DICT operation and maintenance notification method and device, terminal equipment and storage medium

Abstract

The invention discloses a DICT operation and maintenance notification method and device, terminal equipment and a storage medium, and the method is realized based on a DICT operation and maintenance notification system, and comprises the following steps: equipment classification and management: collecting information about equipment performance parameters from various sensors; processing the collected data by using a machine learning algorithm, and extracting key features; dividing the equipment into different groups according to feature similarity; staff classification and management: classifying and scoring professional skills of the staff; tracking and recording various item experiences completed by each person; classification and scoring are performed in combination with professional skills, and comprehensive rating is given to each worker through personal experience; according to the method, key features can be automatically extracted, intelligent matching of tasks and maintenance personnel is realized, and the matching precision and efficiency are improved; the load condition of each person is calculated according to the current task number and the predicted completion time of each person, corresponding adjustment is made accordingly, and resource waste and excessive load are avoided.

Description

Technical Field

[0001] The present invention relates to the field of DICT operation and maintenance technology, and in particular to a DICT operation and maintenance notification method, device, terminal equipment and storage medium. Background Art

[0002] With the development of information technology, more and more enterprises and organizations have begun to adopt cloud computing services to manage and monitor their IT infrastructure. However, in the face of increasingly complex network environments and growing amounts of data, traditional operation and maintenance models can no longer meet the needs of modern enterprises.

[0003] For example, when allocating maintenance tasks, traditional operation and maintenance systems cannot make targeted allocations based on the actual capabilities of maintenance personnel; or in the process of allocating tasks, too many maintenance personnel may be assigned to the same maintenance personnel, resulting in a heavy workload, etc.

[0004] To this end, the present invention proposes a DICT operation and maintenance notification method, apparatus, terminal device and storage medium. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides a DICT operation and maintenance notification method, which is implemented based on the DICT operation and maintenance notification system and includes the following steps:

[0006] S1: Equipment classification and management, collect information about equipment performance parameters from various sensors; use machine learning algorithms to process the collected data and extract key features; classify equipment into different groups based on feature similarity;

[0007] S2: Staff classification and management: classify and rate the professional skills of staff; track and record the various project experiences completed by each person; give each staff member a comprehensive rating based on the classification and rating of professional skills and personal experience;

[0008] S3: Forecasting headcount demand and making resource allocation recommendations. Analyze the frequency of various types of failures and the time required to resolve them within a set historical period; use statistical methods to make reasonable estimates of possible problems in the future; and propose reasonable human resource allocation plans based on the above analysis results.

[0009] S4: Real-time monitoring and task generation: Check the working status of all networked devices in real time; trigger an alarm immediately when any deviation from the normal range is found, and generate maintenance tasks;

[0010] S5: Priority adjustment: determine a fixed time interval for calculating the workload of each staff member; set a threshold, and when the threshold is exceeded, reduce the matching priority of the staff member; as new maintenance tasks are completed, update the workload information of each staff member in real time and make adjustments accordingly;

[0011] S6: Intelligent matching and notification, based on the classification, scoring, comprehensive rating of the staff's professional skills, and the current matching priority; quickly screening out the list of qualified staff according to the established logic; and promptly informing relevant staff of the maintenance task arrangements.

[0012] Preferably, in S1, the collected data is processed to extract key features, which specifically includes the following steps:

[0013] S11: Data collection: Collect equipment performance parameter data from various sensors, log files and monitoring tools;

[0014] S12: Data preprocessing: clean data, remove noise and outliers, and process missing data; standardize data and standardize data of different dimensions;

[0015] S13: Feature selection and extraction: Use correlation analysis or principal component analysis to select the features most relevant to the equipment status and extract key features;

[0016] S14: Model training: Choose decision tree, random forest or support vector machine to train the model; use historical data as training set and adjust model parameters to improve prediction accuracy;

[0017] S15: Model evaluation and optimization: Use cross-validation method to evaluate the performance of the model; adjust model parameters according to the evaluation results;

[0018] S16: Extract key features: Extract key features based on the trained model.

