Ship lock operation scheduling system and method based on big data analysis

Abstract

The invention provides a ship lock operation scheduling system and method based on big data analysis, and relates to the technical field of ship lock operation scheduling. By integrating big data analysis of historical operation data, ship priority evaluation, real-time navigation state monitoring and intelligent prediction, refinement, dynamics and intelligence of ship lock scheduling are achieved, the overall traffic efficiency is remarkably improved, and congestion of a lock area is effectively relieved. Low-efficiency links are identified through clustering analysis, congestion points are captured in real time in combination with a space thermodynamic diagram, and a declaration time period and interval time are dynamically adjusted, so that the adaptive capacity of the system to abnormal conditions such as load change, severe weather and equipment faults is enhanced; differentiated services and green channel support of high-priority ships are realized, and key transportation requirements are guaranteed; and upstream and downstream ship lock linkage scheduling is realized through a network cloud platform, and a neural network model is utilized to generate an optimization scheme containing a lockage sequence, suggested arrival time and a coordination instruction to improve watershed navigation collaboration.

Description

Technical Field

[0001] This invention relates to the field of lock operation scheduling technology, and in particular to a lock operation scheduling system and method based on big data analysis. Background Technology

[0002] With the rapid development of inland waterway shipping, locks, as key nodes in the waterway network, bear an increasingly heavy burden of vessel passage. However, traditional lock operation and scheduling methods are no longer sufficient to meet the demands for efficient, safe, and intelligent navigation. Currently, most locks still employ static scheduling modes based on manual experience or simple queuing rules, lacking in-depth mining and analysis of historical operational data. This makes it impossible to accurately identify bottlenecks in the lock passage process, such as frequent equipment failures, adverse weather conditions, and significant differences in passage efficiency among different types of vessels, resulting in insufficient scientific rigor in scheduling decisions. Furthermore, vessel applications often rely on fixed time slots or first-come, first-served mechanisms, failing to consider differences in vessel type, transport importance, and historical behavior, making priority management difficult and causing delays in the transport of high-value goods and unfair resource allocation. In addition, existing systems have weak real-time navigation status awareness capabilities, lacking dynamic monitoring and early warning of vessel distribution, queuing density, and congestion trends within the lock area, easily leading to severe congestion during peak hours. More importantly, the information silos between upstream and downstream locks are prominent, and there is a lack of effective coordination and linkage mechanisms, which leads to frequent and concentrated arrivals of ships between multiple locks, exacerbating the overall operational pressure on the waterway.

[0003] Therefore, it is necessary to provide a lock operation scheduling system and method based on big data analysis to solve the above-mentioned technical problems. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a lock operation scheduling system and method based on big data analysis to solve the problems of traditional lock operation scheduling, which suffers from simple scheduling methods, lack of data-driven decision-making capabilities, lack of differentiated management and priority mechanisms, and insufficient collaborative capabilities.

[0005] This invention provides a lock operation scheduling method based on big data analysis, the lock operation scheduling method comprising the following steps: S1. Obtain historical lock operation data and identify traffic impact indicators to locate inefficient links in the process. Traffic impact indicators include lock passage time, congestion frequency, equipment failure records, severe weather, or differences in lock passage efficiency between different types of vessels. S2. Obtain vessel information and its corresponding historical lock passage records, and evaluate the passage priority score of each vessel; S3. Obtain the real-time navigation status of the lock through a satellite positioning system or camera system, dynamically adjust the interval time, and identify the congestion points in the current lock area based on the real-time navigation status of the lock within the interval time. S4. Combine inefficient links with congestion points in the current lock area to set up a strategy for adjusting the available time periods. Adjust the initial available time periods of the lock to obtain the adjusted available time periods. S5. Based on the priority scores of each vessel and the adjusted application time periods, the upstream and downstream locks are linked through the network cloud platform to generate a lock operation scheduling plan.

