Workflow system monitoring method and device and storage medium

Abstract

The invention relates to a monitoring method and device for a workflow system and a storage medium, and the method comprises the steps: obtaining related data in a task execution process of the workflow system in real time, the related data comprising task execution information, a user operation log and current environment information; the related data is input into a workflow prediction model, early warning information output by the workflow prediction model is obtained, the early warning information is used for indicating risks existing in the task execution process of the workflow system, real-time monitoring of the production environment is achieved, and therefore real-time and efficient risk management of workflow can be achieved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a monitoring method, device and storage medium for a workflow system. Background Art

[0002] The workflow system is a software technology platform that uses computer technology to implement the workflow engine mechanism, aiming to automate the management of business processes. It has significant advantages in standardizing workflows and reducing production costs. However, current workflow systems can usually only create workflows, but cannot predict and manage risks in workflows. They still rely on manual monitoring and intervention of risks, which increases enterprise management costs. Manual monitoring often fails to detect potential problems in a timely manner, bringing many hidden dangers to enterprise development. Summary of the invention

[0003] The present disclosure provides a monitoring method, device and storage medium for a workflow system, which can realize real-time and efficient risk management of the workflow.

[0004] In a first aspect, the present disclosure provides a monitoring method for a workflow system, comprising:

[0005] Real-time acquisition of relevant data during the execution of tasks by the workflow system, including task execution information, user operation logs, and current environment information;

[0006] The relevant data is input into a workflow prediction model, and warning information output by the workflow prediction model is obtained, where the warning information is used to indicate risks existing in the process of executing tasks by the workflow system.

[0007] In some embodiments, it also includes:

[0008] The relevant data acquired in real time is stored in the edge device, and the relevant data is used to update and train the workflow prediction model.

[0009] In some embodiments, the output of the workflow prediction model also includes a solution corresponding to the early warning information and a score thereof, wherein the score is used to indicate the probability that the solution can resolve the risk in the early warning information.

[0010] In some embodiments, it also includes:

[0011] Generate a warning reminder message based on the warning information;

[0012] The warning reminder message is outputted via at least one of email, text message, instant messaging and application notification.

[0013] In some embodiments, generating a warning reminder message based on the prediction information includes:

[0014] The warning reminder message is generated based on preset rules and the warning information.

[0015] In some embodiments, the warning information includes risk data and a task identifier for which the risk data is targeted, and the warning reminder message includes a deadline for the task for which the warning information is targeted; the preset rule includes whether the interval between the current time and the deadline of the task is less than a preset duration;

[0016] Generating the warning reminder message based on the preset rules and the warning information includes:

[0017] In response to determining that the interval between the current time and the deadline of the task is less than a preset duration;

[0018] The early warning reminder message is generated based on the early warning information.

[0019] In some embodiments, it also includes:

[0020] Get the deadline of the current task, the usage of system resources and the execution progress information of historical tasks;

[0021] Adjusting the priority of the current task based on the deadline of the current task, the usage of system resources and the execution progress information of historical tasks;

[0022] Generate a priority adjustment reminder message based on the priority of the current task;

[0023] The level adjustment reminder message is outputted through at least one of email, text message, instant messaging and application notification, so that relevant personnel can perform resource allocation.

[0024] In some embodiments, it also includes:

[0025] At least one of the current execution progress information, warning information and current resource allocation information of the task is displayed through a visual interface.

[0026] In some embodiments, it also includes:

[0027] Obtain configuration information input by the user through the visualization interface, wherein the configuration information includes at least one of the following items: the task type for which the current execution progress information is to be displayed, the reminder thresholds of different tasks, and the dimensions of the data to be displayed, wherein the reminder thresholds include the thresholds corresponding to the early warning reminder message and the thresholds corresponding to the level adjustment reminder message.

[0028] In some embodiments, the workflow prediction model includes a sub-prediction model for each task, and the relevant data includes task execution information, user operation log, and current environment information for each task;

[0029] The step of inputting the relevant data into a workflow prediction model and obtaining the warning information output by the workflow prediction model includes:

[0030] Inputting the task execution information, user operation log, and current environment information of each task into the sub-prediction model corresponding to the task, and obtaining the sub-warning information for each task output by the sub-prediction model;

[0031] Based on the multiple warning sub-information corresponding to the multiple tasks, warning information for the workflow system is obtained.