[0019] Preferably, in S3, analyzing the frequency of failures and the time required for resolution specifically includes the following steps:

[0020] S31: Data collection: Obtain fault records and maintenance logs from the operation and maintenance record system over the past period of time;

[0021] S32: Data sorting: classify and sort the fault records according to type, occurrence time, and resolution time information;

[0022] S33: Statistical analysis: Calculate the frequency of each type of fault, count the time it takes to resolve each fault, and calculate the average resolution time.

[0023] Preferably, in S3, a statistical method is used to make a reasonable estimate of possible problems in the future, specifically:

[0024] S34: Historical data analysis: collect equipment performance data and maintenance records within a set historical period;

[0025] S35: Build a prediction model: Select ARIMA or LSTM time series model, use historical data to train the model, and predict future equipment performance indicators and potential failure points;

[0026] S36: Risk assessment: Evaluate the severity of possible problems in the future based on the prediction results, and identify high-risk areas and key equipment;

[0027] S37: Develop contingency plans: Develop corresponding preventive measures and maintenance plans for predicted potential problems;

[0028] S38: Continuous monitoring and adjustment: Regularly update the prediction model and adjust the prediction results based on the latest data; continuously optimize the maintenance strategy based on actual conditions.

[0029] Preferably, in S5, the workload information of each staff member is updated in real time, specifically:

[0030] S51: Track the work task status of each staff member in real time;

[0031] S52: Based on the dynamic load calculation module, the load of each worker is calculated according to the current number of tasks and the estimated completion time; the complexity and urgency of different tasks are considered, and a weight is assigned to each task;

[0032] S53: Analyze and judge based on the set load threshold, and trigger a warning when the load of a certain worker exceeds the threshold;

[0033] S54: Load balancing strategy: When it is detected that a worker is overloaded, the load balancing mechanism is automatically started.

[0034] Preferably, in S6, a list of qualified staff members is quickly screened out according to a predetermined logic, which specifically includes the following steps:

[0035] S61: Determine the skills, experience and qualifications required based on task requirements; set priority rules;

[0036] S62: Matching is done based on the characteristics of the task and the capabilities of the staff, based on an automated matching algorithm;

[0037] S63: When there is a new task, the system runs an automated matching algorithm to filter out a list of qualified workers from a database containing detailed information of all workers; and sorts the workers according to preset priority rules;

[0038] S64: The selected staff member sends a notification.

[0039] Preferably: the matching method of the automatic matching algorithm is:

[0040] S621: Define mission characteristics and maintainer capabilities:

[0041] Mission Features: T i represents the i-th task, with attribute A(T i );

[0042] Maintenance personnel capability: P j represents the jth maintenance personnel, with attribute C(P j );

[0043] S622: Use a weighted scoring method to calculate the matching degree between each maintenance personnel and the task; set a weight for each task characteristic and maintenance personnel capability; where k represents the index of the characteristic or capability;

[0044] S623: Calculate the matching degree: For each task T i And each maintenance personnel P j , calculate the matching degree M ij

[0045]

[0046] Among them, sim(A k (T i ),C k (P j )) is the task feature A k (T i ) and maintenance personnel capabilities C k (P j ) similarity function between them;

[0047] S624: Select the best match: For each task T i , select the maintenance personnel P with the highest matching degree j :

[0048]

[0049] S625: Execute the matching process: When there is a new task, the system automatically runs the above matching algorithm to screen out a list of qualified candidates; and sorts the candidates according to the preset priority rules.

[0050] A device for a DICT operation and maintenance notification method, applied to the above-mentioned DICT operation and maintenance notification method, specifically includes:

[0051] Data processor: responsible for receiving data from various sources and processing and analyzing it;

[0052] Classifier: used to classify equipment and staff according to preset standards;

[0053] Predictor: predicts future maintenance needs based on historical data and real-time information;

[0054] Monitor: Continuously monitors the status of the equipment and triggers a warning if an abnormality is detected;

[0055] Matching engine: automatically matches the most suitable candidate based on the characteristics of the task and the ability of the staff;

[0056] Notifier: Send work instructions or reminders to selected staff members;

[0057] Priority Manager: Adjusts the priority of people based on workload factors.

