An intelligent operation and maintenance management platform and method based on AI and big data

Abstract

The present invention provides an intelligent operation and maintenance management platform based on AI and big data and a method thereof, including: screening real-time operation data corresponding to each management area in a big data center, establishing a real-time operation status corresponding to each management area, using AI technology to predict the status of each real-time operation status, obtaining the predicted operation status of the corresponding management area, retrieving the target management area whose predicted operation status belongs to the super-saturation characteristic, establishing a regional adjustment plan based on the current saturation characteristics corresponding to the target management area and the corresponding target real-time operation data, following up the adjustment information of each target management area, and generating an analysis summary report after the target management area is adjusted. Based on the analysis summary report, the cause of the super-saturation corresponding to the target management area is determined, and a comprehensive analysis of matters in the park can be performed, so as to achieve pre-warning, in-process follow-up, and post-event summary, thereby forming a complete management process and solving the problems in traditional technologies.

Description

Technical Field

[0001] The present invention relates to the field of park operation and maintenance management technology, and in particular to an intelligent operation and maintenance management platform and method based on AI and big data. Background Art

[0002] Park operation and maintenance management involves the comprehensive management and operation of facilities, equipment and services within the park. The following are several key aspects and tasks of park operation and maintenance management:

[0003] Facilities Management:

[0004] Facility maintenance and upkeep: Regularly inspect and maintain buildings, roads, green areas and other facilities within the park to ensure their normal operation and good condition.

[0005] Safety management: Implement safety regulations and measures to ensure the safety of people and facilities within the park.

[0006] Environmental management: Manage the environmental quality of the park, including air quality, noise control, waste disposal, etc., to provide a comfortable working and living environment.

[0007] Device Management:

[0008] Equipment maintenance: Regular maintenance and inspection of various equipment in the park (such as air conditioners, elevators, water supply systems, etc.) to ensure their efficient operation.

[0009] Energy Management: Monitor and optimize equipment energy consumption and take steps to reduce energy costs and environmental impact.

[0010] Service Management:

[0011] Infrastructure services: such as the stable provision and management of water supply, power supply, and communication networks.

[0012] Public services: provision and management of public services such as cleaning, garbage disposal, and parking management.

[0013] Community service: Promote communication and cooperation between enterprises and residents in the park, and organize community activities and events.

[0014] Information management:

[0015] Data collection and analysis: Use Internet of Things (IoT) technology to collect park operation data for real-time monitoring and analysis.

[0016] Information system support: manage the information systems required for park operations, such as equipment management systems, security monitoring systems, etc., to improve management efficiency and response speed.

[0017] Planning and coordination:

[0018] Park planning: formulate long-term and short-term development plans based on demand and optimize resource allocation and utilization.

[0019] Coordination and management: Communicate and coordinate with enterprises, owners, residents and other parties within the park to solve problems and promote development.

[0020] However, most industrial parks are still in the manual management stage. This traditional management method has many problems. The operation and maintenance of the industrial park not only requires a large number of management personnel, but also has high manual management costs. Moreover, when special situations arise and require coordination and processing by management personnel, it often leads to delays in coordination and processing by management personnel, and events are not handled in a timely manner.

[0021] Therefore, the present invention provides an intelligent operation and maintenance management platform and method based on AI and big data. Summary of the invention

[0022] The present invention provides an intelligent operation and maintenance management platform based on AI and big data and its method, which can conduct a comprehensive analysis of matters within the park, achieve pre-warning, in-process follow-up, and post-event summary, forming a complete management process and solving problems in traditional technologies.

[0023] The present invention provides an intelligent operation and maintenance management platform based on AI and big data, comprising:

[0024] A data collection module is used to screen the real-time operation data corresponding to each management area in the big data center and establish the real-time operation status corresponding to each management area;

[0025] A status analysis module, used to use AI technology to predict the status of each of the real-time operating states, obtain the predicted operating status of the corresponding management area and display it;

[0026] A management adjustment module, used to retrieve a target management area whose predicted operating state belongs to supersaturation characteristics, and establish a regional adjustment plan based on the current saturation characteristics corresponding to the target management area and the corresponding target real-time operating data;

[0027] A follow-up management module, used to follow up the adjustment information of each target management area and generate an analysis summary report after the adjustment of the target management area is completed;

[0028] The prevention management module is used to determine the supersaturation cause corresponding to the target management area based on the analysis summary report, establish a solution to overcome the supersaturation cause and transmit it to the target management area for display.

[0029] In one practicable manner,

[0030] The data collection module comprises:

[0031] a directional screening unit, configured to establish a screening rule corresponding to each management area based on the type of management data corresponding to each management area and the amount of data corresponding to each management data type, and to screen a number of rule-compliant data in the big data center using the screening rule;

[0032] The precise screening unit is used to trace the source of each of the rule-compliant data, obtain the data source corresponding to each of the rule-compliant data, and when the data source is within the management area, map the corresponding target rule-compliant data to the corresponding management area, and obtain the real-time operation data corresponding to each of the management areas;

[0033] The status analysis unit is used to retrieve the historical data corresponding to each of the management areas, establish an operation data chain corresponding to each operating device in the corresponding management area in combination with the real-time operation data, and establish the real-time operation status corresponding to the management area according to each of the motion data chains.

