Abnormality processing system and method based on artificial intelligence

Abstract

The invention discloses an exception handling system and method based on artificial intelligence, relates to the technical field of information, and solves the technical problem that the efficiency of exception recognition and exception handling systems is relatively low due to poor task execution efficiency caused by automatic execution of background tasks in case of neglecting executing tasks in the prior art. A task state is generated according to task data and task parameters; generating a task state resource occupation coefficient according to the task state and the task parameter; generating an alarm signal according to the task state resource occupancy coefficient; generating a processing suggestion according to the alarm signal and the task data; the corresponding task data is processed through the processing suggestion, the processing feedback signal is generated according to the processing result, the occupied resources of the same task in different states are calculated, the reasonable range of the occupied resources is dynamically adjusted, the abnormal state of each task can be recognized more accurately, and the targeted processing suggestion is given. And the processing efficiency of the intelligent exception processing system is improved.

Description

Technical Field

[0001] The present application belongs to the field of information technology, and specifically is an exception handling system and method based on artificial intelligence. Background Art

[0002] Exception handling is a mechanism in programming languages ​​or computer hardware that is used to handle abnormal conditions in software or information systems, that is, certain special conditions that exceed the normal execution flow of the program. Exception handling is an indispensable part of programming. It can not only improve the robustness and security of the program, but also make the program easier to maintain and debug.

[0003] With the rapid development of cloud computing and big data technology, data centers are carrying more and more business applications, and their operation and maintenance complexity is also increasing. Traditional exception handling relies on manual intervention, which is not only inefficient but also prone to errors, and it is difficult to meet the needs of efficient and automated operation and maintenance. With the development of automation, automatic exception handling systems have also emerged. Existing technologies ignore the resource occupation caused by the automatic execution of background tasks, which makes the tasks being executed often have poor task execution efficiency due to the automatic execution of background tasks, thereby making the exception identification and exception handling system less efficient. For example, when a mobile phone is used to perform work tasks, the automatic execution of a certain task in the background causes insufficient memory resources for the execution of the work tasks, causing the work tasks to become stuck. At this time, the exception handling system cannot accurately identify the cause of the exception, making the exception handling system less efficient; therefore, further improvements are still needed for the exception handling system. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes an exception handling system and method based on artificial intelligence, which is used to solve the technical problem that the prior art ignores the resource occupation caused by the automatic execution of background tasks, so that the tasks being executed are often inefficient due to the automatic execution of background tasks, thereby resulting in low efficiency of exception identification and exception handling systems.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides an artificial intelligence-based exception handling system, comprising: a data acquisition module, a data analysis module, an early warning module and a database;

[0006] The data acquisition module is used to acquire task data and task parameters through data acquisition equipment;

[0007] The data analysis module generates a task state according to task data and task parameters; generates a task state resource occupancy coefficient according to the task state and task parameters; generates an alarm signal according to the task state resource occupancy coefficient; generates a processing suggestion according to the alarm signal and task data; processes the corresponding task data according to the processing suggestion, and generates a processing feedback signal according to the processing result;

[0008] The early warning module makes prompts according to the alarm signal and feedback signal and contacts the management personnel.

[0009] Through the above steps, the present application calculates the occupied resources of different task items under different task states respectively, compares them with the corresponding adaptive reasonable resource range to determine whether there is an abnormal situation, accurately identifies the abnormal state of the task item, and uses the pre-trained suggestion generation model to give targeted processing suggestions for the abnormal state and provide feedback, thereby improving the accuracy of exception identification and the processing efficiency of the intelligent exception handling system.

[0010] Further, generating the task status according to the task data and the task parameters includes:

[0011] Obtaining several task items and their corresponding task parameters in the task data;

[0012] Several task items and their corresponding task parameters are input into a state evaluation model to obtain a task state label; the state evaluation model is constructed through an artificial intelligence model.