[0058] A terminal device for a DICT operation and maintenance notification method, wherein the terminal device is an electronic device having a networking function and capable of implementing the above-mentioned DICT operation and maintenance notification method, and accesses the DICT operation and maintenance notification system based on an installed application.

[0059] A storage medium for a DICT operation and maintenance notification method, wherein an instruction set is stored in the storage medium, and when the instruction set is executed by a processor, the above-mentioned DICT operation and maintenance notification method can be implemented.

[0060] The beneficial effects of the present invention are embodied in:

[0061] 1. The present invention processes data through machine learning algorithms, which can automatically extract key features and realize intelligent matching of tasks and maintenance personnel, thereby improving matching accuracy and efficiency. Based on the dynamic load calculation module, the load situation of each person is calculated according to the current number of tasks and the expected completion time, and corresponding adjustments are made accordingly, effectively avoiding waste of resources and excessive load.

[0062] 2. When there is a new task, the system of the present invention will automatically run the matching algorithm, screen out a list of qualified candidates and promptly notify relevant personnel in a variety of ways, thereby improving work efficiency; by setting participation thresholds for maintenance personnel, the matching priority is automatically adjusted, thereby improving service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0064] Figure 1 The present invention is a flowchart of the DICT operation and maintenance notification method. DETAILED DESCRIPTION

[0065] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0066] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0067] Embodiment 1:

[0068] A DICT operation and maintenance notification method, implemented based on a DICT operation and maintenance notification system, comprises the following steps:

[0069] S1: Equipment classification and management, collect information about equipment performance parameters from various sensors; use machine learning algorithms to process the collected data and extract key features; classify equipment into different groups based on feature similarity, such as network equipment, servers, storage devices, etc.;

[0070] S2: Staff classification and management: classify and rate the professional skills of staff; track and record the various project experiences completed by each person; give each staff member a comprehensive rating based on the classification and rating of professional skills and personal experience;

[0071] S3: Forecasting headcount demand and making resource allocation recommendations. Analyze the frequency of various types of failures and the time required to resolve them within a set historical period; use statistical methods to make reasonable estimates of possible problems in the future; and propose reasonable human resource allocation plans based on the above analysis results.

[0072] S4: Real-time monitoring and task generation, which checks the working status of all networked devices around the clock. When any deviation from the normal range is found, an alarm is triggered immediately and a maintenance task is generated.

[0073] S5: Priority adjustment: determine a fixed time interval for calculating the workload of each staff member; set a threshold, and when the threshold is exceeded, reduce the matching priority of the staff member; as new maintenance tasks are completed, update the workload information of each staff member in real time and make adjustments accordingly;

[0074] S6: Intelligent matching and notification, based on the classification, scoring, comprehensive rating and current matching priority of the staff's professional skills; quickly screening out the list of qualified staff according to the established logic; and promptly informing relevant staff of the maintenance task arrangements through email, SMS, etc.

[0075] In S1, the collected data is processed to extract key features, which specifically includes the following steps:

[0076] S11: Data collection: Collect device performance parameter data from various sensors, log files and monitoring tools; performance parameter data includes CPU usage, memory usage, network traffic, disk I / O, etc.

[0077] S12: Data preprocessing: clean data, remove noise and outliers, and process missing data; standardize data and standardize data of different dimensions;

[0078] S13: Feature selection and extraction: Use correlation analysis or principal component analysis to select the features most relevant to the device status and extract key features, such as device load, response time, error rate, etc.

[0079] S14: Model training: Choose decision tree, random forest or support vector machine to train the model; use historical data as training set and adjust model parameters to improve prediction accuracy;

[0080] S15: Model evaluation and optimization: Use cross-validation method to evaluate the performance of the model; adjust model parameters according to the evaluation results;

[0081] S16: Extract key features: Extract key features based on the trained model.

