination of the priority is related to the historical approval task processing information of the approval personnel, such as the number of approvals, approval efficiency, years of work, and other information that can reflect the approval ability of the approval personnel.

[0085] The above contents all involve the application of the approval task dispatching model. In order to improve the accurate calculation of the approval task dispatching model, it is trained through historical approval data. That is, before the step of inputting the approval data in the approval pool into the approval task dispatching model, it also includes:

[0086] Get historical approval data;

[0087] The approval task dispatching model is generated by training a data model using the historical approval data as a training sample, wherein a corresponding machine learning algorithm is selected according to the data features of the historical approval data, and the machine learning algorithm is used as the data algorithm of the approval task wholesale model.

[0088] Based on the current approval data requirements, a new data model is created for training to obtain an available approval task dispatching model. Therefore, historical approval data is obtained, and the data model is trained using the historical approval data as training samples. Among them, due to the nature and data characteristics of different problems, different machine learning algorithms need to be applicable, including decision trees, support vector machines, neural networks, etc. Therefore, when using historical approval data for training sample application, it is necessary to select a suitable machine learning algorithm for the data model based on the data characteristics and training results of the historical approval data. In this way, based on the selected machine learning algorithm, the acquired historical approval data is formed into training samples for calculation, because the training of the machine learning algorithm involves the calculation of data features as parameters. Relevant data features are extracted from the historical approval data to form training samples for calculation, that is, the content of the training samples is essentially the data features in the historical approval data.

[0089] Furthermore, the approval task dispatching model also has hyperparameters, which are parameters that need to be manually set in the machine learning model to ensure the application performance of the data model; in the process of model training using historical approval data as training samples, different hyperparameters need to be set based on the data information of the historical approval data, that is, hyperparameters are set based on the attribute parameters in the data information, including but not limited to the basic information of the approval data, the approval information, and the corresponding approval personnel information. The performance of the approval task model can be optimized by applying the hyperparameters. In this embodiment, the optimization method of the hyperparameters based on the approval data dispatching model can apply grid search, random search, Bayesian optimization, etc., so as to find the optimal hyperparameter combination in the hyperparameter space. In practical applications, the adjustment of hyperparameters needs to be combined with specific tasks and data sets for repeated experiments and evaluations to find the best hyperparameter combination and improve the performance of the model.

[0090] Furthermore, in order to ensure the application effect of the approval task dispatching model, the training of the approval task dispatching model should be a long-term training process, that is, the approval task dispatching model is continuously trained through the generated historical approval data, and the performance of the approval task dispatching model in each training stage is evaluated.

[0091] In the evaluation process, the performance evaluation operation is performed using pre-set corresponding evaluation methods and indicators in combination with the specific business scenarios and data characteristics of the historical approval data used in the current training phase. Alternatively, new corresponding evaluation methods and indicators are created based on the specific business scenarios and data characteristics of the historical approval data to perform performance evaluation.

[0092] At the same time, attention should also be paid to data preprocessing, model training, test set division and other links in the evaluation process to ensure the accuracy and reliability of the evaluation results. In practical applications, the performance of the data model can be improved by adjusting the model parameters, optimizing the model structure, and adopting advanced training algorithms. In addition, resource consumption can be reduced and processing efficiency can be improved by using more efficient hardware resources and optimizing data storage and processing processes.

[0093] In addition, when evaluating the data model performance of the training job of the current training sample of the approval task dispatching model, on the basis of having the corresponding evaluation methods and indicators, the performance evaluation process has several key stages, namely, data preparation, model training, model evaluation, result analysis and optimization, model verification and selection, model deployment and monitoring, and document recording and reporting. That is, in the training job of training the approval task dispatching model by generating training samples based on the current historical approval data, specific performance evaluation jobs are performed at each key stage based on the training job, and the job content can be as follows:

[0094] 1) Data preparation:

[0095] Data cleaning: Check and process missing values, outliers, duplicate values, etc. in the training samples;

[0096] Data division: The training sample data is divided into a training set, a validation set and a test set. The training set is used to train the model, the validation set is used to adjust hyperparameters and prevent overfitting, and the test set is used to evaluate the generalization ability of the model;

[0097] Feature engineering: selecting or creating performance features that help improve the approval task dispatching model based on business requirements and data characteristics in the training samples.

[0098] 2) Model training: Fit the model using the training data and adjust the model parameters to minimize the training error. A validation set can be used for cross-validation (such as K-fold cross-validation) to evaluate the performance of the approval task dispatch model on different data subsets and select appropriate hyperparameters.

[0099] 3) Model evaluation:

[0100] Select evaluation indicators: Generate training samples based on the historical approval data of the currently trained application, and determine appropriate evaluation indicators based on the task types (such as classification, regression, clustering, etc.) that the training samples have in the training process. The evaluation indicators include accuracy, precision, recall, F1 score, AUC-ROC, mean square error (MSE), root mean square error (RMSE), etc.

