A Smart Operation Management Method and System Based on Dual Control Centers

Abstract

The present invention discloses a smart operation management method and system based on a dual control center, which relates to the field of artificial intelligence technology. The sub-control center continuously collects data through intelligent sensors, and performs preprocessing and preliminary analysis through edge computing devices, extracts key features and generates a preliminary report, and uploads it to the main control center; the main control center uses advanced data fusion algorithms to integrate data from different sources, and through big data analysis, predicts future passenger flow trends; generates decision instructions based on the data analysis results; according to the changes in real-time data, the main control center dynamically adjusts the decision instructions, and when an emergency occurs, automatically activates corresponding response measures. Predicting passenger flow trends through big data analysis to guide decision-making. Generating decision instructions based on the data analysis results and dynamically adjusting according to changes in real-time data enhances the adaptability and efficiency of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and particularly to an intelligent operation management method and system based on a dual control center. Background Art

[0002] With the rapid development of Internet of Things (IoT), big data, and artificial intelligence (AI) technologies, intelligent operation management has become an important means to improve urban governance level and service quality. In recent years, the multi-control center architecture based on a distributed architecture has gradually become a research hotspot. By constructing a mode in which a main control center and multiple sub-control centers work together, more refined data management and faster response capabilities have been achieved. However, in the actual application process, how to effectively coordinate the relationship between each control center is still a key problem to be solved

[0003] The data processing method in the traditional distributed architecture is often relatively rough, lacking an effective data fusion algorithm to achieve in-depth integration of data from different sources. The existing control center architecture has a slow response speed when dealing with emergencies. The generation of decision-making instructions is too static and cannot be dynamically adjusted according to the changes in real-time data, resulting in poor decision-making effects. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent operation management method and system based on a dual control center to solve the problems of insufficient data fusion, untimely decision response, and lack of an effective coordination mechanism in the existing intelligent operation management system.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides an intelligent operation management method based on a dual control center, which includes constructing a dual control center architecture including a main control center and a sub-control center, and establishing a coordination mechanism between the main control center and the sub-control center;

[0008] The sub-control center continuously collects data through intelligent sensors, and performs preprocessing and preliminary analysis through edge computing devices, extracts key features and generates a preliminary report, and uploads it to the main control center;

[0009] The main control center uses an advanced data fusion algorithm to integrate data from different sources, and predicts future passenger flow trends through big data analysis;

[0010] Based on the data analysis results, decision-making instructions are generated;

[0011] According to the changes in real-time data, the master control center dynamically adjusts decision-making instructions and automatically activates corresponding response measures when encountering emergencies.

[0012] As a preferred solution of the intelligent operation management method based on a dual control center according to the present invention, wherein: the continuously collecting data through intelligent sensors includes environmental changes, crowd density, and equipment working status.

[0013] As a preferred solution of the intelligent operation management method based on a dual control center according to the present invention, wherein: the preprocessing includes data cleaning, data conversion, and data compression;

[0014] The preprocessing and preliminary analysis are performed through edge computing devices, key features are extracted and a preliminary report is generated, and uploading to the master control center includes the following steps:

[0015] Extract key features from the preprocessed statistical data and identify periodic patterns for time data;

[0016] Based on the Z-Score method, calculate the outliers of each observation value;

[0017] Record the extracted key features and outliers and generate a preliminary report;

[0018] Establish an encrypted connection using the TLS protocol, and pack the compressed data blocks into data packets in chronological order;

[0019] Encrypt the data packets using the AES-256 encryption algorithm and send the encrypted data packets to the master control center through an encrypted channel.