[0082] Among them, in said S3, analyzing the frequency of failures and the time required for resolution specifically includes the following steps:

[0083] S31: Data collection: Obtain fault records and maintenance logs from the operation and maintenance record system over the past period of time;

[0084] S32: Data sorting: classify and sort the fault records according to type, occurrence time, resolution time and other information;

[0085] S33: Statistical analysis: Calculate the frequency of each type of fault, count the time it takes to resolve each fault, and calculate the average resolution time.

[0086] Among them, in S3, statistical methods are used to make reasonable predictions of possible problems in the future, specifically:

[0087] S34: Historical data analysis: collect equipment performance data and maintenance records within a set historical period;

[0088] S35: Build a prediction model: Select ARIMA or LSTM time series model, use historical data to train the model, and predict future equipment performance indicators and potential failure points;

[0089] S36: Risk assessment: Evaluate the severity of possible problems in the future based on the prediction results, and identify high-risk areas and key equipment;

[0090] S37: Develop contingency plans: Develop corresponding preventive measures and maintenance plans for predicted potential problems;

[0091] S38: Continuous monitoring and adjustment: Regularly update the prediction model and adjust the prediction results based on the latest data; continuously optimize the maintenance strategy based on actual conditions.

[0092] Among them, in said S5, the workload information of each staff member is updated in real time, specifically:

[0093] S51: Real-time tracking of the work task status of each staff member, including the number of assigned tasks, the progress of ongoing tasks, etc.;

[0094] S52: Based on the dynamic load calculation module, the load of each worker is calculated according to the current number of tasks and the estimated completion time; the complexity and urgency of different tasks are considered, and a weight is assigned to each task;

[0095] S53: Analyze and judge based on the set load threshold, and trigger a warning when the load of a certain staff member exceeds this threshold; the threshold can be adjusted according to individual ability and the overall situation of the team;

[0096] S54: Load balancing strategy: When it is detected that a worker is overloaded, the load balancing mechanism is automatically started.

[0097] Among them, in S6, a list of qualified staff members is quickly screened out according to a predetermined logic, which specifically includes the following steps:

[0098] S61: Determine the required skills, experience, and qualifications based on task requirements; set priority rules, such as high-priority tasks require higher-level staff;

[0099] S62: Matching is done based on the characteristics of the task and the capabilities of the staff, based on an automated matching algorithm;

[0100] S63: When there is a new task, the system runs an automated matching algorithm to filter out a list of qualified workers from a database containing detailed information of all workers; and sorts the workers according to preset priority rules;

[0101] S64: Send notification to selected staff members via email, SMS or other instant messaging tools.

[0102] The matching method of the automatic matching algorithm is as follows:

[0103] S621: Define mission characteristics and maintainer capabilities:

[0104] Mission Features: T i represents the i-th task, with attribute A(T i ), such as skill requirements, urgency, geographic location, etc.;

[0105] Maintenance personnel capability: P j represents the jth maintenance personnel, with attribute C(P j ), such as skill level, experience, current workload, etc.;

[0106] S622: Use a weighted scoring method to calculate the matching degree between each maintenance personnel and the task; set a weight for each task characteristic and maintenance personnel capability; where k represents the index of the characteristic or capability;

[0107] S623: Calculate the matching degree: For each task T i And each maintenance personnel P j , calculate the matching degree M ij

[0108]

[0109] Among them, sim(A k (T i ),C k (P j )) is the task feature A k (T i ) and maintenance personnel capabilities C k (P j ) similarity function between them;

[0110] S624: Select the best match: For each task T i , select the maintenance personnel P with the highest matching degree j :

[0111]

[0112] S625: Execute the matching process: When there is a new task, the system automatically runs the above matching algorithm to screen out a list of qualified candidates; and sorts the candidates according to the preset priority rules.