[0032] In a second aspect, the present disclosure provides a method for training a workflow prediction model, comprising:

[0033] Acquire sample data and real warning information thereof, wherein the sample data includes sample-related data during the process of the workflow system executing sample tasks, and the sample-related data includes task execution information, user operation logs, and current environment information;

[0034] Inputting the sample-related data into a workflow prediction model, and obtaining prediction and warning information output by the workflow prediction model;

[0035] The parameters of the workflow prediction model are adjusted based on the real warning information and the predicted warning information.

[0036] In a third aspect, the present disclosure provides a monitoring device for a workflow system, wherein the workflow system is used to execute multiple tasks, and the monitoring device comprises:

[0037] A first acquisition module is configured to acquire relevant data in the process of executing tasks in the workflow system in real time, wherein the relevant data includes task execution information, user operation logs, and current environment information;

[0038] The second acquisition module is configured to input the relevant data into the workflow prediction model and acquire the warning information output by the workflow prediction model.

[0039] In a fourth aspect, the present disclosure provides a training device for a workflow prediction model, comprising:

[0040] A third acquisition module is configured to acquire sample data and real warning information thereof, wherein the sample data includes sample-related data during the execution of a sample task by the workflow system, and the sample-related data includes task execution information, user operation logs, and current environment information;

[0041] A fourth acquisition module is configured to input the sample-related data into a workflow prediction model and acquire prediction and warning information output by the workflow prediction model;

[0042] A parameter adjustment module is configured to adjust the parameters of the workflow prediction model based on the real warning information and the predicted warning information.

[0043] In a fifth aspect, the present disclosure provides an electronic device, comprising a memory, at least one processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-mentioned method.

[0044] In a sixth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned method when executed by a processor.

[0045] The present application provides a monitoring method, device and storage medium for a workflow system, which can obtain relevant data during the execution of tasks by the workflow system, input the relevant data into a workflow prediction model, and obtain early warning information output by the workflow prediction model. By integrating multiple real-time data sources, real-time monitoring of the production environment can be achieved, thereby achieving real-time and efficient risk management of the workflow.

[0046] 1. Technical Features The relevant data acquired in real time is stored in the edge device. The technical effect is to use edge computing technology to process and analyze data in real time through local devices, reduce dependence on the cloud, and thus improve the real-time nature and privacy protection of data processing. And it can make full use of real-time data for accurate prediction and decision support.

[0047] 2. Technical Features The output of the workflow prediction model also includes the solution and score corresponding to the warning information. The technical effect is that the model outputs the solution and score at the same time, and introduces uncertainty quantification technology (such as Bayesian optimization) to evaluate the uncertainty of the prediction results and provide confidence intervals. This makes the prediction solution more reliable and provides a better basis for decision-making.

[0048] 3. The technical feature is to adjust the priority of the current task based on the deadline of the current task, the usage of system resources and the execution progress information of historical tasks, and generate a level adjustment reminder message based on the priority of the current task. The technical effect is to analyze the current production situation, including the urgency of the task, the usage of resources and the historical task completion status. When the completion time of a critical task is approaching and resources are tight, the system will automatically increase the priority of the task and remind the user to allocate resources to ensure the efficiency of task execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of a monitoring method for a workflow system provided in an embodiment of the present disclosure.

[0050] Figure 2A flowchart of a method for training a workflow prediction model provided in an embodiment of the present disclosure.

[0051] Figure 3 A schematic diagram of the structure of a monitoring device for a workflow system provided in an embodiment of the present disclosure.

[0052] Figure 4 A schematic diagram of the structure of a training device for a workflow prediction model provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0055] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0056] With the advent of the information and digital age, workflow systems have become a vital management tool in the process of enterprise development. Originated from the fields of production organization and office automation, workflow systems are used for business processing or collaborative work in daily work. By breaking down work into well-defined tasks and roles and executing these tasks according to certain rules and processes, the goals of standardizing workflows, reducing production costs, and improving work efficiency can be achieved. However, the current workflow system can only create workflows, but cannot manage and predict risks in the process, which means that it has to rely on manual monitoring and adjustment of workflows to solve bottlenecks and obstacles. This not only consumes a lot of human resources, but also has the risk of not being able to discover current problems in a timely manner, resulting in serious consequences such as low production efficiency and slow response to risks.