[0101] Evaluate the model on the test set: Use the test set to evaluate the trained approval task dispatching model and calculate the value of the evaluation index. Ensure that the test set has not been used in the training process of the approval task dispatching model to maintain the fairness of the evaluation.

[0102] 4) Result analysis and optimization: Analyze the performance of the approval task dispatching model on the test set to understand its strengths and weaknesses. Adjust the model structure, parameters or feature selection of the approval task dispatching model based on the evaluation results to optimize the model performance. Tools such as learning curves, validation curves, confusion matrices, and ROC curves can be used for further model analysis.

[0103] 5) Model verification and selection: multiple candidate initial data models can be set to perform the training operation of the training samples to evaluate the performance of the candidate data models on the verification set, and the model with the best performance can be selected as the final data model, that is, the approval data distribution model that can be applied. Alternatively, multiple models can be integrated by using ensemble learning to improve the overall data model performance.

[0104] 6) Model deployment and monitoring: Deploy the trained approval task dispatching model to the production environment and monitor it in real time. Collect data from actual use, regularly evaluate the performance of the approval task dispatching model, and adjust and optimize it as needed.

[0105] 7) Documentation and reporting: Document the key steps and results of the model training, evaluation, and optimization process of the approval task dispatch model. Write reports to show stakeholders the model's performance, strengths, limitations, and directions for future improvements.

[0106] According to the performance evaluation operation of the approval data distribution model training process shown above, by setting relevant evaluation indicators, it is determined whether the performance of the final data model formed by the current sample training results meets the current application requirements, and it is possible to provide a quantitative measure of the model's prediction ability, accuracy and stability. In the performance evaluation process of actual applications, the performance of the approval data distribution model is determined by relevant model performance evaluation indicators. The model performance evaluation indicators can be divided into classification task evaluation indicators, regression task evaluation indicators and other general indicators according to the evaluation task type of the performance evaluation.

[0107] The classification task evaluation indicators include accuracy, precision, recall or sensitivity, F1 score, ROC curve and AUC value; the regression task evaluation indicators include mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), R square (R 2 or Coefficient of Determination); the other general indicators include generalization ability, robustness and stability.

[0108] The evaluation indicators shown above need to be comprehensively considered based on the approval task requirements, approval data characteristics, and application scenarios of the approval data distribution scenarios contained in the historical approval data corresponding to the training samples involved in the current performance evaluation. In this embodiment, one or more evaluation indicators can be selected to perform performance evaluation on the training process of the approval data distribution model.

[0109] In this way, through the application of the machine learning algorithm in the data model, the training samples are calculated by the data machine learning algorithm, and the model performance is evaluated at each training stage to improve the data structure in the data model to form the final approval task dispatching model.

[0110] In this embodiment, by applying the approval task dispatching model, the approval data is input as a parameter into the approval task dispatching model for calculation and then a list of approvers is output, so as to select the best approvers and thus improve the approval efficiency of the approval task.

[0111] Furthermore, the present application embodiment also provides an intelligent dispatching method, referring to Figure 4 , Figure 4 This is a flow chart of the fourth embodiment of the intelligent dispatching method of the present application.

[0112] In this embodiment, the intelligent dispatching method includes steps S70 to S90:

[0113] Step S70: When an approval task enters the pool, the corresponding approval pool partition is determined according to the task information of the approval task;

[0114] Step S80, storing the approval task in the approval pool partition;

[0115] Step S90: When it is determined that the approval personnel corresponding to the approval pool partition are idle, the approval tasks of the approval pool partition are dispatched to the approval personnel according to their priorities.

[0116] In this embodiment, after the approval task is reported from the relevant approval system or approval platform, it enters the approval pool for dispatch processing. When the approval task enters the pool, the approval pool partition to which it belongs is determined according to the task information of the approval task.

[0117] The approval pool is essentially a data pool for temporarily storing approval tasks, which is represented by a data list or other forms. In order to improve the efficiency of distributing approval tasks, the approval pool is pre-partitioned, that is, the approval pool is divided into multiple approval pool partitions, each of which has different approval tasks. Since the approval tasks are related to the approval authority of the corresponding approval personnel when they are distributed, when the approval pool is partitioned, the partition characteristics of each approval pool partition after partitioning are essentially the corresponding approval authority, and the authority difference of the approval authority is defined as the authority level. Based on this, the partition characteristics of the approval pool partition after partitioning should also be the authority level of different approval authorities.

[0118] According to the above analysis, when the approval task in the pool is saved to the corresponding approval pool partition, the approval pool partition to which the approval task belongs can be determined based on the approval authority level that meets the approval task, that is, which approval pool partition's approval authority can approve the approval task is determined as the approval pool partition to which the approval task belongs. The approval authority of the approval task is determined by reading the task information of the approval task, that is, the corresponding approval authority is determined by the approval task attribute parameters contained in the task information of the approval task.