[0006] Preferably, step S1 includes the following specific steps: S101. Obtain historical lock operation data from the lock management system or ship registration system, including historical lock operation data, lock basic information, ship basic information, ship declaration information, and ship navigation status information. S102. From the historical lock operation data, statistical analysis is performed on lock passage time, congestion frequency, equipment failure records, differences in lock passage efficiency due to severe weather or different types of vessels, and the passage impact indicators are determined by using preset threshold ranges. S103. Based on the traffic impact indicators, analyze the lock operation process using cluster analysis and identify inefficient links.

[0007] Preferably, step S2 includes the following specific steps: S201. Obtain information on each vessel preparing to pass through the lock from the vessel registration system or vessel declaration information, including vessel size, tonnage, type, and navigation route; S202. Query the lock management system to obtain the previous lock passage records for each vessel, including the passage time, whether there have been any violations, and the passage efficiency. S203. Preset scoring dimensions and use a weighted summation method to calculate the passage priority score for each vessel.

[0008] Preferably, step S3 includes the following specific steps: S301. Use satellite positioning system or camera system to monitor the distribution and flow of ships in the waters surrounding the lock, and obtain the current real-time navigation status of the lock, including the number of ships in the lock area and ship queuing information. S302. Based on the real-time navigation status, analyze the current operating load of the lock and automatically adjust the interval time according to the current operating load of the lock. The higher the operating load, the longer the adjustment interval time, and the lower the operating load, the shorter the adjustment interval time. S303. Based on the adjusted interval, the congestion points in the current gate area are identified using spatial heat map analysis.

[0009] Preferably, the strategy for adjusting the eligible time period in step S4 is as follows: If the downstream lock chamber is about to reach full capacity or the pilotway is congested during a certain period, the declaration window in that direction will be restricted or closed. For vessel types with high passage efficiency and high priority, a dedicated declaration period or green channel will be opened. During severe weather or equipment maintenance, the declaration capacity will be automatically reduced and the time period distribution will be adjusted.

[0010] Preferably, step S5 includes the following specific steps: S501. Integrate the passage priority score of each vessel with the adjusted claimable time slots, that is, assign the corresponding claimable time slots to each vessel in descending order of priority score to obtain the integrated dataset. S502. The integrated dataset is synchronized to a unified network cloud platform, and the optimal linkage is predicted through a pre-trained neural network model to generate a lock operation scheduling scheme that includes the lock passage sequence, suggested arrival time, designated lock chamber, and upstream and downstream coordination instructions.

[0011] A lock operation scheduling system based on big data analysis, the lock operation scheduling system comprising: The data analysis module is used to acquire historical lock operation data and identify traffic impact indicators to locate inefficient links in the process. These traffic impact indicators include lock passage time, congestion frequency, equipment failure records, and differences in lock passage efficiency due to severe weather or different types of vessels. The priority assessment module is used to obtain vessel information and its corresponding historical lock passage records, and to assess the passage priority score of each vessel. The dynamic identification module is used to obtain the real-time navigation status of the lock through a satellite positioning system or camera system, dynamically adjust the interval time, and identify the congestion points in the current lock area based on the real-time navigation status of the lock within the interval time. The strategy adjustment module is used to set an adjustment strategy for the declareable time period by combining inefficient links and congestion points in the current lock area. It adjusts the initial declareable time period of the lock to obtain the adjusted declareable time period. The linkage scheduling module is used to coordinate upstream and downstream locks through the network cloud platform based on the priority scores of each vessel and the adjusted time slots that can be declared, and generate a lock operation scheduling plan.