[0034] In one practicable manner,

[0035] The state analysis module comprises:

[0036] An intelligent simulation unit, used to establish a simulation area corresponding to each management area according to the real-time operation status corresponding to each management area by using AI technology, and to perform data calibration on the simulation area by using the real-time operation data corresponding to each management area, so as to generate a synchronous simulation area corresponding to each management area;

[0037] A state prediction unit, used for analyzing the trend change range of the synchronous simulation area within a unit time period according to the current presentation trend corresponding to each synchronous simulation area, and establishing several predicted operation states of the management area within a unit time according to the area change range combined with the real-time operation state of the corresponding management area;

[0038] an in-depth analysis unit, configured to respectively simulate each corresponding predicted operation state using the synchronous simulation area, obtain the predicted operation data corresponding to the management area under each predicted operation state, respectively perform an abnormality analysis on each predicted operation data, and establish an abnormality label for the corresponding predicted operation state according to the abnormality analysis result;

[0039] A status presentation unit is used to extract an emergency predicted operating state with an abnormality higher than a target degree according to a label value corresponding to the abnormal label, extract a non-emergency operating state with an abnormality not higher than the target degree, add an emergency mark to the emergency predicted operating state and display it, and add a non-emergency label to the non-emergency operating state and display it.

[0040] In one practicable manner,

[0041] Also includes:

[0042] Establish emergency alerts for emergency management areas with emergency labels;

[0043] The remaining manageable time of the emergency management area is determined according to the emergency prediction operation status corresponding to the emergency tag, and an early warning processing plan is established in combination with the emergency warning and transmitted to the emergency management area for management warning.

[0044] In one practicable manner,

[0045] The management and scheduling module includes:

[0046] A saturation classification unit is used to respectively obtain label information corresponding to each of the predicted operating states, perform cluster analysis on the predicted operating states according to the label information to obtain a plurality of state sets, and respectively obtain an operating saturation threshold corresponding to each of the state sets;

[0047] The execution unit is retrieved and used to perform comparative training on each of the operating saturation thresholds based on a preset super-saturation threshold, obtain a saturation feature corresponding to each of the state sets, sort the state sets in descending order based on the saturation features, search for a target state set with super-saturation features according to the sorting result, and retrieve the corresponding target management area in each of the target state sets;

[0048] A condition building unit, used to determine the data flow difference of the target management area according to the real-time operation data corresponding to the target management area, establish the current saturation characteristics corresponding to the target management area, determine the saturation growth rate of the target management area according to the current saturation characteristics, and establish the saturation adjustment duration corresponding to the target management area;

[0049] A scheme construction unit is used to search for several standard management schemes corresponding to the target management area according to the area attributes corresponding to the target management area, analyze the management direction of each standard management scheme respectively, determine the management direction corresponding to each standard management scheme, retrieve the corresponding target standard management scheme according to the saturation characteristics, and establish the area adjustment scheme of the target management area in combination with the corresponding saturation adjustment duration.

[0050] In one practicable manner,

[0051] The scheme construction unit comprises:

[0052] A solution analysis subunit is used to find several standard management solutions corresponding to each target management area according to the area attributes corresponding to the target management area, and use AI technology to simulate and execute each standard management solution to obtain the management direction of each standard management solution in the corresponding target management area;

[0053] A saturation analysis subunit, used to determine the overflow direction corresponding to the target management area according to the supersaturation characteristics, establish a reverse instruction according to each overflow direction, and use the reverse instruction to search for each management direction to obtain a plurality of target standard management solutions;

[0054] The scheme construction subunit is used to obtain the execution time corresponding to each of the target standard management schemes, combine the target standard management schemes in combination with the saturation adjustment time, and obtain several combination schemes, and use AI technology to simulate the effective value of each combination scheme respectively, and retrieve the combination scheme with the highest effective value as the regional adjustment plan for the target management area.

[0055] In one practicable manner,

[0056] The follow-up management module includes:

[0057] A follow-up execution unit, used to respectively obtain adjustment data of each target management area when executing the area adjustment plan, and generate adjustment information of the target management area;

[0058] An adjustment supervision unit, configured to determine and display the adjustment progress corresponding to the target management area based on the adjustment information;

[0059] A report generating unit is used to create and display an analysis summary report of the target management area according to the adjustment information when the adjustment progress corresponding to the target management area is 100%.

[0060] In one practicable manner,

[0061] The prevention management module comprises:

[0062] A cause analysis unit, used to analyze the analysis summary report to obtain a number of supersaturation causes and a number of abnormal factors corresponding to each target management area;

[0063] A cause tracing unit, used for determining the abnormal source corresponding to each of the supersaturation causes of the target management area according to the logical relationship between each of the supersaturation causes and each of the abnormal factors of the same target management area;

[0064] An overcoming execution unit is used to establish a corresponding overcoming method for the supersaturation cause according to the fault information corresponding to each of the abnormal sources of the same target management area, and to establish a corresponding supersaturation cause overcoming plan for the target management area according to the support information and constraint information between different overcoming methods;

[0065] The transmission and display unit is used to transmit each of the supersaturation cause overcoming solutions to the corresponding target management area for display.