[0113] Embodiment 2:

[0114] A device for a DICT operation and maintenance notification method, comprising:

[0115] Data processor: responsible for receiving data from various sources and performing necessary processing and analysis;

[0116] Classifier: used to classify equipment and staff according to preset standards;

[0117] Predictor: predicts future maintenance needs based on historical data and real-time information;

[0118] Monitor: Continuously monitors the status of the equipment and triggers a warning if an abnormality is detected;

[0119] Matching engine: automatically matches the most suitable candidate based on the characteristics of the task and the ability of the staff;

[0120] Notifier: Send work instructions or reminders to selected staff members;

[0121] Priority Manager: Adjusts the priorities of people based on factors such as workload to ensure fairness.

[0122] Embodiment 3:

[0123] A terminal device of a DICT operation and maintenance notification method, wherein the terminal device can be any electronic device with networking function and capable of running relevant software, such as a smart phone, a tablet computer or a personal computer, etc.; based on the installed application, the DICT operation and maintenance notification system is accessed.

[0124] Embodiment 4:

[0125] A storage medium of a DICT operation and maintenance notification method, wherein an instruction set is stored in the storage medium, and when the instruction set is executed by a processor, all steps of the above-mentioned DICT operation and maintenance notification method can be implemented; such storage medium includes but is not limited to physical forms such as hard disk drives, solid-state drives, and forms such as digital copies downloaded through the network.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A DICT operation and maintenance notification method, characterized in that: Based on the DICT operation and maintenance notification system, it includes the following steps: S1: Equipment classification and management, collecting information about equipment performance parameters from various sensors; using machine learning algorithms to process the collected data and extract key features; Classify devices into different groups based on feature similarities; S2: Staff classification and management: classify and rate the professional skills of staff; track and record the various project experiences completed by each person; give each staff member a comprehensive rating based on the classification and rating of professional skills and personal experience; S3: Forecasting headcount demand and making resource allocation recommendations. Analyze the frequency of various types of failures and the time required to resolve them within a set historical period; use statistical methods to make reasonable estimates of possible problems in the future; and propose reasonable human resource allocation plans based on the above analysis results. S4: Real-time monitoring and task generation, real-time checking of the working status of all networked devices; When any deviation from the normal range is found, an alarm is triggered immediately and a maintenance task is generated; S5: Priority adjustment: determine a fixed time interval for calculating the workload of each staff member; set a threshold, and when the threshold is exceeded, reduce the matching priority of the staff member; as new maintenance tasks are completed, update the workload information of each staff member in real time and make adjustments accordingly; S6: Intelligent matching and notification, based on the classification, scoring, comprehensive rating of the staff's professional skills, and the current matching priority; quickly screening out the list of qualified staff according to the established logic; and promptly informing relevant staff of the maintenance task arrangements.

2. A DICT operation and maintenance notification method according to claim 1, characterized in that: In S1, the collected data is processed to extract key features, which specifically includes the following steps: S11: Data collection: Collect equipment performance parameter data from various sensors, log files and monitoring tools; S12: Data preprocessing: cleaning data, removing noise and outliers, and processing missing data; Standardize data, standardize data of different dimensions; S13: Feature selection and extraction: Use correlation analysis or principal component analysis to select the features most relevant to the equipment status and extract key features; S14: Model training: Choose decision tree, random forest or support vector machine to train the model; use historical data as training set and adjust model parameters to improve prediction accuracy; S15: Model evaluation and optimization: Use cross-validation method to evaluate the performance of the model; adjust model parameters according to the evaluation results; S16: Extract key features: Extract key features based on the trained model.

3. A DICT operation and maintenance notification method according to claim 1, characterized in that: In S3, the frequency of failures and the time required to resolve them are analyzed, which specifically includes the following steps: S31: Data collection: Obtain fault records and maintenance logs from the operation and maintenance record system over the past period of time; S32: Data sorting: classify and sort the fault records according to type, occurrence time, and resolution time information; S33: Statistical analysis: Calculate the frequency of each type of fault, count the time it takes to resolve each fault, and calculate the average resolution time.