[0012] Compared with related technologies, the lock operation scheduling system and method based on big data analysis provided by this invention has the following beneficial effects: This invention achieves refined, dynamic, and intelligent lock scheduling by integrating big data analysis of historical operational data, vessel priority assessment, real-time navigation status monitoring, and intelligent prediction. This significantly improves overall traffic efficiency and effectively alleviates congestion in the lock area. Cluster analysis identifies inefficient processes, and spatial heat maps capture congestion points in real time. Dynamic adjustments to reporting time periods and intervals enhance the system's adaptability to load changes, severe weather, equipment failures, and other anomalies. Simultaneously, a priority scoring system is constructed based on multi-dimensional information such as vessel size, type, and historical behavior, enabling differentiated services and green channel support for high-priority vessels to ensure key transportation needs. Furthermore, a network cloud platform enables coordinated scheduling of upstream and downstream locks, and a neural network model generates optimized solutions including lock passage order, suggested arrival time, and coordination instructions to improve watershed navigation synergy. Attached Figure Description

[0013] Figure 1 This is a flowchart illustrating a lock operation scheduling method based on big data analysis according to the present invention. Figure 2 This is a system block diagram of a lock operation scheduling system based on big data analysis according to the present invention. Detailed Implementation

[0014] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0015] Example 1 like Figure 1 As shown, a lock operation scheduling method based on big data analysis includes the following steps: S1. Obtain historical lock operation data and identify traffic impact indicators to locate inefficient links in the process. Traffic impact indicators include lock passage time, congestion frequency, equipment failure records, severe weather, or differences in lock passage efficiency between different types of vessels. S2. Obtain vessel information and its corresponding historical lock passage records, and evaluate the passage priority score of each vessel; S3. Obtain the real-time navigation status of the lock through a satellite positioning system or camera system, dynamically adjust the interval time, and identify the congestion points in the current lock area based on the real-time navigation status of the lock within the interval time. S4. Combine inefficient links with congestion points in the current lock area to set up a strategy for adjusting the available time periods. Adjust the initial available time periods of the lock to obtain the adjusted available time periods. S5. Based on the priority scores of each vessel and the adjusted application time periods, the upstream and downstream locks are linked through the network cloud platform to generate a lock operation scheduling plan.

[0016] In the specific implementation process, step S1 includes the following steps: S101. Obtain historical lock operation data from the lock management system or ship registration system, including historical lock operation data, lock basic information, ship basic information, ship declaration information, and ship navigation status information.

[0017] Specifically, historical lock operation data is comprehensively collected from two data sources: the lock management system and the ship registration system. The lock management system records various key information during the lock's operation, such as the lock's opening and closing times, the number of ships that can be accommodated in the lock chamber after each opening, the operating status of the lock equipment (e.g., whether the gates open and close normally), and basic lock information such as the time of equipment failure and maintenance records. The ship registration system covers basic ship information, such as the ship's size, tonnage, type (including passenger ships, cargo ships, dangerous goods ships, etc.), and navigation route.

[0018] S102. From the historical lock operation data, statistical analysis is performed on lock passage time, congestion frequency, equipment failure records, differences in lock passage efficiency due to severe weather or different types of vessels, and the passage impact indicators are determined by using preset threshold ranges.

[0019] Specifically, from the massive historical lock operation data obtained in step S101, statistical methods are used to analyze key information such as lock passage time, congestion frequency, equipment failure records, and differences in lock passage efficiency under severe weather or for different types of vessels. This includes: for lock passage time, calculating the total time for each vessel from entering to leaving the lock area, and calculating the average lock passage time for different time periods (peak and off-peak hours) and for different types of vessels; for congestion frequency, analyzing the queue length and queue time within the lock area to determine the number of times congestion occurs within a certain period; regarding equipment failure records, statistically analyzing the frequency and type of failures in various equipment such as gates, hydraulic systems, and electrical systems; and in the analysis of differences in lock passage efficiency under severe weather or for different types of vessels, comparing the differences in lock passage time under severe weather conditions (such as heavy rain, strong winds, and dense fog) and normal weather conditions, as well as the lock passage efficiency of different types of vessels (such as large cargo ships and small passenger ships) under the same conditions. Then, these statistical results are divided according to preset threshold ranges to determine the traffic impact indicators. For example, the average gate passage time exceeding a set duration threshold, the congestion frequency reaching a set number of times threshold, and the equipment failure frequency exceeding a set percentage threshold can be set as indicators to determine whether traffic is affected.