[0057] The present application discloses a monitoring method for a workflow system, which indicates the risks in the process of executing tasks by acquiring relevant data in the process of the workflow system executing tasks in real time, inputting the relevant data into a workflow prediction model, and acquiring the warning information output by the workflow prediction model method. The above-mentioned relevant data includes task execution information, user operation logs, current environment information, etc. The workflow system integrates multiple real-time data sources, including relevant data from IoT devices, user operation logs, and smart phones, etc., to achieve real-time monitoring of the production environment, thereby achieving real-time and efficient risk management of the workflow.

[0058] Embodiment 1

[0059] Figure 1 A flowchart of a monitoring method for a workflow system according to an embodiment of the present application is shown, the method comprising:

[0060] Step S110: Acquire relevant data in the process of executing tasks by the workflow system in real time, wherein the relevant data includes task execution information, user operation logs, and current environment information.

[0061] In an embodiment of the present application, the method of obtaining relevant data can be through an Internet of Things device, a smart phone, etc. Among them, the Internet of Things device includes but is not limited to sensors, controllers, RFID devices, industrial cameras, smart meters, gateways, and edge servers. The relevant data includes task execution information, user operation logs, and current environmental information. Among them, the task execution information includes but is not limited to the name, type, task allocation, execution progress, execution time, historical execution time, and resource inventory of the task; the user operation log includes but is not limited to the type of task, execution progress, operator, operation time, equipment adjustment parameters, quality inspection information, abnormal conditions, and resource inventory; the current environmental information includes but is not limited to weather forecasts and market dynamics. The above relevant data are all obtained from the process of executing tasks in the workflow system, and are used for risk prediction and workflow prediction model training in the subsequent task execution process. For the same type of data obtained from different sources, it is used for subsequent cross-verification of data. The data collection method can be an application programming interface (API) or web scraping, where API data collection is usually more reliable and structured.

[0062] In some embodiments, in order to further improve the accuracy and reliability of relevant data, the relevant data can be cleaned and other data preprocessed to remove noise and incomplete data, and features can be extracted from the data through automatic labeling technology and deep learning technology (such as Autoencoder), or feature selection algorithms (such as LASSO) can be used to select the most representative features.

[0063] In order to ensure the timeliness and consistency of data, data from different sources can also be integrated through multi-source data fusion algorithms to generate a unified real-time workflow view. Multi-source data includes execution information, user operation logs, and current environment information. The algorithm can identify and process redundant information in the data, improving the efficiency and accuracy of data fusion.

[0064] Data preprocessing can be done by using data preprocessing tools and libraries, such as at least one of Pandas, NumPy, and Scikit-learn. Pandas and NumPy have better data processing speed and convenience, and Scikit-learn can provide richer machine learning preprocessing functions.

[0065] In some embodiments, relevant data acquired in real time can also be stored in edge devices, and the relevant data can be used to update and train the workflow prediction model. By using edge computing technology, data can be processed and analyzed in real time through local devices, reducing dependence on the cloud, thereby improving the real-time nature and privacy protection of data processing. And it can make full use of real-time data for accurate prediction and decision support.

[0066] Step S120: inputting relevant data into the workflow prediction model, and obtaining warning information output by the workflow prediction model, where the warning information is used to indicate the risks existing in the process of executing tasks by the workflow system.

[0067] In the embodiment of the present application, the large model used can be GPT-4, which performs well in generating long texts and providing contextual replies, so the prediction and reminder generation capabilities of the workflow prediction model can be guaranteed, especially in long text generation and contextual understanding. In other embodiments, the large model used can also be BERT or T5, which is not limited here.

[0068] In an embodiment of the present application, the early warning information may be relevant information about the risks that may exist in the workflow system. In some embodiments, the workflow prediction model may integrate time series prediction algorithms (such as ARIMA, Prophet) and machine learning models (such as XGBoost). These models can accurately predict future production progress, resource requirements, and potential blocking points by training on historical data.

[0069] In some embodiments, the output of the workflow prediction model may also include the solution corresponding to the warning information and its score, and the score is used to indicate the probability that the solution can solve the risk in the warning information. Specifically, when predicting risks, the workflow prediction model can use Bayesian optimization technology to evaluate the uncertainty of the prediction results and provide a confidence interval. This allows users to not only see the results of the prediction, but also understand the reliability of the prediction results, providing a better basis for decision-making. In the decision support process, the workflow prediction model will provide different solutions based on the uncertainty of the prediction. For example, when the prediction uncertainty is high, the workflow prediction model will advise users to adopt a conservative strategy to reduce risks.