4. A DICT operation and maintenance notification method according to claim 3, characterized in that: In S3, statistical methods are used to make reasonable predictions of possible problems in the future, specifically: S34: Historical data analysis: collect equipment performance data and maintenance records within a set historical period; S35: Build a prediction model: Select ARIMA or LSTM time series model, use historical data to train the model, and predict future equipment performance indicators and potential failure points; S36: Risk assessment: Evaluate the severity of possible problems in the future based on the prediction results and identify high-risk areas and key equipment; S37: Develop contingency plans: Develop corresponding preventive measures and maintenance plans for predicted potential problems; S38: Continuous monitoring and adjustment: Regularly update the prediction model and adjust the prediction results based on the latest data; continuously optimize the maintenance strategy based on actual conditions.

5. A DICT operation and maintenance notification method according to claim 1, characterized in that: In S5, the workload information of each staff member is updated in real time, specifically: S51: Track the work task status of each staff member in real time; S52: Based on the dynamic load calculation module, the load of each worker is calculated according to the current number of tasks and the estimated completion time; the complexity and urgency of different tasks are considered, and a weight is assigned to each task; S53: Analyze and judge based on the set load threshold, and trigger a warning when the load of a certain staff member exceeds the threshold; S54: Load balancing strategy: When it is detected that a worker is overloaded, the load balancing mechanism is automatically started.

6. A DICT operation and maintenance notification method according to claim 1, characterized in that: In S6, a list of qualified staff members is quickly screened out according to a predetermined logic, which specifically includes the following steps: S61: Determine the skills, experience and qualifications required based on task requirements; set priority rules; S62: Matching is done based on the characteristics of the task and the capabilities of the staff, based on an automated matching algorithm; S63: When there is a new task, the system runs an automated matching algorithm to filter out a list of qualified workers from a database containing detailed information of all workers; and sorts the workers according to preset priority rules; S64: The selected staff member sends a notification.

7. A DICT operation and maintenance notification method according to claim 6, characterized in that: The matching method of the automatic matching algorithm is: S621: Define mission characteristics and maintainer capabilities: Mission Features: T i represents the i-th task, with attribute A(T i ); Maintenance personnel capability: P j represents the jth maintenance personnel, with attribute C(P j ); S622: Use a weighted scoring method to calculate the matching degree between each maintenance personnel and the task; set a weight for each task characteristic and maintenance personnel capability; where k represents the index of the characteristic or capability; S623: Calculate the matching degree: For each task T i And each maintenance personnel P j , calculate the matching degree M ij Among them, sim(A k (T i ),C k (P j )) is the task feature A k (T i ) and maintenance personnel capabilities C k (P j ) similarity function between them; S624: Select the best match: For each task T i , select the maintenance personnel P with the highest matching degree j : S625: Execute the matching process: When there is a new task, the system automatically runs the above matching algorithm to screen out a list of qualified candidates; and sorts the candidates according to the preset priority rules.

8. A device for a DICT operation and maintenance notification method, characterized in that: The DICT operation and maintenance notification method as described in any one of claims 1 to 7 specifically includes: Data processor: responsible for receiving data from various sources and processing and analyzing it; Classifier: used to classify equipment and staff according to preset standards; Predictor: predicts future maintenance needs based on historical data and real-time information; Monitor: Continuously monitors the status of the equipment and triggers a warning if an abnormality is detected; Matching engine: automatically matches the most suitable candidate based on the characteristics of the task and the ability of the staff; Notifier: Send work instructions or reminders to selected staff members; Priority Manager: Adjusts the priority of people based on workload factors.

9. A terminal device for a DICT operation and maintenance notification method, characterized in that: The terminal device adopts an electronic device with networking function and capable of implementing the DICT operation and maintenance notification method described in any one of claims 1-7, and accesses the DICT operation and maintenance notification system based on the installed application.

10. A storage medium for a DICT operation and maintenance notification method, characterized in that: The storage medium stores an instruction set, which, when executed by the processor, can implement the DICT operation and maintenance notification method described in any one of claims 1-7.

Images