[0020] As a preferred solution of the intelligent operation management method based on a dual control center according to the present invention, wherein: the master control center uses an advanced data fusion algorithm to integrate data from different sources and predict future passenger flow trends through big data analysis, including the following steps:

[0021] The master control center receives the data packets and decrypts them, verifying the integrity of the data and the authenticity of the source;

[0022] Design a Bayesian network based on probability statistics to fuse the verified multiple types of data;

[0023] Extract key features from the fused data, use the K-means clustering algorithm to group the data, and discover patterns in the data;

[0024] Use the Apriori algorithm to find frequent item sets and association rules in the data, and set support and confidence thresholds to filter out meaningful association rules;

[0025] Build a prediction model to predict the future passenger flow trend, and the expression is:

[0026]

[0027] Among them, f(t) represents the predicted passenger flow trend, i represents the index of the data, n represents the total number of data, t i represents the time point corresponding to the i-th data, t represents the time variable, σ i represents the time standard deviation of the i-th data point, b represents the bias term, λ represents the parameter controlling the steepness of the Sigmoid function, c k represents the amplitude of the k-th harmonic, ω k represents the angular frequency of the k-th harmonic, φ k represents the phase of the k-th harmonic, m represents the total number of harmonics, k represents the harmonic index, and θ represents the offset of the Sigmoid function.

[0028] As a preferred solution of the intelligent operation management method based on the dual control center described in the present invention, wherein: based on the data analysis result, generate a decision instruction, and the expression is:

[0029]

[0030] Among them, D r represents the r-th decision instruction, D represents the set of all decision instructions, d represents the total number of service frequencies to be adjusted, j represents the service frequency index, f j (t) represents the service frequency at time t, p represents the total number of route plans to be optimized, a represents the route plan index to be optimized, h a (t) represents the optimization effect of the a-th route at time t, q represents the total number of facility maintenance plans to be adjusted, and gl(t) represents the l-th facility maintenance status at time t.

[0031] As a preferred solution of the intelligent operation management method based on the dual control center described in the present invention, wherein: according to the change of real-time data, the master control center dynamically adjusts the decision instruction, and the expression is:

[0032]

[0033] Among them, D r ′ represents the adjusted r-th decision instruction, ΔD r represents the adjustment amount of the r-th decision instruction, Δf j (t) represents the change amount of the j-th service frequency adjustment strategy at time t, Δh a (t) represents the change amount of the a-th route planning strategy at time t, Δg l(t) represents the change amount of the l-th facility maintenance plan at time t, and sign(·) represents the sign function.

[0034] As a preferred solution of the intelligent operation management method based on a dual control center according to the present invention, wherein: when an emergency occurs, automatically starting the corresponding response measures includes the following steps:

[0035] Continuously collect data using a sensor network, and analyze the data to identify abnormal patterns;

[0036] Set a safety threshold, and when the detected data exceeds the safety threshold, it is determined as an emergency;

[0037] Confirm the authenticity of the event through multi-source data fusion technology, and automatically classify it according to the nature of the event;

[0038] The system automatically sends an alarm signal to the main control center, retrieves the corresponding pre-plan from the pre-plan database according to the event type, and analyzes each instruction and step in the pre-plan;

[0039] Notify relevant agencies of the emergency response measures according to the requirements of the pre-plan.

[0040] In a second aspect, the present invention provides an intelligent operation management system based on a dual control center, including,

[0041] Dual control center cooperation module: construct a dual control center architecture including a main control center and a sub-control center, and establish a cooperation mechanism between the main control center and the sub-control center;

[0042] Data acquisition and preprocessing module: The sub-control center continuously collects data through intelligent sensors, and performs preprocessing and preliminary analysis through edge computing devices, extracts key features and generates a preliminary report, and uploads it to the main control center;

[0043] Data fusion and analysis module: The main control center uses advanced data fusion algorithms to integrate data from different sources, and predicts future passenger flow trends through big data analysis;

[0044] Instruction generation module: generate decision-making instructions based on the data analysis results;

[0045] Emergency response and coordination module: The main control center dynamically adjusts decision-making instructions according to changes in real-time data, and automatically starts corresponding response measures when an emergency occurs.

[0046] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and: when the computer program is executed by the processor, it implements any step of the intelligent operation management method based on a dual control center as described in the first aspect of the present invention.

[0047] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the intelligent operation management method based on a dual control center as described in the first aspect of the present invention is implemented.