[0066] The present invention provides an intelligent operation and maintenance management method based on AI and big data, comprising:

[0067] Step 1: Filter the real-time operation data corresponding to each management area in the big data center, and establish the real-time operation status corresponding to each management area;

[0068] Step 2: Use AI technology to predict the status of each real-time operating status, obtain the predicted operating status of the corresponding management area and display it;

[0069] Step 3: Retrieve the target management area whose predicted operating state belongs to the supersaturation characteristic, and establish a regional adjustment plan based on the current saturation characteristic corresponding to the target management area and the corresponding target real-time operating data;

[0070] Step 4: Follow up the adjustment information of each target management area, and generate an analysis summary report after the adjustment of the target management area is completed;

[0071] Step 5: Determine the supersaturation cause corresponding to the target management area based on the analysis summary report, establish a solution to overcome the supersaturation cause and transmit it to the target management area for display.

[0072] In one practicable manner,

[0073] The step 1 comprises:

[0074] Step 11: establishing a screening rule corresponding to each management area based on the type of management data corresponding to each management area and the amount of data corresponding to each management data type, and screening a number of rule-compliant data in the big data center using the screening rule;

[0075] Step 12: Tracing the source of each of the rule-compliant data respectively to obtain the data source corresponding to each of the rule-compliant data; when the data source is within the management area, mapping the corresponding target rule-compliant data to the corresponding management area to obtain the real-time operation data corresponding to each of the management areas;

[0076] Step 13: Retrieve the historical data corresponding to each of the management areas, and establish an operation data chain corresponding to each operating device in the corresponding management area in combination with the real-time operation data, and establish the real-time operation status corresponding to the management area according to each of the motion data chains.

[0077] The achievable beneficial effects of the above technical solution are: in order to build a management platform that can prevent in advance, handle in the process and analyze after the event, in the process of working in the management area, the real-time operation status of the park is established by collecting the real-time operation data of the management area, and then the real-time operation status is predicted by using the intelligence of AI means, thereby obtaining the predicted operation status of the management area. If it is found through prediction that the management area has the possibility of over-saturation in the future, then the management area is prevented in advance by establishing a regional adjustment plan, and adjustments are followed up during the prevention and saturation adjustment process, and an analysis summary report is generated after the adjustment is completed to resolve the crisis. Managers can further manage the park based on the analysis summary report to avoid similar saturation phenomena from happening again.

[0078] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0079] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0081] Figure 1 Schematic diagram of the composition of an intelligent operation and maintenance management platform based on AI and big data in an embodiment of the present invention;

[0082] Figure 2 The figure is a schematic diagram of the workflow of an intelligent operation and maintenance management method based on AI and big data in an embodiment of the present invention. DETAILED DESCRIPTION

[0083] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0084] Example 1

[0085] This embodiment provides an intelligent operation and maintenance management platform based on AI and big data. Figure 1 As shown, including:

[0086] A data collection module is used to screen the real-time operation data corresponding to each management area in the big data center and establish the real-time operation status corresponding to each management area;

[0087] A status analysis module, used to use AI technology to predict the status of each of the real-time operating states, obtain the predicted operating status of the corresponding management area and display it;

[0088] A management adjustment module, used to retrieve a target management area whose predicted operating state belongs to supersaturation characteristics, and establish a regional adjustment plan based on the current saturation characteristics corresponding to the target management area and the corresponding target real-time operating data;

[0089] A follow-up management module, used to follow up the adjustment information of each target management area and generate an analysis summary report after the adjustment of the target management area is completed;

[0090] The prevention management module is used to determine the supersaturation cause corresponding to the target management area based on the analysis summary report, establish a solution to overcome the supersaturation cause and transmit it to the target management area for display.

[0091] In this example, the management area can be big data information processing scenarios in the fields of smart transportation, smart community, Xueliang Project, smart farm, smart park, etc.

[0092] In this example, real-time operation data refers to data generated during the operation of the management area;

[0093] In this instance, the supersaturated feature indicates that the project in the management area has collapsed;

[0094] In this example, the platform can manage one or more management areas simultaneously.

[0095] The working principle and beneficial effects of the above technical solution: In order to build a management platform that can prevent in advance, handle in the process and analyze after the event, the real-time operation status of the park is established by collecting real-time operation data of the management area during the work in the management area, and then the real-time operation status is predicted by using the intelligence of AI means, thereby obtaining the predicted operation status of the management area. If it is found through prediction that the management area has the possibility of over-saturation in the future, then the management area is prevented in advance by establishing a regional adjustment plan, and adjustments are followed up during the prevention and saturation adjustment process, and an analysis summary report is generated after the adjustment is completed to resolve the crisis. Managers can conduct further preventive management of the park based on the analysis summary report to avoid similar saturation phenomena from happening again.