[0070] In a specific example, when the warning information indicates that a task is at risk of being overdue, the solution to the risk may be a combination of one or more of adding production lines, adding personnel, adjusting the production sequence, or adding backup resources, and each solution corresponds to a confidence interval that can resolve the risk, so that users can make decisions.

[0071] In some embodiments, warning reminder information can also be generated based on the warning information, and the warning reminder message can be output through at least one of email, SMS, instant messaging and application notification to send the warning reminder information to relevant personnel, prompting the relevant personnel to handle the situation in a timely manner. Among them, the instant communication can be Slack or Microsoft Teams, which has the advantages of being instant and highly interactive, and can further improve the response speed of relevant personnel.

[0072] In some embodiments, the warning reminder message may be generated based on preset rules and warning information, wherein the warning information includes risk data and a task identifier for the risk data, and the warning reminder message includes a deadline for the task for which the warning information is intended.

[0073] In a specific example, the preset rule includes whether the interval between the current time and the deadline of the task is less than the preset duration. Generating the warning reminder message based on the preset rule and the warning information includes: in response to determining that the interval between the current time and the deadline of the task is less than the preset duration; generating the warning reminder message based on the warning information. This is to achieve a reminder of the approaching deadline of the task.

[0074] In some embodiments, the workflow prediction model can also obtain the deadline of the current task, the usage of system resources, and the execution progress information of historical tasks; adjust the priority of the current task based on the deadline of the current task, the usage of system resources, and the execution progress information of historical tasks; generate a level adjustment reminder message based on the priority of the current task; output the level adjustment reminder message through at least one of email, SMS, instant messaging, and application notifications, so that relevant personnel can allocate resources. In this way, the current production situation can be analyzed, including the urgency of the task, the usage of resources, and the historical completion of tasks. When the completion time of a critical task is approaching and resources are tight, the workflow prediction model will automatically increase the priority of the task and remind the user to allocate resources to ensure the efficiency of task execution. Among them, the prediction of system resources can be made using random forests or decision trees to improve its interpretability and speed advantages.

[0075] In some embodiments, at least one of the current execution progress information, warning information, and current resource allocation information of the task can also be displayed through a visualization interface, so that users can view the production progress, forecast results, and resource allocation in real time by dragging, zooming, and clicking. The charts on the interface can be dynamically updated to reflect changes in real-time data. Among them, the front-end framework of the visualization interface can be React.js, Angular, or Vue.js. React.js has a flexible component system and rich ecological support. The data visualization tool can be an interactive visualization interface based on D3.js or Plotly. D3.js has customization and complex interaction capabilities.

[0076] In some embodiments, the configuration information input by the user through the visualization interface can also be obtained, and the configuration information includes at least one of the following items: the task type of the current execution progress information to be displayed, the reminder threshold of different tasks, and the dimension of the data to be displayed. The reminder threshold includes the threshold corresponding to the early warning reminder message and the threshold corresponding to the level adjustment reminder message. This allows users to customize reminders and prediction parameters according to personal needs in the system's settings panel. For example, users can choose the task type of interest, set the reminder threshold of different tasks, select the data dimension to be displayed, etc., to adapt to different application scenarios.

[0077] In some embodiments, the workflow prediction model includes a sub-prediction model for each task, and the related data includes task execution information, user operation log, and current environment information of each task.

[0078] The step of inputting relevant data into the workflow prediction model and obtaining the warning information output by the workflow prediction model includes the following steps:

[0079] Step S121: Input the task execution information, user operation log, and current environment information of each task into the sub-prediction model corresponding to the task, and obtain the sub-warning information for each task output by the sub-prediction model.

[0080] Step S122: based on the multiple warning sub-information corresponding to the multiple tasks, obtain warning information for the workflow system.

[0081] In this way, the multi-model integration technology is used to fine-tune the dedicated models of the integrated sub-tasks, and the prediction results of multiple models are integrated to generate the final prediction value. This hybrid architecture combines the generative large model with the dedicated small model, which is mainly used in specific sub-task areas, reduces the use of general models, and can adjust the sub-prediction model through fine-tuning technology to improve model efficiency.