[0013] Furthermore, the state assessment model is constructed by an artificial intelligence model, including:

[0014] Get several historical task items, corresponding task parameters and task status labels;

[0015] Divide several historical task items, corresponding task parameters and task status labels into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;

[0016] Select an AI model as the base model;

[0017] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0018] By verifying the pre-trained model on the test set, we finally obtain a state assessment model whose input is task items and task parameters and whose output is task state labels.

[0019] Further, generating the task status resource occupancy coefficient according to the task status and task parameters includes:

[0020] Extracting resource data from several task items and their corresponding task states and task parameters in the task data;

[0021] By formula Calculate the resource occupancy coefficients RZXi of several task states; where αij represents the weight coefficient, αij∈(0,1); ZDij represents the size of the jth resource space occupied by the i-th task; and ZZDj represents the total size of the j-th resource space.

[0022] This application performs status analysis on task items through the above steps. The same tasks in different states will have great deviations in resource occupancy. The resource occupancy is quantified by the proportion of task items in several resource spaces to calculate the task status resource occupancy coefficient, providing strong data support for identifying abnormal situations.

[0023] Further, the generating of an alarm signal according to the task status resource occupancy coefficient includes:

[0024] Obtain the task status and task status resource occupancy coefficient corresponding to several task items;

[0025] Determine whether the task status resource occupancy coefficient corresponding to the task item under the same task status is within its corresponding coefficient range; the coefficient range is obtained through the historical task status resource occupancy coefficient;

[0026] Yes, do nothing;

[0027] No, an abnormal task project resource usage alert signal is generated.

[0028] Furthermore, the coefficient range is obtained through the resource occupancy coefficient of the historical task status, including:

[0029] Get the resource occupancy coefficients RZXkm of several historical task states under each task state when the task project is in normal condition;

[0030] By formula Calculate the average coefficient PRZXk under each state;

[0031] By formula Calculate the coefficient standard deviation XBCk in each state; where k represents the number of the task state, m represents the number of the resource occupancy coefficient of the historical task state, and max{} represents the maximum value;

[0032] The coefficient range of the task item under each task state is XFk∈(PRZXk-A×XBCk, PRZXk+A×XBCk); where A is the proportional coefficient, A>0.

[0033] Further, generating a processing suggestion according to the alarm signal and the task data includes:

[0034] Obtaining task data, task status, and task item resource occupancy abnormality alarm signals in the alarm signals;

[0035] The task data, the task status and the task item resource occupancy abnormality alarm signal in the alarm signal are input into a suggestion generation model to obtain a processing suggestion; the suggestion generation model is constructed by a large language model.

[0036] Furthermore, the suggestion generation model is constructed by a large language model, including:

[0037] Obtain some historical task data, task status, and abnormal alarm signals of task project resource usage and their corresponding processing suggestions;

[0038] Divide a number of historical task data, task status, and abnormal alarm signals of task project resource usage and their corresponding processing suggestions into training data, verification data, and test data; perform data preprocessing on the training data, verification data, and test data to obtain a training set, a verification set, and a test set;

[0039] Select a large language model as the base model;

[0040] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0041] By verifying the pre-trained model on the test set, we finally obtain a suggestion generation model whose input is task data, task status and abnormal alarm signal of task item resource occupancy, and whose output is processing suggestions.

[0042] Further, generating a processing feedback signal according to the processing result includes:

[0043] Obtain the resource occupancy coefficient of the processed task status and its corresponding coefficient range;

[0044] Determine whether the task status resource occupancy coefficient is within the coefficient range; if yes, generate a processing suggestion useful signal; if no, generate a processing suggestion useless alarm signal.

[0045] Another aspect of the present invention provides an exception handling method based on artificial intelligence, comprising:

[0046] S0: Get task data and task parameters;

[0047] S1: Generate task status according to task data and task parameters; generate task status resource occupancy coefficient according to task status and task parameters;

[0048] S2: Generate an alarm signal according to the resource occupancy coefficient of the task status; generate processing suggestions according to the alarm signal and task data;

[0049] S3: Process the corresponding task data through the processing suggestions, and generate a processing feedback signal according to the processing results;

[0050] S4: Provide prompts based on alarm signals and feedback signals and contact management personnel.