[0096] Example 2

[0097] On the basis of Example 1, the intelligent operation and maintenance management platform based on AI and big data, the data collection module includes:

[0098] a directional screening unit, configured to establish a screening rule corresponding to each management area based on the type of management data corresponding to each management area and the amount of data corresponding to each management data type, and to screen a number of rule-compliant data in the big data center using the screening rule;

[0099] The precise screening unit is used to trace the source of each of the rule-compliant data, obtain the data source corresponding to each of the rule-compliant data, and when the data source is within the management area, map the corresponding target rule-compliant data to the corresponding management area, and obtain the real-time operation data corresponding to each of the management areas;

[0100] The status analysis unit is used to retrieve the historical data corresponding to each of the management areas, establish an operation data chain corresponding to each operating device in the corresponding management area in combination with the real-time operation data, and establish the real-time operation status corresponding to the management area according to each of the motion data chains.

[0101] In this example, rule-compliant data refers to data whose data type and data quantity are consistent with the data type and data quantity produced by the management area, that is, data that passes the screening rules;

[0102] In this example, one piece of rule-compliant data corresponds to one data source, and one data source can generate several pieces of rule-compliant data or one piece of rule-compliant data at the same time.

[0103] The working principle and beneficial effects of the above technical solution: In order to build an effective operating status and avoid interference from external data, the management data type and management data quantity corresponding to each management area are used to establish screening rules, so as to screen the data in the big data and obtain a number of rule-compliant data. Then, each rule-compliant data is traced to the source, and the real-time operating data of each management area is determined. Finally, the corresponding historical data is combined to establish an operating data chain, and the real-time operating status of the management area is established through the information contained in the operating data chain. In this way, it can not only ensure the influence of external data on the final status, but also ensure that the real-time operating status is updated synchronously with the actual status of the management area.

[0104] Example 3

[0105] On the basis of Example 1, the intelligent operation and maintenance management platform based on AI and big data, the status analysis module includes:

[0106] An intelligent simulation unit, used to establish a simulation area corresponding to each management area according to the real-time operation status corresponding to each management area by using AI technology, and to perform data calibration on the simulation area by using the real-time operation data corresponding to each management area, so as to generate a synchronous simulation area corresponding to each management area;

[0107] A state prediction unit, used for analyzing the trend change range of the synchronous simulation area within a unit time period according to the current presentation trend corresponding to each synchronous simulation area, and establishing several predicted operation states of the management area within a unit time according to the area change range combined with the real-time operation state of the corresponding management area;

[0108] an in-depth analysis unit, configured to respectively simulate each corresponding predicted operation state using the synchronous simulation area, obtain the predicted operation data corresponding to the management area under each predicted operation state, respectively perform an abnormality analysis on each predicted operation data, and establish an abnormality label for the corresponding predicted operation state according to the abnormality analysis result;

[0109] A status presentation unit is used to extract an emergency predicted operating state with an abnormality higher than a target degree according to a label value corresponding to the abnormal label, extract a non-emergency operating state with an abnormality not higher than the target degree, add an emergency mark to the emergency predicted operating state and display it, and add a non-emergency label to the non-emergency operating state and display it.

[0110] In this example, the abnormal label indicates that the state presented by the predicted operation state belongs to abnormal work;

[0111] In this example, the predicted operating states corresponding to a management area may include one or more abnormalities or 0 emergency labels, or one or more abnormalities or 0 non-emergency labels;

[0112] In this example, one predicted operating state corresponds to one abnormal label;

[0113] In this example, the emergency tag indicates that the predicted operation status display management area will have a contained tag;

[0114] In this example, the target degree is 45%;

[0115] In this example, the unit time period is 1 hour;

[0116] In this example, a predicted operating state can only correspond to one emergency label or one non-emergency label. When it corresponds to the emergency label, it is an emergency predicted operating state, and an emergency mark is added to it. When it corresponds to the non-emergency label, it is a non-emergency predicted operating state, and a non-emergency mark is added to it.

[0117] The working principle and beneficial effects of the above technical solution: In order to further limit and analyze the predicted operating status, a synchronous simulation area is constructed to determine the range of changes in the presentation area of ​​the management area in the next hour, and then several predicted operating states in the next hour are established. Then, the synchronous simulation area is used to perform an abnormal analysis on each predicted operating state, so as to construct an abnormal label based on the abnormal analysis results, and then the target degree is used to classify the predicted operating status, and different labels are added for final display, thereby realizing synchronous analysis and real-time display, and improving the efficiency of analysis.

[0118] Example 4

[0119] On the basis of Example 3, the intelligent operation and maintenance management platform based on AI and big data further includes:

[0120] Establish emergency alerts for emergency management areas with emergency labels;

[0121] The remaining manageable time of the emergency management area is determined according to the emergency prediction operation status corresponding to the emergency tag, and an early warning processing plan is established in combination with the emergency warning and transmitted to the emergency management area for management warning.

[0122] The working principle and beneficial effects of the above technical solution: Early warning of emergency management areas and establishment of management plans can not only achieve early prevention but also improve the efficiency of prevention.