[0020] In this embodiment, a large-scale ship lock analysis revealed that during peak hours (9:00 AM - 11:00 AM), the average passage time for cargo ships was 2 hours, while during off-peak hours (2:00 PM - 4:00 PM), the average passage time was 1 hour. For passenger ships, the average passage time during peak hours was 1.5 hours, and during off-peak hours, it was 0.8 hours. Regarding congestion frequency, statistics showed that on average, there were 3 instances per week where the queue length exceeded 50% of the lock chamber length, which was considered congestion. For equipment failure records, there were 5 gate failures and 3 hydraulic system failures in the past year. In severe weather analysis, the average passage time for ships during heavy rain increased by 30 minutes compared to normal weather. Regarding differences in passage efficiency between different types of ships, large cargo ships had a 20% lower passage efficiency than small passenger ships. Based on preset threshold ranges, such as an average passage time exceeding 1.8 hours, a weekly congestion frequency exceeding 2 times, and a gate failure frequency exceeding 3 times, these statistical results were categorized as traffic impact indicators.

[0021] S103. Based on the traffic impact indicators, analyze the lock operation process using cluster analysis and identify inefficient links.

[0022] Specifically, based on the determined traffic impact indicators, cluster analysis is used to conduct an in-depth analysis of the lock operation process. In this analysis, each stage of lock operation (such as vessel declaration, queuing, entering the lock chamber, lock chamber operation, and leaving the lock chamber) is treated as a data object. These stages are clustered according to the traffic impact indicators. By analyzing the clustering results, stages that show significant differences in traffic impact indicators compared to other stages are identified; these stages are considered inefficient. For example, if the average vessel passage time in a certain stage is significantly higher than in other stages, or if congestion occurs more frequently in that stage, then that stage can be judged as inefficient.

[0023] In this embodiment, cluster analysis is used to analyze the lock operation process. The various stages of lock operation are clustered according to indicators such as lock passage time and congestion frequency. Analysis revealed a significant difference between the ship queuing stage and other stages. In this stage, the average queuing time is long, especially during peak hours, often exceeding one hour, and the congestion frequency is high, with an average of two instances per week where the queue length exceeds 50% of the lock chamber length. Other stages, such as entering the lock chamber, lock chamber operation, and leaving the lock chamber, have relatively lower lock passage times and congestion frequencies. Therefore, the ship queuing stage can be identified as an inefficient stage in the lock operation process.

[0024] In the specific implementation process, step S2 includes the following steps: S201. Obtain information on each vessel preparing to pass through the lock from the vessel registration system or vessel declaration information, including vessel size, tonnage, type, and navigation route.

[0025] In this embodiment, a cargo ship A is preparing to pass through a certain lock. The lock management department obtains the ship's basic information through the ship registration system: length 120 meters, width 20 meters, depth 8 meters, gross tonnage 5,000 tons, type is bulk carrier, and its usual voyage route is from upstream port A to downstream port B. Meanwhile, the ship's declaration information indicates that it is carrying 3,000 tons of coal and is expected to arrive at the lock at 10:00 AM that day to apply for passage.

[0026] S202. Query the lock management system to obtain the previous lock passage records for each vessel, including the passage time, whether there have been any violations, and the passage efficiency.

[0027] Specifically, in this embodiment, a query of the lock management system revealed that cargo ship A passed through the lock a total of 10 times in the past year. On two occasions, the lock passage time was more than 30 minutes longer than the average time, due to the ship's unbalanced cargo load causing slow sailing speed; and on one occasion, a violation occurred, with the ship speeding within the lock area, which was recorded by the lock management department.

[0028] S203. Preset scoring dimensions and use a weighted summation method to calculate the passage priority score for each vessel.

