Maritime port operation efficiency optimization method and device, electronic equipment and medium
By synchronizing, weighting, and cleaning multi-source data from maritime ports, and using key optimization point prediction and time series analysis, port scheduling optimization strategies are generated, solving the problem of multi-source data integration and improving port operation efficiency.
Patent Information
- Application Number
- CN202410952575.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-19
AI Technical Summary
Existing technologies struggle to effectively integrate and utilize various types of data from different data sources, resulting in limited optimization effects of port scheduling optimization strategies.
By synchronizing and weighting multi-source port data over time, cleaning and integrating the data, and using a well-trained maritime port operation efficiency optimization model to predict key optimization points and perform time-series analysis, port scheduling optimization strategies are generated.
It enables the comprehensive consideration and application of multi-source data, improves the effectiveness of port operation scheduling optimization strategies, and enhances port operation efficiency.
Smart Images

Figure CN118982170A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of port dispatching, and in particular to a method, device, electronic equipment and medium for optimizing the operating efficiency of a maritime port. Background Art
[0002] In the operation and management of maritime ports, a reasonable scheduling strategy is the key to ensuring the efficiency of port operations. Existing maritime port scheduling strategy planning is generally divided into manual scheduling methods and deep learning methods. Manual scheduling methods generally rely on experience and historical data for planning, but it is usually difficult to respond to emergencies and changes in real-time data in real time, resulting in delayed or inaccurate decision-making. Deep learning uses a prediction model to predict the corresponding scheduling plan based on the port's operating data. Compared with manual scheduling, the timeliness and accuracy of decision-making by deep learning methods are improved.
[0003] However, the operation and management of maritime ports are often affected by many complex factors, such as possible delays in the arrival of ships, the impact of wind speed in the port area, and the different efficiencies of loading and unloading of different types of cargo. These data usually come from different data sources. Existing deep learning methods often find it difficult to reasonably integrate and utilize various types of data from different data sources in scheduling planning, and are unable to give full play to the application potential of various types of data in optimization decision-making, resulting in limited optimization effects of the obtained port scheduling optimization strategy.
[0004] Therefore, in the planning of port operation scheduling strategies, the existing technology is difficult to reasonably integrate and utilize various types of data from different data sources, and is unable to give full play to the application potential of various types of data obtained in optimization decision-making, and the optimization effect of the obtained port scheduling optimization strategy is limited. Summary of the invention
[0005] In view of this, it is necessary to provide a method, device, electronic equipment and medium for optimizing maritime port operational efficiency, which are used to solve the technical problems in the existing technology that it is difficult to reasonably integrate and utilize various types of data from different data sources, cannot give full play to the application potential of various types of data obtained in optimization decision-making, and the optimization effect of the obtained port scheduling optimization strategy is limited.
[0006] In order to solve the above problems, on the one hand, the present invention provides a method for optimizing the operating efficiency of a maritime port, comprising: The acquired port multi-source data is time synchronized and weighted to obtain weighted multi-source data, and the weighted multi-source data is cleaned and integrated to obtain port integrated data; The port integration data is input into a well-trained maritime port operation efficiency optimization model, and the key optimization points of the port integration data are predicted to obtain the operation data to be optimized. The time series analysis and prediction of the operation data to be optimized are performed to obtain the operation pressure prediction results and the adjustment demand prediction results. The port scheduling optimization strategy is generated according to the operation pressure prediction results and the adjustment demand prediction results.
[0007] In one possible implementation, the port multi-source data includes vessel data, cargo data, environmental data and loading and unloading data. The vessel data includes the vessel position and vessel speed. The cargo data includes the cargo number, cargo weight and cargo destination. The environmental data includes temperature, humidity and wind speed environmental parameters. The loading and unloading data includes the type of loading and unloading activities, loading and unloading time and loading and unloading information.
[0008] In a possible implementation, the acquired port multi-source data is time synchronized and weighted to obtain weighted multi-source data, including: Obtain the clock errors between various types of data sources in the port multi-source data, and establish a time synchronization function based on the clock errors; Determine the importance score of each data type in the port multi-source data based on historical data analysis, application value analysis and operational data feedback, and determine the data weight of each data type in the port multi-source data based on the importance score; The multi-source data of the port are time synchronized according to the time synchronization function, and the multi-source data of the port are weighted according to the data weight to obtain weighted multi-source data.