[0082] The present application provides a monitoring method for a workflow system, which can output warning information based on relevant data obtained in real time during the execution of tasks by the workflow system, thereby achieving efficient risk management of the workflow, and providing corresponding solutions and their scores while providing warning information, which can effectively provide a basis for decision-making and improve the efficiency of problem solving. The warning reminder information is output in multiple ways to facilitate users to respond quickly, and a visualization page is provided for users. On the one hand, it can conveniently display production progress, prediction results, and resource allocation to reflect changes in real-time data. On the other hand, users can input configuration information through the visualization page and customize reminders and prediction parameters according to personal needs to adapt to different application scenarios.

[0083] Embodiment 2

[0084] Based on the above embodiments, Figure 2 A flowchart of a method for training a workflow prediction model according to an embodiment of the present application is shown, and the method includes:

[0085] Step 210: Obtain sample data and its real warning information. The sample data includes sample-related data in the process of the workflow system executing the sample task. The sample-related data includes task execution information, user operation logs, and current environment information.

[0086] Step 220: Input the sample-related data into the workflow prediction model, and obtain the prediction warning information output by the workflow prediction model.

[0087] Step 230: Adjust the parameters of the workflow prediction model based on the real warning information and the predicted warning information.

[0088] In the embodiment of the present application, it is possible to perform tuning training in a specific field of the workflow system based on a pre-trained large model. Furthermore, the workflow prediction model includes a sub-prediction model for each task, and it is possible to fine-tune the sub-prediction model for each task, integrate the prediction results of multiple models, and generate the final prediction value.

[0089] In the embodiments of the present application, the sample data may be historical data obtained through IoT devices and smart phones. The task execution information in the sample-related data includes but is not limited to the task name, type, task allocation, execution progress, execution time, historical execution time, and resource inventory; the user operation log includes but is not limited to the task type, execution progress, operator, operation time, equipment adjustment parameters, quality inspection information, abnormal conditions, and resource inventory; the current environment information includes but is not limited to weather forecasts and market trends.

[0090] The real warning information is the historical data recorded in the workflow system, and the predicted warning information is the predicted data generated according to the workflow prediction model. The parameters of the workflow prediction model are adjusted according to the real warning data and the predicted warning information, which enables it to understand the time model, resource consumption pattern and potential risks of different tasks. The model performance is evaluated through cross-validation, confusion matrix, etc., and the parameters are repeatedly optimized to ensure the prediction accuracy.

[0091] In the embodiments of the present application, the model training method may be to use a deep learning framework, such as TensorFlow, PyTorch, etc., wherein the TensorFlow production environment is stable, and PyTorch is easier to debug and develop. The training strategy may be to use distributed training or federated learning, wherein distributed training can accelerate the model training speed.

[0092] A monitoring method for a workflow system provided in an embodiment of the present application can train a workflow prediction model in combination with sample data, real warning information and predicted warning information. Through adaptive learning and optimization, the workflow prediction model can dynamically adjust and optimize the workflow according to real-time data feedback, thereby further improving the flexibility and robustness of the system.

[0093] Embodiment 3

[0094] Based on the above embodiments, Figure 3 A schematic diagram of the structure of a monitoring device 300 for a workflow system according to an embodiment of the present application is shown. The device 300 includes:

[0095] The first acquisition module 301 is configured to acquire relevant data in the process of executing tasks in the workflow system in real time, wherein the relevant data includes task execution information, user operation logs, and current environment information;

[0096] The second acquisition module 302 is configured to input the relevant data into the workflow prediction model and acquire the warning information output by the workflow prediction model.

[0097] In some embodiments, it also includes: a storage module, configured to store the relevant data acquired in real time into an edge device, and the relevant data is used to update and train the workflow prediction model.

[0098] In some embodiments, the output of the workflow prediction model also includes a solution corresponding to the early warning information and a score thereof, wherein the score is used to indicate the probability that the solution can resolve the risk in the early warning information.

[0099] In some embodiments, it also includes:

[0100] A first message generating module is configured to generate a warning reminder message based on the warning information;

[0101] The first output module is configured to output the warning reminder message via at least one of email, text message, instant messaging and application notification.

[0102] In some embodiments, the first message generation module is configured to generate a warning reminder message based on the warning information by following the steps below:

[0103] The warning reminder message is generated based on preset rules and the warning information.