[0029] Specifically, based on the actual needs and objectives of lock operation management, multiple scoring dimensions are preset, including vessel type, tonnage, past violations, and lock passage efficiency. According to the importance of each scoring dimension to lock operation scheduling, a weight is pre-set for each dimension. For each vessel, a score is assigned based on its performance in each scoring dimension. Then, the score for each dimension is multiplied by its corresponding weight, and finally, the weighted scores of all dimensions are summed to obtain the vessel's passage priority score. The formula for calculating the passage priority score is: Passage Priority Score = Σ (Score of each dimension × Weight of each dimension). The scoring of performance in each scoring dimension can be matched according to pre-set scoring rules. For example, a bulk carrier receives a score of 70 points; a vessel of 4000-6000 tons (a medium tonnage) receives a score of 70 points; 1-2 violations receive a score of 50 points; and for the lock passage efficiency dimension, 2-4 instances of low passage efficiency receive a score of 65 points.

[0030] In this embodiment, the four preset scoring dimensions—vessel type, tonnage, past violations, and lock passage efficiency—have weights of 0.2, 0.3, 0.2, and 0.3, respectively. For cargo ship A, as a bulk carrier, it receives 70 points for vessel type; 60 points for tonnage (5000 tons, considered medium tonnage); 50 points for one violation; and 65 points for three instances of long lock passage times and low efficiency. The priority score is calculated as follows: Priority Score = 70 × 0.2 + 60 × 0.3 + 50 × 0.2 + 65 × 0.3 = 61.5 points.

[0031] In the specific implementation process, step S3 includes the following steps: S301. Use satellite positioning system or camera system to monitor the distribution and flow of ships in the waters surrounding the lock, and obtain the current real-time navigation status of the lock, including the number of ships in the lock area and ship queuing information.

[0032] Specifically, in this embodiment, within a busy lock B, the monitoring center, through a satellite positioning system, detected a large cargo ship approaching the lock's approach channel from upstream at a normal speed. Simultaneously, several small passenger ships were queuing in the approach channel, waiting to pass through. Through a camera system, monitoring personnel observed a vessel slightly deviating from its course at the approach channel entrance due to improper operation, but this did not cause serious congestion. Based on the combined information from satellite positioning and the camera system, the monitoring center accurately grasped the distribution and flow of vessels in the waters surrounding the lock, determining that there were a total of 10 vessels in the lock area: 5 queuing in the approach channel, 3 waiting near the lock chamber, and 2 approaching the approach channel.

[0033] S302. Based on the real-time navigation status, analyze the current operating load of the lock and automatically adjust the interval time according to the current operating load of the lock. The higher the operating load, the longer the adjustment interval time, and the lower the operating load, the shorter the adjustment interval time.

[0034] Specifically, the operational load is measured by various indicators, including the number of vessels passing through the lock per unit time, the total tonnage of vessels inside the lock chamber, and the queue length of vessels in the pilot channel. These indicators are compared with preset standard values ​​to determine whether the current operational load of the lock is high or low. For example, if the number of vessels passing through the lock per unit time exceeds the preset average throughput, or if the queue length of vessels in the pilot channel exceeds the safe distance, the operational load is considered high. Based on the results of the operational load analysis, the lock's opening and closing intervals are automatically adjusted. When the operational load is high, it means there are many vessels in the waters surrounding the lock, requiring a longer interval to allow more vessels sufficient time and space to queue and prepare for passage. Conversely, when the operational load is low, the interval is shortened to improve the lock's utilization efficiency and reduce vessel waiting time.

[0035] In this embodiment, the preset standard is that the average number of ships passing through the lock per unit time is 5, and the queue length of ships in the pilot channel does not exceed 200 meters. The monitoring center detects that 8 ships are applying to pass through the lock per unit time, and the queue length in the pilot channel has reached 250 meters, indicating a high operational load. Therefore, the lock opening and closing interval is automatically extended from 30 minutes to 45 minutes. This allows ships in the pilot channel more time to queue in an orderly manner, preventing congestion from worsening due to overly frequent lock opening and closing. After a period of time, as some ships successfully pass through the lock, the number of ships applying to pass through the lock per unit time decreases to 3, and the queue length in the pilot channel shortens to 150 meters, reducing the operational load. Then, the interval is automatically shortened back to 30 minutes to improve the lock's operational efficiency.