[0009] In a possible implementation, the weighted multi-source data is cleaned and integrated to obtain port integrated data, including: Based on the data lake architecture, weighted multi-source data is integrated to obtain integrated port operation data; The integrated port operation data is cleaned and transformed to obtain the port integrated data.
[0010] In a possible implementation, key optimization points are predicted for port integrated data to obtain operation data to be optimized, including: Extract key features from port integrated data to obtain operational feature data; Perform feature mapping on the operation feature data to obtain event mapping features, and cluster similar event mapping features to obtain operation mode groups; The key optimization points are predicted based on the operation mode groups and port integration data to obtain the key operation periods, and the operation data to be optimized is determined based on the key operation periods and port integration data.
[0011] In a possible implementation, the operation data to be optimized is subjected to time series analysis and prediction to obtain operation pressure prediction results and adjustment demand prediction results, including: Perform time series forecasting of operation pressure according to the operation data to be optimized to obtain the operation pressure forecast result; The external impact is estimated based on the operational data to be optimized to obtain the adjusted demand forecast results.
[0012] In a possible implementation, a port scheduling optimization strategy is generated according to the operation pressure forecast result and the adjustment demand forecast result, including: Based on the operational pressure forecast results and the adjusted demand forecast results, port scheduling optimization calculations are performed to obtain the optimal ship arrival sequence, optimal ship departure sequence and cargo loading and unloading priority.
[0013] On the other hand, the present invention also provides a device for optimizing the operation efficiency of a maritime port, comprising: A data integration unit is used to perform time synchronization and weight distribution on the acquired port multi-source data to obtain weighted multi-source data, and to perform data cleaning and integration on the weighted multi-source data to obtain port integrated data; The scheduling optimization unit is used to input the port integration data into a well-trained maritime port operation efficiency optimization model, predict the key optimization points of the port integration data to obtain the operation data to be optimized, predict the port operation pressure of the operation data to be optimized to obtain the operation pressure prediction results and the adjustment demand prediction results, and generate the port scheduling optimization strategy according to the operation pressure prediction results and the adjustment demand prediction results.
[0014] On the other hand, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned method for optimizing the operating efficiency of a maritime port is implemented.
[0015] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned method for optimizing the operating efficiency of a maritime port is implemented.
[0016] The beneficial effect of adopting the above-mentioned implementation method is: the present invention reasonably integrates multi-source port data from different sources through time synchronization, weight allocation and data cleaning integration, analyzes and utilizes the integrated data through key optimization point prediction and time series analysis prediction, and can realize comprehensive consideration and application of multi-source data in port operation scheduling optimization, give full play to the potential of data from various sources in optimization decision-making, improve the optimization effect of scheduling optimization strategy, and thus improve port operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0018] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for optimizing the operating efficiency of a maritime port provided by the present invention; Figure 2 A schematic diagram of a process of time synchronization and weight allocation of multi-source port data according to an embodiment of the present invention; Figure 3 A schematic diagram of a process of data cleaning and integration according to an embodiment of the present invention; Figure 4 A schematic diagram of a process for predicting key optimization points in an embodiment of the present invention; Figure 5 A schematic diagram of the process flow of the timing analysis prediction of the present invention; Figure 6 A schematic structural diagram of an embodiment of a device for optimizing maritime port operation efficiency provided by the present invention; Figure 7 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0020] It should be understood that the drawings of the schematic diagrams are not drawn to scale. The flow charts used in the present invention illustrate the operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flow charts may be implemented out of order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flow charts, or may remove one or more operations from the flow charts, under the guidance of the content of the present invention.
[0021] Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.
[0022] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0023] Figure 1 A flow chart of an embodiment of a method for optimizing the operating efficiency of a maritime port provided by the present invention is shown in FIG. Figure 1 As shown in the figure, the methods for optimizing the efficiency of maritime port operations include: S101, performing time synchronization and weight distribution on the acquired port multi-source data to obtain weighted multi-source data, and performing data cleaning and integration on the weighted multi-source data to obtain port integrated data; S102. Input the port integration data into a well-trained maritime port operation efficiency optimization model, predict key optimization points of the port integration data to obtain the operation data to be optimized, perform time series analysis and prediction on the operation data to be optimized to obtain the operation pressure prediction results and the adjustment demand prediction results, and generate a port scheduling optimization strategy based on the operation pressure prediction results and the adjustment demand prediction results.