[0104] In some embodiments, the warning information includes risk data and a task identifier for which the risk data is targeted, and the warning reminder message includes a deadline for the task for which the warning information is targeted; the preset rule includes whether the interval between the current time and the deadline of the task is less than a preset duration;

[0105] The first message generation module is configured to generate the warning reminder message based on the preset rules and the warning information through the following steps:

[0106] In response to determining that the interval between the current time and the deadline of the task is less than a preset duration;

[0107] The early warning reminder message is generated based on the early warning information.

[0108] In some embodiments, it also includes:

[0109] A fifth acquisition module is configured to acquire the deadline of the current task, the usage of system resources and the execution progress information of the historical tasks;

[0110] An adjustment module, configured to adjust the priority of the current task based on the deadline of the current task, the usage of system resources and the execution progress information of the historical tasks;

[0111] A level adjustment module, configured to generate a level adjustment reminder message based on the priority of the current task;

[0112] The second output module is configured to output the level adjustment reminder message through at least one of email, text message, instant messaging and application notification, so that relevant personnel can perform resource allocation.

[0113] In some embodiments, it also includes:

[0114] The display module is configured to display at least one of the current execution progress information, warning information and current resource allocation information of the task through a visual interface.

[0115] In some embodiments, it also includes:

[0116] The sixth acquisition module is configured to obtain configuration information input by the user through the visualization interface, and the configuration information includes at least one of the following items: the task type for which the current execution progress information is to be displayed, the reminder thresholds of different tasks, and the dimensions of the data to be displayed, and the reminder thresholds include the thresholds corresponding to the early warning reminder messages and the thresholds corresponding to the level adjustment reminder messages.

[0117] In some embodiments, the workflow prediction model includes a sub-prediction model for each task, and the relevant data includes task execution information, user operation log, and current environment information for each task;

[0118] The second acquisition module is configured to input the relevant data into the workflow prediction model and acquire the warning information output by the workflow prediction model through the following steps:

[0119] Inputting the task execution information, user operation log, and current environment information of each task into the sub-prediction model corresponding to the task, and obtaining the sub-warning information for each task output by the sub-prediction model;

[0120] Based on the multiple warning sub-information corresponding to the multiple tasks, warning information for the workflow system is obtained.

[0121] Embodiment 4

[0122] Based on the above embodiments, Figure 4 A schematic diagram of the structure of a training device 400 for a workflow prediction model according to an embodiment of the present application is shown, and the device 400 includes:

[0123] The third acquisition module 401 is configured to acquire sample data and real warning information thereof, wherein the sample data includes sample-related data during the execution of sample tasks by the workflow system, and the sample-related data includes task execution information, user operation logs, and current environment information;

[0124] The fourth acquisition module 402 is configured to input the sample-related data into the workflow prediction model and obtain the prediction warning information output by the workflow prediction model;

[0125] The parameter adjustment module 403 is configured to adjust the parameters of the workflow prediction model based on the real warning information and the predicted warning information.

[0126] Embodiment 5

[0127] On the basis of the above embodiments, this embodiment provides an electronic device, including a memory and at least one processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in the above embodiments.

[0128] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0129] In some implementations of this embodiment, a computer program product is provided, including a computer program / instructions, and when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0130] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the method in the above embodiments.

[0131] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof. The computer-readable storage medium may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (such as hard disks, floppy disks, solid-state drives, removable disks, Blu-ray Disc, etc.).

[0132] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0133] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0134] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

[0135] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0136] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes 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 box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0137] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0138] Although the embodiments disclosed in the present disclosure are as above, the above contents are only embodiments adopted for facilitating the understanding of the present disclosure and are not intended to limit the present disclosure. Any technician in the technical field to which the present disclosure belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the scope of patent protection of the present disclosure shall still be subject to the scope defined in the attached claims.

Claims

1. A monitoring method for a workflow system, wherein the workflow system is used to execute multiple tasks, characterized in that: The monitoring method comprises: Real-time acquisition of relevant data during the execution of tasks by the workflow system, including task execution information, user operation logs, and current environment information; The relevant data is input into a workflow prediction model, and warning information output by the workflow prediction model is obtained, where the warning information is used to indicate risks existing in the process of executing tasks by the workflow system.

2. The monitoring method according to claim 1, characterized in that: Also includes: The relevant data acquired in real time is stored in the edge device, and the relevant data is used to update and train the workflow prediction model.