[0036] S303. Based on the adjusted interval, the congestion points in the current gate area are identified using spatial heat map analysis.

[0037] Specifically, the vessel location information obtained in step S301 is combined with the adjusted interval time in step S302, and a spatial heat map of the waters surrounding the lock is generated using spatial heat map analysis software. It should be noted that the spatial heat map uses different colored areas to represent the density of vessels; the darker the color, the more vessels are in that area, and the greater the likelihood of congestion. For example, red areas indicate high vessel density, potentially leading to congestion; yellow areas indicate relatively dense vessel density, requiring attention; and green areas indicate sparse vessel distribution, with relatively smooth passage.

[0038] In the specific implementation process, the strategy for adjusting the time period that can be declared in step S4 is as follows: If the downstream lock chamber is about to reach full capacity or the pilotway is congested during a certain period, the declaration window in that direction will be restricted or closed. For vessel types with high passage efficiency and high priority, a dedicated declaration period or green channel will be opened. During severe weather or equipment maintenance, the declaration capacity will be automatically reduced and the time period distribution will be adjusted.

[0039] Specifically, the lock management system obtains real-time information on vessel berthing status in downstream lock chambers, queue length and density in the pilot channel, etc. A preset full-load threshold (the maximum number of vessels a downstream lock chamber can accommodate or the safe queue length in the pilot channel) is compared and analyzed with the real-time data. In this embodiment, when the number of vessels berthed in the downstream lock chamber reaches 80% of its maximum capacity, and the queue length in the pilot channel approaches 90% of the safe queue length, it is determined that the downstream lock chamber is about to reach full load or the pilot channel is congested. Upon determining that the downstream lock chamber is about to reach full load or the pilot channel is congested, an instruction is automatically sent to the vessel declaration system to restrict or close the declaration window for that direction. For vessels that have submitted declarations but have not yet been scheduled to pass through the lock, their declaration status is promptly notified of the change, and the vessels are advised to choose another time period or direction for declaration. For example, the declaration period originally open to downstream vessels from 9:00 AM to 11:00 AM is closed due to congestion in the downstream lock chamber and pilot channel, and relevant vessels are informed via SMS or push notification that they cannot declare during this period. During the daily operation of the locks, one or more time slots are specifically designated as dedicated reporting periods for these high-priority vessels. For example, 10:00-11:00 AM and 3:00-4:00 PM are designated as dedicated reporting periods for large container ships. At the same time, a green channel is set up at the lock site, allowing these vessels to pass through inspection and scheduling with priority when they arrive at the locks, reducing waiting time.

[0040] In the specific implementation process, step S5 includes the following steps: S501. Integrate the passage priority score of each vessel with the adjusted claimable time slots, that is, assign the corresponding claimable time slots to each vessel in descending order of priority score to obtain the integrated dataset.

[0041] Specifically, all vessels preparing to pass through the lock are sorted from highest to lowest according to their passage priority scores. Then, based on the adjusted available time slots, a corresponding available time slot is assigned to each vessel. The information of each vessel (including vessel name, number, size, tonnage, type, etc.), its passage priority score, and its assigned available time slot are integrated to form a complete dataset. This dataset will serve as a crucial basis for subsequent steps in generating the lock operation scheduling plan.

[0042] S502. The integrated dataset is synchronized to a unified network cloud platform, and the optimal linkage is predicted through a pre-trained neural network model to generate a lock operation scheduling scheme that includes the lock passage sequence, suggested arrival time, designated lock chamber, and upstream and downstream coordination instructions.

[0043] Specifically, the generated integrated dataset is synchronized to a unified cloud platform via a network interface. On the cloud platform, a pre-trained neural network model is used to analyze and predict the integrated dataset. It should be noted that this neural network model is trained using a large amount of historical lock operation data and actual scheduling cases. Based on the input vessel information, priority scores, and available time periods, it predicts the optimal lock linkage scheme. Based on the prediction results of the neural network model, a lock operation scheduling scheme is generated, which includes the vessel passage sequence, suggested arrival time, designated lock chamber, and upstream and downstream coordination instructions.