[0048] The beneficial effects of the present invention are as follows: A dual control center architecture is constructed, and hierarchical management is achieved through the collaboration mechanism between the main and sub-control centers, improving the flexibility and reliability of the system. The sub-control center uses intelligent sensors to collect data such as environmental changes and pedestrian flow density, and performs preprocessing and preliminary analysis through edge computing, improving data quality and transmission efficiency. The main control center uses advanced data fusion algorithms to integrate data from different sources, predicts passenger flow trends through big data analysis, and guides decision-making. Decision-making instructions are generated based on the analysis results of the data and dynamically adjusted according to real-time data changes, enhancing the adaptability and efficiency of the system. When an emergency occurs, the system can automatically initiate response measures, ensuring the stability and security of the system. This series of steps significantly improves the operation efficiency, user experience, and security guarantee level. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0050] Figure 1 It is a flowchart of the intelligent operation management method based on a dual control center in Embodiment 1.

[0051] Figure 2 It is a flowchart of decision-making instruction generation in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the drawings in the specification.

[0053] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention, but the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0054] Second, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that are mutually exclusive with other embodiments.

[0055] Embodiment 1, referring to Figure 1 and Figure 2 , is the first embodiment of the present invention. This embodiment provides a smart operation management method based on a dual control center, including the following steps:

[0056] S1. Construct a dual control center architecture including a main control center and a sub-control center, and establish a coordination mechanism between the main control center and the sub-control center.

[0057] S2. Continuously collect data through intelligent sensors, including environmental changes, population density, and equipment working status; perform preprocessing and preliminary analysis through edge computing devices, extract key features, and generate a preliminary report, and upload it to the main control center, including the following steps: extract key features from the preprocessed statistical data, identify periodic patterns in the time data; calculate the outliers of each observation value based on the Z-Score method; record and generate a preliminary report with the extracted key features (such as maximum value, minimum value, mean, etc.) and outliers; establish an encrypted connection using the TLS protocol, package the compressed data blocks into data packets in chronological order; encrypt the data packets using the AES-256 encryption algorithm, and send the encrypted data packets to the main control center through the encrypted channel.

[0058] Furthermore, data cleaning includes invalid data filtering and error data correction;

[0059] Invalid data filtering means detecting and removing null values or missing values. For numerical data, remove outliers outside the reasonable range, such as temperature data exceeding the human survival range; error data correction means filling missing values using simple time series methods (such as moving average) and applying outlier detection algorithms to remove abnormal data points; data conversion means converting data into a unified format, such as unifying the temperature unit to Celsius and converting unstructured data (such as text remarks) into structured data (such as tags or classifications); data compression means compressing the preprocessed data using the LZ4 compression algorithm to reduce the bandwidth required for data transmission.

[0060] It should be noted that the intelligent sensor can monitor environmental changes (such as temperature and humidity), the density of the flow of people, and the working status of equipment (such as operating efficiency and fault warning) in real time, ensuring a comprehensive understanding of the status of the monitored area, being able to detect potential problems in a timely manner, such as overheating, overcrowding of people or equipment failures, etc., so as to prevent the occurrence of safety accidents; the edge computing device can process data nearby, relieve the pressure on the main control center, and quickly generate key features and preliminary reports for quick decision-making, reducing the amount of data transmission and latency, and improving the response speed and overall efficiency of the system; by extracting key features (such as maximum value, minimum value, average value, etc.) and identifying the periodic patterns of time data, it can help understand the trends and laws of the data, and be able to predict future environmental changes, fluctuations in the flow of people and equipment status more accurately, and make preparations in advance; by extracting key features (such as maximum value, minimum value, average value, etc.) and identifying the periodic patterns of time data, it can help understand the trends and laws of the data; using statistical methods (Z-Score) to identify outliers helps to distinguish normal data from abnormal data, improving the accuracy and reliability of data analysis.