[0123] Example 5

[0124] On the basis of Example 1, the intelligent operation and maintenance management platform based on AI and big data, the management and scheduling module includes:

[0125] A saturation classification unit is used to respectively obtain label information corresponding to each of the predicted operating states, perform cluster analysis on the predicted operating states according to the label information to obtain a plurality of state sets, and respectively obtain an operating saturation threshold corresponding to each of the state sets;

[0126] The execution unit is retrieved and used to perform comparative training on each of the operating saturation thresholds based on a preset super-saturation threshold, obtain a saturation feature corresponding to each of the state sets, sort the state sets in descending order based on the saturation features, search for a target state set with super-saturation features according to the sorting result, and retrieve the corresponding target management area in each of the target state sets;

[0127] A condition building unit, used to determine the data flow difference of the target management area according to the real-time operation data corresponding to the target management area, establish the current saturation characteristics corresponding to the target management area, determine the saturation growth rate of the target management area according to the current saturation characteristics, and establish the saturation adjustment duration corresponding to the target management area;

[0128] A scheme construction unit is used to search for several standard management schemes corresponding to the target management area according to the area attributes corresponding to the target management area, analyze the management direction of each standard management scheme respectively, determine the management direction corresponding to each standard management scheme, retrieve the corresponding target standard management scheme according to the saturation characteristics, and establish the area adjustment scheme of the target management area in combination with the corresponding saturation adjustment duration.

[0129] In this example, one state set corresponds to one operating saturation threshold;

[0130] In this example, the data flow difference represents the data generated by the flow objects of each item in the management area. For example, if the management area is an amusement park, the data flow difference represents the personnel flow difference corresponding to each amusement facility;

[0131] In this example, the preset supersaturation threshold is 99%;

[0132] In this example, the management direction indicates the direction in which adjustment can be achieved after the standard management solution performs corresponding management on the management area.

[0133] The working principle and beneficial effects of the above technical solution: In order to effectively manage the management area and reduce unnecessary accidents of all sizes, cluster analysis is performed based on the label information of each predicted operating state to obtain the set state. The operating saturation threshold corresponding to each set state is combined with the preset super-saturation threshold to find the target state set with super-saturation characteristics, and the corresponding target management area is obtained in the target state set. Then, the saturation speed analysis is performed on each target management area to determine the duration of this adjustment. Then, the corresponding standard management plan is called up, and further calls are made based on the management direction corresponding to each standard management plan. Finally, the regional adjustment plan is constructed in combination with the adjustment duration to achieve the purpose of prior prevention.

[0134] Example 6

[0135] On the basis of Example 5, the intelligent operation and maintenance management platform based on AI and big data, the solution building unit includes:

[0136] A solution analysis subunit is used to find several standard management solutions corresponding to each target management area according to the area attributes corresponding to the target management area, and use AI technology to simulate and execute each standard management solution to obtain the management direction of each standard management solution in the corresponding target management area;

[0137] A saturation analysis subunit, used to determine the overflow direction corresponding to the target management area according to the supersaturation characteristics, establish a reverse instruction according to each overflow direction, and use the reverse instruction to search for each management direction to obtain a plurality of target standard management solutions;

[0138] The scheme construction subunit is used to obtain the execution time corresponding to each of the target standard management schemes, combine the target standard management schemes in combination with the saturation adjustment time, and obtain several combination schemes, and use AI technology to simulate the effective value of each combination scheme respectively, and retrieve the combination scheme with the highest effective value as the regional adjustment plan for the target management area.

[0139] The working principle and beneficial effects of the above technical solution are as follows: by utilizing the overflow direction to construct a reverse instruction to retrieve the corresponding target standard management solution, and then combining the execution time of each target standard management solution and the saturation adjustment time to construct a combination solution, and analyzing the effectiveness of each combination solution, so as to select the combination solution with the highest effective value as the regional adjustment solution. In this way, experimental analysis can be carried out on multiple adjustment solutions, and the effectiveness of the solution can be verified by experiments, thereby improving the availability of the solution.

[0140] Example 7

[0141] On the basis of Example 1, the intelligent operation and maintenance management platform based on AI and big data, the follow-up management module includes:

[0142] A follow-up execution unit, used to respectively obtain adjustment data of each target management area when executing the area adjustment plan, and generate adjustment information of the target management area;

[0143] An adjustment supervision unit, configured to determine and display the adjustment progress corresponding to the target management area based on the adjustment information;

[0144] A report generating unit is used to create and display an analysis summary report of the target management area according to the adjustment information when the adjustment progress corresponding to the target management area is 100%.

[0145] The working principle and beneficial effects of the above technical solution are as follows: corresponding supervision is carried out during the execution of the adjustment, and an analysis report is generated for reference by management personnel after the adjustment is completed, thus realizing in-process supervision.