[0044] In this embodiment, in a busy lock area, there are 5 ships preparing to pass through the lock, namely A, B, C, D, and E. After calculation in step S2, their passage priority scores are as follows: ship A has 90 points, ship B has 85 points, ship C has 80 points, ship D has 75 points, and ship E has 70 points. After adjustments in step S4, the available time slots for declaration on that day are 9:00-11:00 AM and 2:00-4:00 PM. Based on priority scores from highest to lowest, available time slots are allocated to each vessel: Vessel A, with the highest priority, is allocated the 9:00-10:00 AM slot; Vessel B is allocated the 10:00-11:00 AM slot; Vessel C is allocated the 2:00-2:30 PM slot; Vessel D is allocated the 2:30-3:00 PM slot; and Vessel E is allocated the 3:00-4:00 PM slot. After synchronizing the integrated datasets of vessels A, B, C, D, and E to the network cloud platform, the neural network model performs predictions and analyses, generating the following scheduling plan: Based on priority scores and available time slots, the vessel passage order is determined as A, B, C, D, E; Vessel A is 50 kilometers from the lock and has a speed of 20 km / h, so it is recommended to depart at 8:30 AM and arrive at the lock at 9:00 AM; based on the lock's real-time operating status and the vessel's size and type, a lock chamber is assigned to each vessel. Vessel A is a large container ship and is designated to enter lock chamber No. 1 (large lock chamber); Vessel B is a medium-sized cargo ship and is designated to enter lock chamber No. 2 (medium-sized lock chamber). It should be noted that if a vessel is about to arrive at the upstream lock, the network cloud platform will send a coordination instruction to the downstream lock, informing it to prepare to receive the vessel and ensuring a smooth connection between the upstream and downstream locks.

[0045] Example 2 like Figure 2 As shown, a lock operation scheduling system based on big data analysis, which applies a lock operation scheduling method based on big data analysis, specifically includes: The data analysis module is used to acquire historical lock operation data and identify traffic impact indicators to locate inefficient links in the process. These traffic impact indicators include lock passage time, congestion frequency, equipment failure records, and differences in lock passage efficiency due to severe weather or different types of vessels. The priority assessment module is used to obtain vessel information and its corresponding historical lock passage records, and to assess the passage priority score of each vessel. The dynamic identification module is used to obtain the real-time navigation status of the lock through a satellite positioning system or camera system, dynamically adjust the interval time, and identify the congestion points in the current lock area based on the real-time navigation status of the lock within the interval time. The strategy adjustment module is used to set an adjustment strategy for the declareable time period by combining inefficient links and congestion points in the current lock area. It adjusts the initial declareable time period of the lock to obtain the adjusted declareable time period. The linkage scheduling module is used to coordinate upstream and downstream locks through the network cloud platform based on the priority scores of each vessel and the adjusted time slots that can be declared, and generate a lock operation scheduling plan.

[0046] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0047] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0048] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

Claims

1. A lock operation scheduling method based on big data analysis, characterized in that, The lock operation scheduling method includes the following steps: S1. Obtain historical lock operation data and identify traffic impact indicators to locate inefficient links in the process. Traffic impact indicators include lock passage time, congestion frequency, equipment failure records, severe weather, or differences in lock passage efficiency between different types of vessels. S2. Obtain vessel information and its corresponding historical lock passage records, and evaluate the passage priority score of each vessel; S3. Obtain the real-time navigation status of the lock through a satellite positioning system or camera system, dynamically adjust the interval time, and identify the congestion points in the current lock area based on the real-time navigation status of the lock within the interval time. S4. Combine inefficient links with congestion points in the current lock area to set up a strategy for adjusting the available time periods. Adjust the initial available time periods of the lock to obtain the adjusted available time periods. S5. Based on the priority scores of each vessel and the adjusted application time periods, the upstream and downstream locks are linked through the network cloud platform to generate a lock operation scheduling plan.