[0051] Compared with the prior art, the beneficial effects of this application are:

[0052] 1. The present application generates a task status according to task data and task parameters; generates a task status resource occupancy coefficient according to the task status and task parameters; generates an alarm signal according to the task status resource occupancy coefficient; generates a processing suggestion according to the alarm signal and the task data; processes the corresponding task data according to the processing suggestion, generates a processing feedback signal according to the processing result, calculates the occupied resources under different states of the same task, and dynamically adjusts the reasonable range of its occupied resources, so as to more accurately identify the abnormal state of each task, give targeted processing suggestions and feedback, and improve the processing efficiency of the intelligent exception handling system.

[0053] 2. This application analyzes the status of task items. The same tasks in different states will have great deviations in resource occupancy. By quantifying the resource occupancy, the task status resource occupancy coefficient of each state under each task item is calculated, which provides strong support for identifying abnormal situations and improves the accuracy of task item abnormality identification.

[0054] 3. This application dynamically calculates the coefficient range of resource occupancy coefficients of several historical task states under each task state when the task project is in normal conditions, and sets the coefficient range under normal conditions for each task state of each task project, so that each task project has its own coefficient range for measuring abnormal conditions, thereby improving the accuracy of task anomaly identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] 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, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 This is a schematic diagram of the principle of an exception handling system based on artificial intelligence in this application;

[0057] Figure 2Generate a flow chart for processing feedback signals for this application;

[0058] Figure 3 This is a flow chart of an exception handling method based on artificial intelligence in this application. DETAILED DESCRIPTION

[0059] The technical solution of the present application will be described clearly and completely below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0060] See also Figure 1 , the first aspect of the present application provides an artificial intelligence-based exception handling system, including: a data acquisition module, a data analysis module, an early warning module and a database;

[0061] Data acquisition module: obtains task data and task parameters through data acquisition equipment; data acquisition equipment includes various sensors, etc.; task data includes task number and task item, etc.; task parameters include parameter information generated when the task item is running, such as resource data, etc.;

[0062] Data analysis module: Generate task status based on task data and task parameters, including execution status and background status, etc.; Generate task status resource occupancy coefficient based on task status and task parameters, which refers to the degree of resources occupied by task items under the current task status; Generate alarm signals based on task status resource occupancy coefficient; Generate processing suggestions based on alarm signals and task data; Process corresponding task data through processing suggestions, and generate processing feedback signals based on processing results, which are evaluations of processing suggestions;

[0063] Early warning module: Prompts are given based on alarm signals and feedback signals, and management personnel are contacted. Alarm signals include alarm signals indicating abnormal resource usage of task projects, and feedback signals include alarm signals indicating useful processing suggestions and alarm signals indicating useless processing suggestions.

[0064] In this embodiment, the task status is generated according to the task data and the task parameters, including:

[0065] Obtaining several task items and their corresponding task parameters in the task data;

[0066] Several task items and their corresponding task parameters are input into the state assessment model to obtain the task state label; the state assessment model is constructed through an artificial intelligence model.

[0067] The state assessment model in this embodiment is constructed by an artificial intelligence model, including:

[0068] Get several historical task items, corresponding task parameters and task status labels;

[0069] Divide several historical task items, corresponding task parameters and task status labels into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain training set, verification set and test set; the ratio between the training set, test set and verification set is 7:2:1;

[0070] Select an artificial intelligence model as a basic model; the artificial intelligence model includes a convolutional neural network model, etc.; in this embodiment, what is needed is to classify the states corresponding to the task items, and the convolutional neural network model has a better classification evaluation effect, and the result obtained by this model is also more accurate;

[0071] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0072] By verifying the pre-trained model on the test set, we finally obtain a state assessment model whose input is task items and task parameters and whose output is task state labels.