[0024] Compared with the prior art, the present invention reasonably integrates multi-source port data from different sources through time synchronization, weight allocation and data cleaning integration, and analyzes and utilizes the integrated data through key optimization point prediction and time series analysis prediction. It can realize the comprehensive consideration and application of multi-source data in port operation scheduling optimization, give full play to the potential of data from various sources in optimization decision-making, improve the optimization effect of scheduling optimization strategy, and thus improve port operation efficiency.
[0025] In some embodiments of the present invention, the port multi-source data includes vessel data, cargo data, environmental data and loading and unloading data. The vessel data includes the vessel position and the vessel speed. The cargo data includes the cargo number, cargo weight and cargo destination. The environmental data includes temperature, humidity and wind speed environmental parameters. The loading and unloading data includes the type of loading and unloading activities, loading and unloading time and loading and unloading information.
[0026] Specifically, port multi-source data includes relevant data from multiple data sources such as ship data, cargo data, environmental data, and loading and unloading data.
[0027] The ship data includes the ship position and ship speed. The ship position is provided by the satellite positioning system, and the ship speed is provided by the ship's own speed sensor. The data is formatted as time series data. :
[0028] in, Indicates that from Position data received from satellites, Indicates that from The sum of the squares of the speed data collected by the speed sensors is used to calculate the vector composite value of the speed. Indicates the number of data collection sources, that is, the number of satellites or sensors.
[0029] The cargo data is automatically identified by radio frequency identification technology for each cargo entering and leaving the port, including the cargo ID number, cargo weight and cargo destination. The data set is recorded as :
[0030] in, Indicates The goods are in The weight of each monitoring point, represents a set of possible destinations, and the final destination is determined by intersection. is the number of detection points.
[0031] Environmental data is monitoring data collected from IoT devices in various regions, including temperature, humidity, and wind speed environmental parameters. The data is collected as an environmental data set. :
[0032] in, is the type of environmental parameter monitored, Indicates at different times The environmental parameter values for all The values in are averaged to obtain the average environmental state for each parameter.
[0033] The loading and unloading data is obtained by analyzing the video of the loading and unloading activities of ships and cargoes through the visual recognition system, and the activity type, loading and unloading time and loading and unloading information are extracted from it to form a video analysis data set. :
[0034] in, Indicates at time Type of activity identified The frequency of Indicates activity Loading and unloading involved , It represents the number of loads and unloads identified during the period, and the average load and unload characteristics of the activity are represented by the average.
[0035] In some embodiments of the present invention, Figure 2 FIG. 1 is a flow chart of time synchronization and weight allocation of multi-source port data according to an embodiment of the present invention. Figure 2 As shown, the acquired port multi-source data is synchronized in time and weighted to obtain weighted multi-source data, including: S201, obtaining the clock error between various types of data sources in the port multi-source data, and establishing a time synchronization function according to the clock error; S202, determining the importance score of each data type in the port multi-source data based on historical data analysis, application value analysis and operational data feedback, and determining the data weight of each data type in the port multi-source data according to the importance score; S203, time synchronization is performed on the port multi-source data according to the time synchronization function, and weights are assigned to the port multi-source data according to the data weights to obtain weighted multi-source data.
[0036] Specifically, before integrating the data obtained from various data sources, considering that different data sources may have inconsistent timestamp standards for recorded data due to their internal clocks or network delays, in order to ensure that the data from different data sources can be accurately integrated according to a unified timing standard during integration, these timestamps need to be synchronized first. To this end, the embodiment defines a time synchronization function:
[0037] in, Represents the original data time label, Indicates the time adjustment required to synchronize to a unified timing standard, determined by the clock error between various types of data sources. For example, the satellite system of a ship records the arrival time of the ship as , while the RF scanning system records the start time of cargo loading and unloading as , and it is known that In line with the unified timing standard, the data recorded by the satellite system is delayed by 10 seconds compared to the RF scanning system. Corresponding time adjustment The value of In this way, the embodiment can unify the timing standard of data obtained from all data sources.