2. The lock operation scheduling method based on big data analysis according to claim 1, characterized in that, The specific steps of step S1 include: S101. Obtain historical lock operation data from the lock management system or ship registration system, including historical lock operation data, lock basic information, ship basic information, ship declaration information, and ship navigation status information. S102. From the historical lock operation data, statistical analysis is performed on lock passage time, congestion frequency, equipment failure records, differences in lock passage efficiency due to severe weather or different types of vessels, and the passage impact indicators are determined by using preset threshold ranges. S103. Based on the traffic impact indicators, analyze the lock operation process using cluster analysis and identify inefficient links.

3. The lock operation scheduling method based on big data analysis according to claim 1, characterized in that, The specific steps of step S2 include: S201. Obtain information on each vessel preparing to pass through the lock from the vessel registration system or vessel declaration information, including vessel size, tonnage, type, and navigation route; S202. Query the lock management system to obtain the previous lock passage records for each vessel, including the passage time, whether there have been any violations, and the passage efficiency. S203. Preset scoring dimensions and use a weighted summation method to calculate the passage priority score for each vessel.

4. The lock operation scheduling method based on big data analysis according to claim 1, characterized in that, The specific steps of step S3 include: S301. Use satellite positioning system or camera system to monitor the distribution and flow of ships in the waters surrounding the lock, and obtain the current real-time navigation status of the lock, including the number of ships in the lock area and ship queuing information. S302. Based on the real-time navigation status, analyze the current operating load of the lock and automatically adjust the interval time according to the current operating load of the lock. The higher the operating load, the longer the adjustment interval time, and the lower the operating load, the shorter the adjustment interval time. S303. Based on the adjusted interval, the congestion points in the current gate area are identified using spatial heat map analysis.

5. The lock operation scheduling method based on big data analysis according to claim 1, characterized in that, The specific strategy for adjusting the eligible time period mentioned in step S4 is as follows: If the downstream lock chamber is about to reach full capacity or the pilotway is congested during a certain period, the declaration window in that direction will be restricted or closed. For vessel types with high passage efficiency and high priority, a dedicated declaration period or green channel will be opened. During severe weather or equipment maintenance, the declaration capacity will be automatically reduced and the time period distribution will be adjusted.

6. The lock operation scheduling method based on big data analysis according to claim 1, characterized in that, The specific steps of step S5 include: S501. Integrate the passage priority score of each vessel with the adjusted claimable time slots, that is, assign the corresponding claimable time slots to each vessel in descending order of priority score to obtain the integrated dataset. S502. The integrated dataset is synchronized to a unified network cloud platform, and the optimal linkage is predicted through a pre-trained neural network model to generate a lock operation scheduling scheme that includes the lock passage sequence, suggested arrival time, designated lock chamber, and upstream and downstream coordination instructions.

7. A lock operation scheduling system based on big data analysis, employing a lock operation scheduling method based on big data analysis as described in any one of claims 1-6, characterized in that, The lock operation scheduling system includes: The data analysis module is used to acquire historical lock operation data and identify traffic impact indicators to locate inefficient links in the process. These traffic impact indicators include lock passage time, congestion frequency, equipment failure records, and differences in lock passage efficiency due to severe weather or different types of vessels. The priority assessment module is used to obtain vessel information and its corresponding historical lock passage records, and to assess the passage priority score of each vessel. The dynamic identification module is used to obtain the real-time navigation status of the lock through a satellite positioning system or camera system, dynamically adjust the interval time, and identify the congestion points in the current lock area based on the real-time navigation status of the lock within the interval time. The strategy adjustment module is used to set an adjustment strategy for the declareable time period by combining inefficient links and congestion points in the current lock area. It adjusts the initial declareable time period of the lock to obtain the adjusted declareable time period. The linkage scheduling module is used to coordinate upstream and downstream locks through the network cloud platform based on the priority scores of each vessel and the adjusted time slots that can be declared, and generate a lock operation scheduling plan.

Images