[0073] In this embodiment, the task status resource occupancy coefficient is generated according to the task status and task parameters, including:

[0074] Extract several task items in the task data and their corresponding task status and resource data in the task parameters; resource data includes CPU resource occupancy, memory resource occupancy, etc.;

[0075] By formula Calculate several task status resource occupancy coefficients RZXi; where αij is represented as the weight coefficient, αij∈(0, 1), and the specific value is set based on experience; ZDij represents the size of the jth resource space occupied by the ith task; ZZDj represents the total size of the jth resource space; the higher the proportion of the current task item in any resource data, the more resources the task item occupies; therefore, the task status resource occupancy coefficient will increase accordingly.

[0076] This embodiment performs status analysis on task items. The same tasks in different states may have large deviations in resource occupancy. By quantifying the resource occupancy, the task status resource occupancy coefficient of each state under each task item is calculated, which provides strong support for identifying abnormal situations and improves the accuracy of task item abnormality identification.

[0077] In this embodiment, generating an alarm signal according to the task status resource occupancy coefficient includes:

[0078] Obtain the task status and task status resource occupancy coefficient corresponding to several task items;

[0079] Determine whether the task status resource occupancy coefficient corresponding to the task item under the same task status is within its corresponding coefficient range; the coefficient range is obtained through the historical task status resource occupancy coefficient;

[0080] Yes, do nothing;

[0081] No, an abnormal task project resource usage alert signal is generated.

[0082] It is worth noting that the abnormal state of a task has no direct correlation with the size of the task state resource occupancy coefficient, but is directly related to the coefficient range under its corresponding task state; if the task state resource occupancy coefficient is not within the coefficient range under its corresponding task state, the task item is judged to be in an abnormal state.

[0083] The coefficient range in this embodiment is obtained by the resource occupancy coefficient of the historical task status, including:

[0084] Get the resource occupancy coefficients RZXkm of several historical task states under each task state when the task project is in normal condition;

[0085] By formula Calculate the average coefficient PRZXk in each state; the higher the resource occupancy coefficient of the historical task state, the higher the corresponding average coefficient will be

[0086] By formula Calculate the coefficient standard deviation XBCk in each state; where k represents the number of the task state, m represents the number of the resource occupancy coefficient of the historical task state in the current task project, and max{} represents the maximum value; the coefficient standard deviation measures the fluctuation of the resource occupancy coefficient of several historical task states. The larger the coefficient standard deviation, the greater the fluctuation of the resource occupancy coefficient of several historical task states.

[0087] The coefficient range XFk∈(PRZXk-A×XBCk, PRZXk+A×XBCk) under each task state of the task project; wherein, A is the proportional coefficient, A>0, the specific value of A is set according to experience, and in this embodiment, A is set to 2; it is worth noting that the coefficient range in this embodiment is divided based on the normal distribution of the resource occupancy coefficients of several historical task states; if the fluctuation of the resource occupancy coefficients of several historical task states is small, then the corresponding coefficient range will be smaller.

[0088] This embodiment dynamically calculates the coefficient range through the above steps, and sets the coefficient range under normal circumstances for each task item and each task state, thereby avoiding the problem of low abnormality accuracy caused by using the same coefficient range to judge abnormal situations in different task items and different task states, thereby greatly improving the accuracy of abnormality recognition for each task.

[0089] In this embodiment, generating a processing suggestion according to the alarm signal and the task data includes:

[0090] Obtaining task data, task status, and task item resource occupancy abnormality alarm signals in the alarm signals;

[0091] The task data, task status and task item resource usage abnormal alarm signal in the alarm signal are input into the suggestion generation model to obtain processing suggestions; the suggestion generation model is constructed through a large language model, and the abnormal processing suggestions for the corresponding task items are generated in the pre-trained large language model. It has high accuracy and automation, reduces the time required for manual search for information and giving suggestions, and greatly improves the efficiency of abnormal processing of task items.