[0146] Example 8

[0147] On the basis of Example 1, the intelligent operation and maintenance management platform based on AI and big data, the prevention management module includes:

[0148] A cause analysis unit, used to analyze the analysis summary report to obtain a number of supersaturation causes and a number of abnormal factors corresponding to each target management area;

[0149] A cause tracing unit, used for determining the abnormal source corresponding to each of the supersaturation causes of the target management area according to the logical relationship between each of the supersaturation causes and each of the abnormal factors of the same target management area;

[0150] An overcoming execution unit is used to establish a corresponding overcoming method for the supersaturation cause according to the fault information corresponding to each of the abnormal sources of the same target management area, and to establish a corresponding supersaturation cause overcoming plan for the target management area according to the support information and constraint information between different overcoming methods;

[0151] The transmission and display unit is used to transmit each of the supersaturation cause overcoming solutions to the corresponding target management area for display.

[0152] In this example, a saturation cause may include one or more abnormal factors.

[0153] The working principle and beneficial effects of the above technical solution: In order to overcome the problems existing in the management area, the causes of supersaturation and abnormal factors in the target management area are determined through analysis and summary reports, and then the abnormal factors are traced back, and the methods of overcoming each abnormal source are combined to establish a plan to overcome the causes of supersaturation. In this way, the management area can be reviewed afterwards, and the next step of preventive preparation can be made.

[0154] Example 9

[0155] This embodiment provides an intelligent operation and maintenance management method based on AI and big data. Figure 2 As shown, including:

[0156] Step 1: Filter the real-time operation data corresponding to each management area in the big data center, and establish the real-time operation status corresponding to each management area;

[0157] Step 2: Use AI technology to predict the status of each real-time operating status, obtain the predicted operating status of the corresponding management area and display it;

[0158] Step 3: Retrieve the target management area whose predicted operating state belongs to the supersaturation characteristic, and establish a regional adjustment plan based on the current saturation characteristic corresponding to the target management area and the corresponding target real-time operating data;

[0159] Step 4: Follow up the adjustment information of each target management area, and generate an analysis summary report after the adjustment of the target management area is completed;

[0160] Step 5: Determine the supersaturation cause corresponding to the target management area based on the analysis summary report, establish a solution to overcome the supersaturation cause and transmit it to the target management area for display.

[0161] In this example, the management area can be big data information processing scenarios in the fields of smart transportation, smart community, Xueliang Project, smart farm, smart park, etc.

[0162] In this example, real-time operation data refers to data generated during the operation of the management area;

[0163] In this instance, the supersaturated feature indicates that the project in the management area has collapsed;

[0164] In this example, the platform can manage one or more management areas simultaneously.

[0165] The working principle and beneficial effects of the above technical solution: In order to build a management platform that can prevent in advance, handle in the process and analyze after the event, the real-time operation status of the park is established by collecting real-time operation data of the management area during the work in the management area, and then the real-time operation status is predicted by using the intelligence of AI means, thereby obtaining the predicted operation status of the management area. If it is found through prediction that the management area has the possibility of over-saturation in the future, then the management area is prevented in advance by establishing a regional adjustment plan, and adjustments are followed up during the prevention and saturation adjustment process, and an analysis summary report is generated after the adjustment is completed to resolve the crisis. Managers can conduct further preventive management of the park based on the analysis summary report to avoid similar saturation phenomena from happening again.

[0166] Example 10

[0167] On the basis of Example 9, the intelligent operation and maintenance management method based on AI and big data, step 1, comprises:

[0168] Step 11: establishing a screening rule corresponding to each management area based on the type of management data corresponding to each management area and the amount of data corresponding to each management data type, and screening a number of rule-compliant data in the big data center using the screening rule;

[0169] Step 12: Tracing the source of each of the rule-compliant data respectively to obtain the data source corresponding to each of the rule-compliant data; when the data source is within the management area, mapping the corresponding target rule-compliant data to the corresponding management area to obtain the real-time operation data corresponding to each of the management areas;

[0170] Step 13: Retrieve the historical data corresponding to each of the management areas, and establish an operation data chain corresponding to each operating device in the corresponding management area in combination with the real-time operation data, and establish the real-time operation status corresponding to the management area according to each of the motion data chains.

[0171] In this example, rule-compliant data refers to data whose data type and data quantity are consistent with the data type and data quantity produced by the management area, that is, data that passes the screening rules;

[0172] In this example, one piece of rule-compliant data corresponds to one data source, and one data source can generate several pieces of rule-compliant data or one piece of rule-compliant data at the same time.

[0173] The working principle and beneficial effects of the above technical solution: In order to build an effective operating status and avoid interference from external data, the management data type and management data quantity corresponding to each management area are used to establish screening rules, so as to screen the data in the big data and obtain a number of rule-compliant data. Then, each rule-compliant data is traced to the source, and the real-time operating data of each management area is determined. Finally, the corresponding historical data is combined to establish an operating data chain, and the real-time operating status of the management area is established through the information contained in the operating data chain. In this way, it can not only ensure the influence of external data on the final status, but also ensure that the real-time operating status is updated synchronously with the actual status of the management area.