[0061] S3. The main control center uses advanced data fusion algorithms to integrate data from different sources, and through big data analysis, predicts future passenger flow trends, including the following steps:

[0062] The main control center receives the data packet and decrypts it, verifying the integrity of the data and the authenticity of the source;

[0063] Design a Bayesian network based on probability statistics to fuse the verified multiple types of data;

[0064] Extract key features from the fused data, use the K-means clustering algorithm to group the data, and discover patterns in the data;

[0065] Use the Apriori algorithm to find frequent item sets and association rules in the data, and set support and confidence thresholds to filter out meaningful association rules;

[0066] Build a prediction model to predict future passenger flow trends, and the expression is:

[0067]

[0068] Among them, f(t) represents the predicted passenger flow trend, i represents the index of the data, n represents the total number of data, t i represents the time point corresponding to the i-th data, t represents the time variable, σ i represents the time standard deviation of the i-th data point, b represents the bias term, λ represents the parameter controlling the steepness of the Sigmoid function, c k represents the amplitude of the k-th harmonic, ω krepresents the angular frequency of the k-th harmonic, φ k represents the phase of the k-th harmonic, m represents the total number of harmonics, k represents the harmonic index, and θ represents the offset of the Sigmoid function.

[0069] Furthermore, the expression for fusing data by the Bayesian network is:

[0070]

[0071] Among them, A represents the probability of traffic congestion occurring in a specific area within a specific time period, B represents the traffic flow data from the sub-control center, C represents the weather data from another sub-control center, D represents the pedestrian flow data from the third sub-control center, E represents the special event data from the fourth sub-control center, p(a) represents the prior probability of event A, P(B∣A) represents the probability of observing data B when event A occurs, P(C∣A) represents the probability of observing data C when event A occurs, P(D∣A) represents the probability of observing data D when event A occurs, P(E∣A) represents the probability of observing data E when event A occurs, P(B), P(C), P(D), and P(E) respectively represent the marginal probabilities of data B, C, D, and E, and P(A∣B, C, D, E) respectively represents the posterior probability of event A when given data B, C, D, and E.

[0072] It should be noted that by receiving data packets through the main control center and decrypting them, verifying the integrity and authenticity of the data sources improves the credibility of the data and ensures the accuracy of subsequent data analysis and prediction; designing a Bayesian network based on probability statistics to fuse various types of verified data improves the accuracy of the prediction model and can more accurately predict future passenger flow trends; extracting key features from the fused data, using the K-means clustering algorithm to group the data, and discovering patterns in the data helps to more deeply understand the characteristics of passenger flow distribution and provides support for optimizing operation strategies; using the Apriori algorithm to find frequent item sets and association rules in the data and setting support and confidence thresholds to filter out meaningful association rules helps to identify which factors have a significant impact on passenger flow changes and provides a basis for decision-making; predicting future passenger flow trends based on historical data and analysis results improves operation efficiency and reduces losses caused by improper resource allocation.

[0073] S4. Generate decision instructions based on the data analysis results, and the expression is:

[0074]

[0075] Among them, D rDenote the r-th decision instruction, D represents the set of all decision instructions, d represents the total number of service frequencies to be adjusted, j represents the service frequency index, and f j f(t) represents the service frequency at time t, p represents the total number of route plans to be optimized, a represents the route plan index to be optimized, and h a h(t) represents the optimization effect of the a-th route at time t, q represents the total number of facility maintenance plans to be adjusted, and gl(t) represents the l-th facility maintenance status at time t.

[0076] Furthermore, the generation process of decision instructions includes collecting real-time frequency data of all services (such as train schedules, bus routes, etc.), real-time data of all route plans, including congestion conditions, traffic flow, etc., and status data of all facility maintenance, including equipment failure rates, maintenance records, etc.; calculating the weighted sum of all service frequencies at time t, calculating the total sum of the optimization effects of all routes at time t, calculating the total square root value sum of all facility maintenance statuses at time t, generating all possible decision instructions, and selecting the largest instruction as the best decision to maximize service frequency and service quality while minimizing the negative impact brought by facility maintenance problems.

[0077] Furthermore, regarding the adjustment of service frequencies, increase the service frequencies of other unaffected lines to relieve the pressure on the affected lines, reduce the service frequencies during off-peak hours, and concentrate resources on peak hours and key routes; for route plan optimization, re-plan the train routes to avoid affected areas and add temporary bus routes as alternative means of transportation; for facility maintenance, strengthen the maintenance inspections of facilities around the affected areas and prioritize the maintenance and repair work of key equipment.