3. The monitoring method according to claim 1, characterized in that: The output of the workflow prediction model also includes the solution corresponding to the early warning information and its score, where the score is used to indicate the probability that the solution can resolve the risk in the early warning information.

4. The monitoring method according to claim 1, characterized in that: Also includes: Generate a warning reminder message based on the warning information; The warning reminder message is outputted via at least one of email, text message, instant messaging and application notification.

5. The monitoring method according to claim 4, characterized in that: Generating an early warning reminder message based on the prediction information includes: The warning reminder message is generated based on preset rules and the warning information.

6. The monitoring method according to claim 5, characterized in that: The warning information includes risk data and a task identifier to which the risk data relates, and the warning reminder message includes a deadline for the task to which the warning information relates; The preset rules include whether the interval between the current time and the deadline of the task is less than the preset duration; Generating the warning reminder message based on the preset rules and the warning information includes: In response to determining that the interval between the current time and the deadline of the task is less than a preset duration; The early warning reminder message is generated based on the early warning information.

7. The monitoring method according to any one of claims 1 to 6, characterized in that: Also includes: Get the deadline of the current task, the usage of system resources and the execution progress information of historical tasks; Adjusting the priority of the current task based on the deadline of the current task, the usage of system resources and the execution progress information of historical tasks; Generate a priority adjustment reminder message based on the priority of the current task; The level adjustment reminder message is outputted through at least one of email, text message, instant messaging and application notification, so that relevant personnel can perform resource allocation.

8. The monitoring method according to claim 7, characterized in that: Also includes: At least one of the current execution progress information, warning information and current resource allocation information of the task is displayed through a visual interface.

9. The monitoring method according to any one of claims 1 to 6, characterized in that: Also includes: Obtain configuration information input by the user through the visualization interface, wherein the configuration information includes at least one of the following items: the task type for which the current execution progress information is to be displayed, the reminder thresholds of different tasks, and the dimensions of the data to be displayed, wherein the reminder thresholds include the thresholds corresponding to the early warning reminder message and the thresholds corresponding to the level adjustment reminder message.

10. The monitoring method according to any one of claims 1 to 6, characterized in that: The workflow prediction model includes a sub-prediction model for each task, and the related data includes task execution information, user operation log, and current environment information of each task; The step of inputting the relevant data into a workflow prediction model and obtaining the warning information output by the workflow prediction model includes: Inputting the task execution information, user operation log, and current environment information of each task into the sub-prediction model corresponding to the task, and obtaining the sub-warning information for each task output by the sub-prediction model; Based on the multiple warning sub-information corresponding to the multiple tasks, warning information for the workflow system is obtained.

11. A method for training a workflow prediction model, characterized in that: include: Acquire sample data and real warning information thereof, wherein the sample data includes sample-related data during the process of the workflow system executing sample tasks, and the sample-related data includes task execution information, user operation logs, and current environment information; Inputting the sample-related data into a workflow prediction model, and obtaining prediction and warning information output by the workflow prediction model; The parameters of the workflow prediction model are adjusted based on the real warning information and the predicted warning information.

12. A monitoring device for a workflow system, wherein the workflow system is used to execute multiple tasks, characterized in that: The monitoring device comprises: A first acquisition module is configured to acquire relevant data in the process of executing tasks in the workflow system in real time, wherein the relevant data includes task execution information, user operation logs, and current environment information; The second acquisition module is configured to input the relevant data into the workflow prediction model and acquire the warning information output by the workflow prediction model.

13. A training device for a workflow prediction model, characterized in that: include: A third acquisition module is configured to acquire sample data and real warning information thereof, wherein the sample data includes sample-related data during the execution of a sample task by the workflow system, and the sample-related data includes task execution information, user operation logs, and current environment information; A fourth acquisition module is configured to input the sample-related data into a workflow prediction model and acquire prediction and warning information output by the workflow prediction model; A parameter adjustment module is configured to adjust the parameters of the workflow prediction model based on the real warning information and the predicted warning information.

14. An electronic device, characterized in that: include: Memory; At least one processor, the memory stores a computer program, and the computer program can be executed by the at least one processor to implement the method according to any one of claims 1 to 11.

15. A non-transitory computer-readable storage medium storing a computer program, wherein: The computer program is used to make a computer execute the method according to any one of claims 1 to 11.

Images