[0092] The suggestion generation model in this embodiment is constructed by a large language model, including:

[0093] Obtain some historical task data, task status, and abnormal alarm signals of task project resource usage and their corresponding processing suggestions;

[0094] Several historical task data, task status, and abnormal alarm signals of task project resource usage and their corresponding processing suggestions are divided into training data, verification data, and test data; data preprocessing is performed on the training data, verification data, and test data to obtain training sets, verification sets, and test sets; the ratio between the training set, the test set, and the verification set is 7:2:1;

[0095] Select a large language model as the basic model; large language models include T5 models, etc.

[0096] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0097] By verifying the pre-trained model on the test set, we finally obtain a suggestion generation model whose input is task data, task status and abnormal alarm signal of task item resource occupancy, and whose output is processing suggestions.

[0098] See also Figure 2 , in this embodiment, generating a processing feedback signal according to the processing result includes:

[0099] Obtain the resource occupancy coefficient of the processed task status and its corresponding coefficient range;

[0100] Determine whether the task status resource occupancy coefficient is within the coefficient range; if so, generate a processing suggestion useful signal; if not, generate a processing suggestion useless alarm signal.

[0101] This embodiment uses a large model to make targeted processing suggestions for each abnormal task item, and feedbacks the processing effect after using the processing suggestions. When the processing suggestions do not meet the target requirements, timely and effective feedback is provided, which greatly improves the efficiency of the intelligent exception handling system.

[0102] See also Figure 3 Another aspect of the present application provides an artificial intelligence-based exception handling method, comprising:

[0103] S0: Get task data and task parameters;

[0104] S1: Generate task status according to task data and task parameters; generate task status resource occupancy coefficient according to task status and task parameters;

[0105] S2: Generate an alarm signal according to the resource occupancy coefficient of the task status; generate processing suggestions according to the alarm signal and task data;

[0106] S3: Process the corresponding task data through the processing suggestions, and generate a processing feedback signal according to the processing results;

[0107] S4: Provide prompts based on alarm signals and feedback signals and contact management personnel.

[0108] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0109] The working principle of the present application is as follows: by acquiring task data and task parameters; generating task status according to task data and task parameters; generating task status resource occupancy coefficient according to task status and task parameters; generating alarm signals according to task status resource occupancy coefficient; generating processing suggestions according to alarm signals and task data; processing corresponding task data through processing suggestions, and generating processing feedback signals according to processing results; making prompts according to alarm signals and feedback signals, and contacting management personnel, calculating occupied resources under different states of the same task, and dynamically adjusting the reasonable range of occupied resources, so as to more accurately identify the abnormal states of each task, give targeted processing suggestions and feedback, improve the processing efficiency of the intelligent exception handling system, and avoid the problem that the prior art ignores the resource occupancy caused by the automatic execution of background tasks, so that the tasks being executed are often inefficient due to the automatic execution of background tasks, thereby causing the problem of low efficiency of exception identification and exception handling systems.

[0110] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. An exception handling system based on artificial intelligence, characterized in that: include: Data collection module, data analysis module, early warning module and database; The data acquisition module is used to acquire task data and task parameters through data acquisition equipment; The data analysis module generates a task status according to the task data and task parameters; generates a task status resource occupancy coefficient according to the task status and task parameters; Generate an alarm signal based on the resource occupancy coefficient of the task status; generate processing suggestions based on the alarm signal and task data; Processing the corresponding task data through processing suggestions, and generating processing feedback signals according to the processing results; The early warning module makes prompts according to the alarm signal and feedback signal and contacts the management personnel.

2. The artificial intelligence-based exception handling system according to claim 1, characterized in that: The generating of the task status according to the task data and the task parameters includes: Obtaining several task items and their corresponding task parameters in the task data; Several task items and their corresponding task parameters are input into a state evaluation model to obtain a task state label; the state evaluation model is constructed through an artificial intelligence model.