[0078] It should be noted that by collecting real-time frequency data of all services (such as train schedules, bus routes, etc.), the dynamic monitoring of service frequencies is realized, and then the service frequencies are adjusted according to the monitoring data. Finally, the service frequencies are increased during peak hours to meet the needs of passengers, and the service frequencies are reduced during off-peak hours to save resources.

[0079] S5. According to the changes in real-time data, the master control center dynamically adjusts the decision instructions, and the expression is:

[0080]

[0081] where D r ′ represents the adjusted r-th decision instruction, ΔD r represents the adjustment amount of the r-th decision instruction, Δf j f(t) represents the change amount of the j-th service frequency adjustment strategy at time t, Δh a(t) represents the change amount of the a-th route planning strategy at time t, Δg l (t) represents the change amount of the l-th facility maintenance plan at time t, and sign(·) represents the sign function.

[0082] It should be noted that the main control center dynamically adjusts the decision-making instructions according to the changes in real-time data, which enables the system to make the most appropriate decisions based on the current situation, ensures that the decision-making instructions are always optimal, can better adapt to the changing operating environment, improves the flexibility and adaptability of the system, and ensures the quality and efficiency of the operating services.

[0083] S6. When an emergency occurs, the automatic activation of the corresponding response measures includes the following steps:

[0084] Continuously collect data using the sensor network and analyze the data to identify abnormal patterns;

[0085] Set a safety threshold. When the detected data exceeds the safety threshold, it is determined as an emergency;

[0086] Confirm the authenticity of the event through multi-source data fusion technology and automatically classify it according to the nature of the event;

[0087] The system automatically sends an alarm signal to the main control center, retrieves the corresponding emergency plan from the emergency plan database according to the event type, and analyzes each instruction and step in the emergency plan;

[0088] Notify the relevant agencies of the emergency response measures according to the requirements of the emergency plan.

[0089] It should be noted that continuously collecting data using the sensor network and analyzing the data to identify abnormal patterns improves the response speed and accuracy of emergencies; by setting a safety threshold, the system can more accurately identify emergencies, reduce false alarms, and improve the reliability and efficiency of the system; by automatically sending alarm signals and retrieving emergency plans, the automation and rapid startup of emergency response are achieved; by notifying the relevant agencies of the emergency response measures, cross-departmental cooperation is realized, the overall response speed and efficiency are improved, and the impact of emergencies is reduced.

[0090] This embodiment also provides a smart operation management system based on a dual control center, including a dual control center collaboration module: constructing a dual control center architecture including a main control center and a sub-control center, and establishing a collaboration mechanism between the main control center and the sub-control center;

[0091] Data acquisition and preprocessing module: The sub-control center continuously collects data through intelligent sensors, performs preprocessing and preliminary analysis through edge computing devices, extracts key features and generates a preliminary report, and uploads it to the main control center;

[0092] Data fusion and analysis module: The main control center uses advanced data fusion algorithms to integrate data from different sources and predicts future passenger flow trends through big data analysis;

[0093] Instruction generation module: Generates decision-making instructions based on the data analysis results;

[0094] Emergency response and coordination module: According to the changes in real-time data, the main control center dynamically adjusts the decision-making instructions. When an emergency occurs, corresponding response measures are automatically initiated.

[0095] This embodiment also provides a computer device applicable to the situation of the intelligent operation management method based on a dual control center, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the intelligent operation management method based on a dual control center as proposed in the above embodiment.

[0096] The computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0097] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the intelligent operation and management method based on a dual control center as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0098] In summary, the present invention constructs a dual control center architecture, realizes hierarchical management through the collaborative mechanism between the main and sub-control centers, and improves the flexibility and reliability of the system. The sub-control center uses intelligent sensors to collect data such as environmental changes and crowd density, and performs pre-processing and preliminary analysis through edge computing, thereby improving data quality and transmission efficiency. The main control center uses advanced data fusion algorithms to integrate data from different sources, predicts passenger flow trends through big data analysis, and guides decision-making. Decision instructions are generated based on data analysis results, and dynamically adjusted according to real-time data changes, which enhances the adaptability and efficiency of the system. When encountering emergencies, the system can automatically initiate response measures to ensure the stability and security of the system. This series of steps significantly improves operational efficiency, user experience, and security levels.