[0174] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent operation and maintenance management platform based on AI and big data, characterized in that: include: A data collection module is used to screen the real-time operation data corresponding to each management area in the big data center and establish the real-time operation status corresponding to each management area; A status analysis module, used to use AI technology to predict the status of each of the real-time operating states, obtain the predicted operating status of the corresponding management area and display it; A management adjustment module, used to retrieve a target management area whose predicted operating state belongs to supersaturation characteristics, and establish a regional adjustment plan based on the current saturation characteristics corresponding to the target management area and the corresponding target real-time operating data; A follow-up management module, used to follow up the adjustment information of each target management area and generate an analysis summary report after the adjustment of the target management area is completed; A prevention management module, for determining the supersaturation cause corresponding to the target management area based on the analysis summary report, establishing a solution to overcome the supersaturation cause and transmitting the solution to the target management area for display; The management adjustment module includes: A saturation classification unit is used to respectively obtain label information corresponding to each of the predicted operating states, perform cluster analysis on the predicted operating states according to the label information to obtain a plurality of state sets, and respectively obtain an operating saturation threshold corresponding to each of the state sets; The execution unit is retrieved and used to perform comparative training on each of the operating saturation thresholds based on a preset super-saturation threshold, obtain a saturation feature corresponding to each of the state sets, sort the state sets in descending order based on the saturation features, search for a target state set with super-saturation features according to the sorting result, and retrieve the corresponding target management area in each of the target state sets; A condition building unit, used to determine the data flow difference of the target management area according to the real-time operation data corresponding to the target management area, establish the current saturation characteristics corresponding to the target management area, determine the saturation growth rate of the target management area according to the current saturation characteristics, and establish the saturation adjustment duration corresponding to the target management area; A scheme construction unit is used to search for several standard management schemes corresponding to the target management area according to the regional attributes corresponding to the target management area, analyze the management direction of each standard management scheme respectively, determine the management direction corresponding to each standard management scheme, retrieve the corresponding target standard management scheme according to the saturation characteristics, and establish the regional adjustment scheme of the target management area in combination with the corresponding saturation adjustment duration; The scheme construction unit comprises: A solution analysis subunit is used to find several standard management solutions corresponding to each target management area according to the area attributes corresponding to the target management area, and use AI technology to simulate and execute each standard management solution to obtain the management direction of each standard management solution in the corresponding target management area; A saturation analysis subunit, used to determine the overflow direction corresponding to the target management area according to the supersaturation characteristics, establish a reverse instruction according to each overflow direction, and use the reverse instruction to search for each management direction to obtain a plurality of target standard management solutions; The scheme construction subunit is used to obtain the execution time corresponding to each of the target standard management schemes, combine the target standard management schemes in combination with the saturation adjustment time, and obtain several combination schemes, and use AI technology to simulate the effective value of each combination scheme respectively, and retrieve the combination scheme with the highest effective value as the regional adjustment plan for the target management area.

2. The intelligent operation and maintenance management platform based on AI and big data as claimed in claim 1, characterized in that: The data collection module comprises: a directional screening unit, configured to establish a screening rule corresponding to each management area based on the type of management data corresponding to each management area and the amount of data corresponding to each management data type, and to screen a number of rule-compliant data in the big data center using the screening rule; The precise screening unit is used to trace the source of each of the rule-compliant data, obtain the data source corresponding to each of the rule-compliant data, and when the data source is within the management area, map the corresponding target rule-compliant data to the corresponding management area, and obtain the real-time operation data corresponding to each of the management areas; The status analysis unit is used to retrieve the historical data corresponding to each of the management areas, establish an operation data chain corresponding to each operating device in the corresponding management area in combination with the real-time operation data, and establish the real-time operation status corresponding to the management area according to each of the operation data chains.

3. The intelligent operation and maintenance management platform based on AI and big data as claimed in claim 1, characterized in that: The state analysis module comprises: An intelligent simulation unit, used to establish a simulation area corresponding to each management area according to the real-time operation status corresponding to each management area by using AI technology, and to perform data calibration on the simulation area by using the real-time operation data corresponding to each management area, so as to generate a synchronous simulation area corresponding to each management area; A state prediction unit, used for analyzing the trend change range of the synchronous simulation area within a unit time period according to the current presentation trend corresponding to each synchronous simulation area, and establishing several predicted operation states of the management area within a unit time according to the area change range combined with the real-time operation state of the corresponding management area; an in-depth analysis unit, configured to respectively simulate each corresponding predicted operation state using the synchronous simulation area, obtain the predicted operation data corresponding to the management area under each predicted operation state, respectively perform an abnormality analysis on each predicted operation data, and establish an abnormality label for the corresponding predicted operation state according to the abnormality analysis result; A status presentation unit is used to extract an emergency predicted operating state with an abnormality higher than a target degree according to a label value corresponding to the abnormal label, extract a non-emergency operating state with an abnormality not higher than the target degree, add an emergency mark to the emergency predicted operating state and display it, and add a non-emergency label to the non-emergency operating state and display it.

4. The intelligent operation and maintenance management platform based on AI and big data as claimed in claim 3, characterized in that: Also includes: Establish emergency alerts for emergency management areas with emergency labels; The remaining manageable time of the emergency management area is determined according to the emergency prediction operation status corresponding to the emergency tag, and an early warning processing plan is established in combination with the emergency warning and transmitted to the emergency management area for management warning.