[0038] In addition, considering that data from different sources have different importance in port operation decisions, the embodiment also analyzes the importance of different data types and sets different weights. First, the embodiment analyzes the importance of data through historical data analysis, application value analysis, and operational data feedback. Among them, historical data analysis uses historical data to analyze the influence and accuracy of each data type in past operational decisions. For example, if satellite positioning data plays a key role in avoiding or reducing ship delays, this data type is considered to be of high importance. Application value analysis is to evaluate the application value and reliability of different data types in daily operations management by port operation experts based on industry research experience. Operational data feedback is to collect feedback in real-time operations and analyze the contribution of different data types to emergency response capabilities.
[0039] After determining the importance of each data type, the embodiment assigns weights using the following formula:
[0040] in, represents the importance score of the data, and is the adjustment parameter of the curve shape, The weight of the data type.
[0041] Embodiment Through the above evaluation, importance scores of 0.9, 0.8, 0.6 and 0.7 are assigned to vessel data, cargo data, environmental data and loading and unloading data respectively. Set to 0.5, parameter It is set to 1.5 to obtain the weight value of each source data type and to distribute the weights of the multi-source data of the port.
[0042] In some embodiments of the present invention, Figure 3 FIG. 1 is a flow chart of data cleaning and integration according to an embodiment of the present invention. Figure 3 As shown in the figure, the weighted multi-source data is cleaned and integrated to obtain the port integrated data, including: S301. Integrate weighted multi-source data based on the data lake architecture to obtain integrated port operation data; S302, performing data cleaning and data transformation and integration on the integrated port operation data to obtain port integrated data.
[0043] Specifically, in order to reasonably utilize data from different data sources, it is necessary to clean and transform each data. First, the embodiment integrates and manages data in various formats and sources through the data lake architecture. , and respond to data query and update requests in real time through data lake architecture access and analysis. The data lake architecture formula is expressed as:
[0044] in, Indicates at time and type The data lake integration results below, Indicates Class data, is a weight factor assigned based on the importance of the data source, is the time synchronization function, is the total number of data sources.
[0045] Then, the embodiment performs data cleaning on the data integrated through the data lake architecture. Data cleaning includes identifying and deleting duplicate data records, and correcting format errors and inconsistencies in the data. The formula is expressed as:
[0046] in, Represents a detection data item Is it a duplicate record? Indicates confirmation data item format consistency.
[0047] Then the embodiment performs data transformation and integration through data transformation technology, and the integration operation formula is expressed as:
[0048] in, Indicates the integrated port data. Represents a data integration operation, Indicates Class data conversion functions apply specific data processing logic and format standards to different types of data. Based on data type The weights are used to balance the contributions of different data. are the parameters of the conversion function, adjusting the details of data processing, Indicates the total number of data types that need to be integrated.
[0049] In the data transformation technology, for quantitative data, such as the deadweight of a ship and the volume of cargo, the embodiment uses the Z-score standardization method for standardization. For timestamps in different formats, the embodiment converts all time data into a unified standard format (ISO 8601) and ensures that all timestamps are converted to the same time zone. In addition, for missing data, if the missing data is sequence data, such as environmental monitoring data, the embodiment uses the interpolation method of the time series to fill in the missing values. If the missing data is non-sequential data, the embodiment uses the mean or median of the data set to fill it. For outliers, the embodiment uses the IQR (interquartile range) method to identify outliers and replace them with the median of the corresponding variable.
[0050] The integration operation sorts and connects time series data according to timestamps. For data with the same timestamp but different sources, such as satellite positioning data and RFID cargo data, data fusion technology is used to merge them according to their importance weights.
[0051] In some embodiments of the present invention, Figure 4 Schematic diagram of the key optimization point prediction process of an embodiment of the present invention, such as Figure 4 As shown in the figure, the key optimization points of the port integration data are predicted to obtain the operation data to be optimized, including: S401, extracting key features from the port integration data to obtain operation feature data; S402, performing feature mapping on the operation feature data to obtain event mapping features, and clustering similar event mapping features to obtain operation mode groups; S403, predicting key optimization points based on the operation mode group and the port integration data to obtain key operation periods, and determining the operation data to be optimized based on the key operation periods and the port integration data.