[0099] Example 2

[0100] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of the intelligent operation management method based on dual control centers are provided.

[0101] A dual control center architecture consisting of a main control center and four sub-control centers was deployed at a large transportation hub. Each sub-control center is responsible for monitoring environmental changes, crowd density, and equipment working status in a specific area.

[0102] Intelligent sensors are installed in each area, which can monitor environmental temperature, humidity, pedestrian flow, equipment operation status, etc. in real time. At the same time, edge computing devices are configured to perform data preprocessing, outlier detection, and pack the data and send it to the main control center. The edge computing device uses the Z-Score method to identify outliers and fills in missing values by the moving average method. The data is converted into a unified format and compressed by the LZ4 compression algorithm, then encrypted by the AES-256 encryption algorithm and sent to the main control center. After receiving the data, the main control center uses a Bayesian network to fuse data from different sub-control centers. Through the K-means clustering algorithm and the Apriori algorithm, data patterns and association rules are discovered, and a prediction model is constructed to predict the passenger flow trend in the next week. Based on the results of the prediction model, the main control center generates a series of decision instructions, including adjusting service frequency, optimizing route planning, and facility maintenance plans. For example, when it is predicted that a peak period is coming, the subway train frequency is increased, and additional bus routes are planned to cope with the high passenger flow. The system dynamically adjusts decision instructions according to changes in real-time data and activates emergency response measures when an emergency is detected. For example, when a fire breaks out in a certain area, the system immediately takes measures to evacuate the crowd and adjusts the route planning to avoid the affected area. Specifically, as shown in Table 1:

[0103] Table 1 Experimental Record Table

[0104]

[0105] By analyzing the table data and historical data, the accuracy rate of the prediction model reaches between 93% and 97%, which indicates that the model has high prediction accuracy and can accurately predict the passenger flow change trend in the next week. When high passenger flow is predicted, the system responds by increasing the service frequency (such as subway train frequency), and the adjustment range varies from +5% to +15%. This effectively alleviates the congestion during peak periods and improves the travel experience of passengers. By optimizing the route, the system can guide passengers to less congested paths, and the optimization effect varies from +3% to +7%, thus reducing the waiting time and travel time of passengers. By maintaining and repairing equipment in advance and in a timely manner, the facility maintenance status has been improved, and the facility maintenance status has improved from -2% to -4%, reducing the equipment failure rate and improving the overall system stability.

[0106] In summary, the technical solution proposed in the present invention has achieved remarkable effects in practical applications. It not only improves the prediction accuracy, but also optimizes the service quality through intelligent decision-making, reduces the facility maintenance cost, and enhances the overall experience of passengers. Compared with the traditional manual management method, the present invention can respond to changes faster and make more accurate decisions, reflecting its innovation and practicality.

[0107] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A smart operation management method based on dual control centers, characterized in that: include, Build a dual control center architecture including a main control center and a sub-control center, and establish a coordination mechanism between the main control center and the sub-control center; The sub-control center continuously collects data through intelligent sensors, and performs pre-processing and preliminary analysis through edge computing devices, extracts key features and generates preliminary reports, which are then uploaded to the main control center; The main control center uses advanced data fusion algorithms to integrate data from different sources and analyze big data to predict future passenger flow trends, including the following steps: The main control center receives the data packet and decrypts it to verify the integrity of the data and the authenticity of the source; Design a Bayesian network based on probability statistics to integrate multiple types of verified data; Extract key features from the fused data, group the data using the K-means clustering algorithm, and discover patterns in the data; Use the Apriori algorithm to find frequent item sets and association rules in the data, and set support and confidence thresholds to filter out meaningful association rules; Construct a prediction model to predict future passenger flow trends. The expression is: Among them, f(t) represents the predicted passenger flow trend, i represents the index of the data, n represents the total number of data, and t i represents the time point corresponding to the i-th data, t represents the time variable, σ i represents the time standard deviation of the ith data point, b represents the bias term, λ represents the parameter that controls the steepness of the Sigmoid function, and c k represents the amplitude of the kth harmonic, ω k represents the angular frequency of the kth harmonic, φ k represents the phase of the kth harmonic, m represents the total number of harmonics, k represents the harmonic index, and θ represents the offset of the Sigmoid function; Based on the data analysis results, a decision instruction is generated, and the expression is: Among them, D r represents the rth decision instruction, D represents the set of all decision instructions, d represents the total number of service frequencies that need to be adjusted, j represents the service frequency index, and f j (t) represents the service frequency at time t, p represents the total number of route plans that need to be optimized, a represents the route plan index that needs to be optimized, and h a (t) represents the optimization effect of the ath route at time t, q represents the total number of facility maintenance plans that need to be adjusted, and gl(t) represents the maintenance status of the lth facility at time t; According to the changes in real-time data, the main control center dynamically adjusts decision-making instructions and automatically initiates corresponding response measures when encountering emergencies.