[0119] Furthermore, after the approval authority of the approval task has been determined, the approval task is saved to the approval pool partition with the approval authority. After the approval task enters the corresponding approval pool partition, it is sorted according to the priority of the approval task, and the approval task is dispatched to the approval personnel corresponding to the approval pool partition in sequence. Among them, the approval personnel corresponding to the approval pool partition are the approval personnel with relevant approval authority. The approval personnel corresponding to the approval pool partition include one or more. By real-time detection of the working status of the approval personnel, each approval task sorted by priority is dispatched to the approval personnel in the idle state.

[0120] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method of assigning approval tasks for the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0121] The present application provides an intelligent order dispatching device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent order dispatching method in the above-mentioned embodiment one.

[0122] Reference below Figure 5 , which shows a schematic diagram of the structure of an intelligent dispatching device suitable for implementing the embodiment of the present application. The intelligent dispatching device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The smart dispatching device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0123] like Figure 5 As shown, the intelligent dispatching device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the intelligent dispatching device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the intelligent dispatching device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows an intelligent dispatching device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0124] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0125] The intelligent dispatching device provided by the present application adopts the intelligent dispatching method in the above embodiment, which can solve the technical problem of low efficiency of order review caused by insufficient response time of existing order review. Compared with the prior art, the beneficial effects of the intelligent dispatching device provided by the present application are the same as the beneficial effects of the intelligent dispatching method provided by the above embodiment, and the other technical features in the intelligent dispatching device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0126] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0127] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0128] The present application provides a storage medium, which is a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the intelligent dispatching method in the above-mentioned embodiment.

[0129] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0130] The above-mentioned computer-readable storage medium may be included in the intelligent dispatching device; or it may exist independently without being assembled into the intelligent dispatching device.

[0131] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the intelligent order dispatching device, the intelligent order dispatching device implements the technical content of the intelligent order dispatching method embodiment shown above.

[0132] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0133] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0134] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0135] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned intelligent dispatching method, and can solve the technical problem that the existing technology cannot meet the response time limit of the existing inspection, resulting in low inspection efficiency. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the intelligent dispatching method provided in the above-mentioned embodiment, and will not be repeated here.

Claims

1. An intelligent dispatching method, characterized in that: The method includes: Determine the corresponding approval task set based on the approval authority of the current approver; Sorting the approval tasks in the approval task set according to their priorities, and dispatching the approval tasks to the approval personnel in order; Wherein, the approval task is dispatched when the working status of the approval personnel is idle.

2. The intelligent dispatching method according to claim 1, characterized in that: The step of determining the corresponding approval task set according to the approval authority of the current approver includes: Determine the attribute parameters of the approval tasks that the approval personnel can handle based on their approval authority; The corresponding approval task set is determined according to the approval task attribute parameters.

3. The intelligent dispatching method according to claim 1, characterized in that: After the step of sorting the approval tasks in the approval task set according to their priorities and dispatching the approval tasks to the approval personnel in sequence, the method further includes: Counting the pending time of each approval task, and marking the target approval tasks whose pending time is greater than or equal to the preset approval time; Submit the marked target approval task.

4. The intelligent dispatching method according to claim 3, characterized in that: The step of counting the pending processing time of each approval task and marking the target approval task whose pending processing time is greater than or equal to the preset approval time includes: Determining the priority of each of the approval tasks; The preset approval time corresponding to each approval task is determined according to the priority.

5. The intelligent dispatching method according to claim 1, characterized in that: The step of sorting the approval tasks in the approval task set according to their priorities and dispatching the approval tasks to the approval personnel in sequence includes: Obtaining the corresponding weight value of each attribute parameter in the task information of the approval task; The priority of the approval task is calculated according to the weight value.

6. The intelligent dispatching method according to claim 1, characterized in that: The intelligent dispatching method further includes: Input the approval data in the approval pool into the approval task dispatching model, and determine the approver based on the data algorithm in the approval task dispatching model; Output the list of reviewers of the review data to distribute the review task according to the list of reviewers.

7. The intelligent dispatching method according to claim 6, characterized in that: Before the step of inputting the approval data in the approval pool into the approval task dispatching model, the method further includes: Get historical approval data; The approval task dispatching model is generated by training a data model using the historical approval data as a training sample, wherein a corresponding machine learning algorithm is selected according to the data features of the historical approval data, and the machine learning algorithm is used as the data algorithm of the approval task wholesale model.

8. An intelligent dispatching method, characterized in that: The intelligent dispatching method comprises: When an approval task enters the pool, the corresponding approval pool partition is determined according to the task information of the approval task; Storing the approval task in the approval pool partition; When it is determined that the approval personnel corresponding to the approval pool partition are idle, the approval tasks of the approval pool partition are dispatched to the approval personnel according to their priorities.

9. An intelligent dispatching device, characterized in that: Said include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the intelligent dispatching method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the intelligent dispatching method according to any one of claims 1 to 8 are implemented.

Images