[0052] Specifically, the maritime port operation efficiency optimization model in the embodiment consists of three parts: key optimization point prediction, time series analysis prediction and port scheduling optimization strategy planning. Each part uses a different model to process and predict the port integrated data.
[0053] First, the embodiment configures and trains the machine learning model To process port integration data And extract key features, machine learning model The training formula can be expressed as:
[0054] in, Represents the training data set, including feature vectors and output target , is the number of training samples. The training data is obtained by integrating the historical data in the same way as above.
[0055] After extracting the operational feature data of the port integration data, the embodiment uses a deep learning method to perform feature analysis on the data features. The embodiment first constructs a deep learning network to perform feature mapping on the operational events in the operational feature data to obtain event mapping features, wherein the deep neural network includes multiple convolutional layers, pooling layers, and fully connected layers, and the network structure is represented as follows:
[0056] in, Indicates that it is applied to data The convolutional layer, is the activation function, represents the pooling layer, Indicates that the pooled data is passed to the fully connected layer.
[0057] The deep neural network training process uses the back propagation algorithm to optimize the weights, and the formula is expressed as:
[0058] in, represents the old value of the model parameter, represents the new value of the model parameter, is the loss function About Model Parameters The gradient of The network is the input predictions, is the actual label.
[0059] In the embodiment, the formula for obtaining event mapping features by performing feature mapping on the operation feature data through a deep learning network is expressed as:
[0060] in, is the event mapping feature, represents a deep learning network, Indicates The characteristic function of the layer network output, Indicates the number of network layers.
[0061] At the same time, the embodiment also uses image processing algorithms to extract abnormal events from the corresponding data of the processed videos of the loading and unloading activities of ships and cargoes, and identifies non-standard operations and potential risks.
[0062] Then the embodiment also performs a deep cluster analysis on the event mapping features, automatically groups similar operation modes, and obtains operation mode groups, which are expressed as follows:
[0063] in, Represents the operation mode groups classified according to event mapping characteristics, represents the clustering function, is the clustering threshold used to decide when an operation mode should be considered as an independent group.
[0064] The final example designs an improved prediction model , based on the results of deep learning analysis, predict the potential efficiency improvement points and key influencing factors of maritime port operations.
[0065] Prediction Model It is an integrated learning model that combines multiple different types of algorithms. The formula is as follows:
[0066] in, Represents the deep learning network The extracted feature set, represents the prediction output of random forest, represents the predicted output of the gradient boosting machine, represents the prediction output of the deep neural network, , and represents the output weight parameters of random forest, gradient boosting machine and neural network, Adjust parameters for output.
[0067] Among them, the random forest part The formula is:
[0068] in, Indicates The prediction results of the tree, Represents the number of trees in the forest.
[0069] Gradient boosting machine part The formula is:
[0070] in, Indicates The weights of the weak learners, It is to increase the number of iterations.
[0071] Deep neural network part The formula is:
[0072] in, Indicates The network parameters of the layer, Represents the activation function.
[0073] Embodiment: A prediction model combining different types of algorithms , predict the busiest key operating period of the port, and use this feature data set to determine the operating data to be optimized corresponding to the key operating period.
[0074] In some embodiments of the present invention, Figure 5 The flowchart of the timing analysis prediction of the present invention is as follows: Figure 5 As shown, the operation data to be optimized is subjected to time series analysis and forecasting to obtain the operation pressure forecast results and the adjustment demand forecast results, including: S501, performing time series forecasting of operation pressure according to the operation data to be optimized to obtain an operation pressure forecast result; S502. Estimate external impacts based on the operational data to be optimized to obtain an adjusted demand forecast result.
[0075] Specifically, according to the results of the key optimization point prediction, the embodiment constructs a dynamic prediction model Used to predict operational pressure, cargo throughput and service demand in different time periods that need to be optimized. Dynamic forecasting model The forecast is made by considering multiple factors including weather conditions, ship arrival delays and changes in market demand. The formula of the dynamic forecast model is expressed as:
[0076] in, represents the input feature vector, which is the operation data to be optimized obtained from the key optimization point prediction step. is the index or identifier of the forecast time period, It is Model characteristic function Parameters, Represents a processing function. The function type is determined according to the specific application object, including nonlinear transformation and Fourier transform to process periodic and non-periodic patterns.