2. The intelligent operation management method based on dual control centers as claimed in claim 1, characterized in that: The data continuously collected through the intelligent sensors include environmental changes, crowd density and equipment working status.

3. The intelligent operation management method based on dual control centers as claimed in claim 1, characterized in that: The preprocessing includes data cleaning, data conversion and data compression; The preprocessing and preliminary analysis by edge computing equipment, extraction of key features and generation of preliminary reports, and uploading to the main control center include the following steps: Extract key features from preprocessed statistical data and identify periodic patterns in temporal data; Based on the Z-Score method, calculate the outlier value of each observation; The extracted key features and outliers are recorded and a preliminary report is generated; Use the TLS protocol to establish an encrypted connection and package the compressed data blocks into data packets in chronological order; The data packet is encrypted using the AES-256 encryption algorithm and sent to the main control center through an encrypted channel.

4. The intelligent operation management method based on dual control centers as claimed in claim 1, characterized in that: According to the changes in real-time data, the main control center dynamically adjusts the decision instructions, and the expression is: Among them, D r ′ represents the rth decision instruction after adjustment, ΔD r represents the adjustment amount of the rth decision instruction, Δf j (t) represents the change in the jth service frequency adjustment strategy at time t, Δh a (t) represents the change in the ath route planning strategy at time t, Δg l (t) represents the change in the lth facility maintenance plan at time t, and sign(·) represents the sign function.

5. The intelligent operation management method based on dual control centers as claimed in claim 4, characterized in that: When an emergency occurs, automatically initiating the corresponding response measures includes the following steps: Utilize sensor networks to continuously collect data and analyze it to identify unusual patterns; Set a safety threshold. When the detected data exceeds the safety threshold, it is considered an emergency. Confirm the authenticity of the event through multi-source data fusion technology and automatically classify it according to its nature; The system automatically sends an alarm signal to the main control center, retrieves the corresponding plan from the plan database according to the event type, and analyzes the instructions and steps in the plan; According to the requirements of the plan, the emergency response measures will be notified to relevant agencies.

6. A smart operation management system based on dual control centers, based on the smart operation management method based on dual control centers according to any one of claims 1 to 5, characterized in that: include, Dual control center collaboration module: Build a dual control center architecture including a main control center and a sub-control center, and establish a collaboration mechanism between the main control center and the sub-control center; Data collection and preprocessing module: The sub-control center continuously collects data through intelligent sensors, and performs preprocessing and preliminary analysis through edge computing devices, extracts key features and generates preliminary reports, which are then uploaded to the main control center; Data fusion and analysis module: The main control center uses advanced data fusion algorithms to integrate data from different sources and predict future passenger flow trends through big data analysis; Instruction generation module: generates decision instructions based on data analysis results; Emergency response and coordination module: According to the changes in real-time data, the main control center dynamically adjusts decision-making instructions and automatically initiates corresponding response measures when encountering emergencies.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent operation management method based on dual control centers described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent operation management method based on dual control centers described in any one of claims 1 to 5 are implemented.

Images