3. The artificial intelligence-based exception handling system according to claim 2, characterized in that: The state assessment model is constructed through an artificial intelligence model, including: Get several historical task items, corresponding task parameters and task status labels; Divide several historical task items, corresponding task parameters and task status labels into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtain a state assessment model whose input is task items and task parameters and whose output is task state labels.

4. The artificial intelligence-based exception handling system according to claim 1, characterized in that: The generating of the task status resource occupancy coefficient according to the task status and the task parameters includes: Extracting resource data from several task items and their corresponding task states and task parameters in the task data; By formula Calculate the resource occupancy coefficients RZXi of several task states; where αij represents the weight coefficient, αij∈(0,1); ZDij represents the size of the jth resource space occupied by the i-th task; and ZZDj represents the total size of the j-th resource space.

5. The artificial intelligence-based exception handling system according to claim 1, characterized in that: The generating of an alarm signal according to the task status resource occupancy coefficient comprises: Obtain the task status and task status resource occupancy coefficient corresponding to several task items; Determine whether the task status resource occupancy coefficient corresponding to the task item under the same task status is within its corresponding coefficient range; the coefficient range is obtained through the historical task status resource occupancy coefficient; Yes, do nothing; No, an abnormal task project resource usage alert signal is generated.

6. The artificial intelligence-based exception handling system according to claim 5, characterized in that: The coefficient range is obtained through the resource occupancy coefficient of the historical task status, including: Get the resource occupancy coefficients RZXkm of several historical task states under each task state when the task project is in normal condition; By formula Calculate the average coefficient PRZXk under each state; By formula Calculate the coefficient standard deviation XBCk in each state; where k represents the number of the task state, m represents the number of the resource occupancy coefficient of the historical task state, and max{} represents the maximum value; The coefficient range of the task item under each task state is XFk∈(PRZXk-A×XBCk, PRZXk+A×XBCk); where A is the proportional coefficient, A>0.

7. The artificial intelligence-based exception handling system according to claim 1, characterized in that: The generating of processing suggestions according to the alarm signal and the task data comprises: Obtain task item resource occupancy abnormality alarm signals in task data, task status and alarm signals; The task data, the task status and the task item resource occupancy abnormality alarm signal in the alarm signal are input into a suggestion generation model to obtain a processing suggestion; the suggestion generation model is constructed by a large language model.

8. The artificial intelligence-based exception handling system according to claim 7, characterized in that: The suggestion generation model is constructed through a large language model, including: Obtain some historical task data, task status, and abnormal alarm signals of task project resource usage and their corresponding processing suggestions; Divide a number of historical task data, task status, and abnormal alarm signals of task project resource occupancy and their corresponding processing suggestions into training data, verification data, and test data; perform data preprocessing on the training data, verification data, and test data to obtain a training set, a verification set, and a test set; Select a large language model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtain a suggestion generation model whose input is task data, task status and abnormal alarm signal of task item resource occupancy, and whose output is processing suggestions.

9. The artificial intelligence-based exception handling system according to claim 1, characterized in that: The step of generating a processing feedback signal according to the processing result includes: Obtain the resource occupancy coefficient of the processed task status and its corresponding coefficient range; Determine whether the task status resource occupancy coefficient is within the coefficient range; Yes, generate processing suggestion useful signal; No, generate a processing suggestion useless alert signal.

10. An artificial intelligence-based exception handling method, applied to an artificial intelligence-based exception handling system according to any one of claims 1 to 9, characterized in that: include: S0: Get task data and task parameters; S1: Generate task status based on task data and task parameters; Generate a task status resource occupancy coefficient according to the task status and task parameters; S2: Generate an alarm signal according to the resource occupancy coefficient of the task status; generate processing suggestions according to the alarm signal and task data; S3: Process the corresponding task data through the processing suggestions, and generate a processing feedback signal according to the processing results; S4: Provide prompts based on alarm signals and feedback signals and contact management personnel.

Images