5. The intelligent operation and maintenance management platform based on AI and big data as claimed in claim 1, characterized in that: The follow-up management module includes: A follow-up execution unit, used to respectively obtain adjustment data of each target management area when executing the area adjustment plan, and generate adjustment information of the target management area; An adjustment supervision unit, configured to determine and display the adjustment progress corresponding to the target management area based on the adjustment information; A report generating unit is used to create and display an analysis summary report of the target management area according to the adjustment information when the adjustment progress corresponding to the target management area is 100%.

6. The intelligent operation and maintenance management platform based on AI and big data as claimed in claim 1, characterized in that: The prevention management module comprises: A cause analysis unit, used to analyze the analysis summary report to obtain a number of supersaturation causes and a number of abnormal factors corresponding to each target management area; A cause tracing unit, used for determining the abnormal source corresponding to each of the supersaturation causes of the target management area according to the logical relationship between each of the supersaturation causes and each of the abnormal factors of the same target management area; An overcoming execution unit is used to establish a corresponding overcoming method for the supersaturation cause according to the fault information corresponding to each of the abnormal sources of the same target management area, and to establish a corresponding supersaturation cause overcoming plan for the target management area according to the support information and constraint information between different overcoming methods; The transmission and display unit is used to transmit each of the supersaturation cause overcoming solutions to the corresponding target management area for display.

7. An intelligent operation and maintenance management method based on AI and big data, characterized in that: include: Step 1: Filter the real-time operation data corresponding to each management area in the big data center, and establish the real-time operation status corresponding to each management area; Step 2: Use AI technology to predict the status of each real-time operating status, obtain the predicted operating status of the corresponding management area and display it; Step 3: Retrieve the target management area whose predicted operating state belongs to the supersaturation characteristic, and establish a regional adjustment plan based on the current saturation characteristic corresponding to the target management area and the corresponding target real-time operating data; Step 4: Follow up the adjustment information of each target management area, and generate an analysis summary report after the adjustment of the target management area is completed; Step 5: Determine the supersaturation cause corresponding to the target management area based on the analysis summary report, establish a solution to overcome the supersaturation cause and transmit it to the target management area for display; The step 3 comprises: Step 31: respectively obtain label information corresponding to each of the predicted operating states, perform cluster analysis on the predicted operating states according to the label information to obtain a plurality of state sets, and respectively obtain an operating saturation threshold corresponding to each of the state sets; Step 32: performing comparative training on each of the operating saturation thresholds based on a preset supersaturation threshold, obtaining a saturation feature corresponding to each of the state sets, sorting the state sets in descending order based on the saturation features, searching for a target state set with supersaturation features according to the sorting result, and retrieving the target management area corresponding to each of the target state sets; Step 33: determining the data flow difference of the target management area according to the real-time operation data corresponding to the target management area, establishing the current saturation characteristics corresponding to the target management area, determining the saturation growth rate of the target management area according to the current saturation characteristics, and establishing the saturation adjustment duration corresponding to the target management area; Step 34: searching for several standard management schemes corresponding to the target management area according to the regional attributes corresponding to the target management area, analyzing the management direction of each standard management scheme respectively, determining the management direction corresponding to each standard management scheme, retrieving the corresponding target standard management scheme according to the saturation characteristics, and establishing the regional adjustment scheme of the target management area in combination with the corresponding saturation adjustment duration; The step 34 comprises: Step 341: searching for several standard management schemes corresponding to each target management area according to the area attributes corresponding to the target management area, using AI technology to simulate and execute each standard management scheme, and obtaining the management direction of each standard management scheme in the corresponding target management area; Step 342: determining the overflow direction corresponding to the target management area according to the supersaturation characteristics, establishing a reverse instruction according to each overflow direction, searching each management direction using the reverse instruction, and obtaining a plurality of target standard management solutions; Step 343: Obtain the execution time corresponding to each of the target standard management plans, combine the target standard management plans in combination with the saturation adjustment time to obtain several combination plans, use AI technology to simulate the effective value of each combination plan respectively, and retrieve the combination plan with the highest effective value as the regional adjustment plan for the target management area.

8. The intelligent operation and maintenance management method based on AI and big data as claimed in claim 7, characterized in that: The step 1 comprises: Step 11: establishing a screening rule corresponding to each management area based on the type of management data corresponding to each management area and the amount of data corresponding to each management data type, and screening a number of rule-compliant data in the big data center using the screening rule; Step 12: Tracing the source of each of the rule-compliant data respectively to obtain the data source corresponding to each of the rule-compliant data; when the data source is within the management area, mapping the corresponding target rule-compliant data to the corresponding management area to obtain the real-time operation data corresponding to each of the management areas; Step 13: Retrieve the historical data corresponding to each of the management areas, and establish an operation data chain corresponding to each operation device in the corresponding management area in combination with the real-time operation data, and establish the real-time operation status corresponding to the management area according to each of the operation data chains.

Images