[0077] Dynamic prediction model In the paper, time series analysis technology is introduced to predict operational pressure and cargo throughput, and the formula is expressed as:
[0078] in, Indicates at time The operational pressure forecast results are: Indicates that time delay is taken into account No. input features, It is for The transformation functions corresponding to the features include logarithmic transformation and exponential smoothing. are the parameters of the transformation function, represents the error term, which is used to capture the randomness not explained in the model.
[0079] Dynamic prediction model In the forecast, the service demand adjustment caused by external factors such as weather changes and ship delays is also predicted. The estimation of weather and delay effects is adjusted using regression analysis, and the formula is expressed as:
[0080] in, The table shows the adjusted demand forecast results due to weather conditions and ship impacts. Indicates at time weather conditions, Indicates at time The vessel delay time, and functions that represent weather conditions and vessel impact times, including polynomial or exponential response curves, represents the error term, capturing the part not explained by the model.
[0081] Then the prediction results of each part are integrated to get the final prediction model :
[0082] in, It represents the final forecast after comprehensive consideration of operational pressure and external factors. is a kernel function used to evaluate historical data For current forecasts The impact of Indicates at time Incremental forecast.
[0083] In some embodiments of the present invention, a port scheduling optimization strategy is generated according to the operation pressure forecast result and the adjustment demand forecast result, including: Based on the operational pressure forecast results and the adjusted demand forecast results, port scheduling optimization calculations are performed to obtain the optimal ship arrival sequence, optimal ship departure sequence and cargo loading and unloading priority.
[0084] Finally, the embodiment performs scheduling optimization calculations through a decision model based on the predicted operating pressure forecast results and the adjusted demand forecast results, and automatically generates suggestions for ship scheduling, cargo loading and unloading priority ranking, and resource reallocation plans. The decision model formula is expressed as follows:
[0085] in, Represents relevant data inputs for port operations, such as vessel arrival times, cargo information, and resource status, It is A decision function of 2 decision factors is proposed, involving cargo priority, resource allocation, and vessel scheduling.
[0086] The embodiment optimizes the ship scheduling suggestions based on real-time data and historical data analysis, and calculates the optimal ship arrival and departure sequence through an optimization algorithm:
[0087] in, Indicates the scheduled arrival and departure times of the vessel. It's in time Ship dispatch plan, Represents an optimization algorithm.
[0088] Then the embodiment according to The predicted throughput and The output of the automatic adjustment of cargo handling priorities includes adjusting the order in which cargo is handled, including type, weight and destination.
[0089] In summary, the present invention reasonably integrates multi-source port data from different sources through time synchronization, weight allocation and data cleaning integration, and analyzes and utilizes the integrated data through key optimization point prediction and time series analysis prediction, so as to realize the comprehensive consideration and application of multi-source data in port operation scheduling optimization, give full play to the potential of data from various sources in optimization decision-making, improve the optimization effect of scheduling optimization strategy, and thus improve port operation efficiency.
[0090] Based on the maritime port operation efficiency optimization method provided by the present invention, the present invention also provides a maritime port operation efficiency optimization device 600, such as Figure 6 As shown, including: The data integration unit 601 is used to perform time synchronization and weight distribution on the acquired port multi-source data to obtain weighted multi-source data, and perform data cleaning and integration on the weighted multi-source data to obtain port integrated data; The scheduling optimization unit 602 is used to input the port integration data into a well-trained maritime port operation efficiency optimization model, predict the key optimization points of the port integration data to obtain the operation data to be optimized, predict the port operation pressure of the operation data to be optimized to obtain the operation pressure prediction results and the adjustment demand prediction results, and generate a port scheduling optimization strategy based on the operation pressure prediction results and the adjustment demand prediction results.
[0091] The maritime port operation efficiency optimization device 600 provided in the above embodiment can implement the technical solution described in the above embodiment of the maritime port operation efficiency optimization method. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above embodiment of the maritime port operation efficiency optimization method, which will not be repeated here.
[0092] The present invention also provides an electronic device 700, such as Figure 7 As shown, Figure 7 This is a structural diagram of an embodiment of an electronic device provided by the present invention. The electronic device 700 includes a processor 701, a memory 702, and a computer program stored in the memory 702 and executable on the processor 701. When the processor 701 executes the program, the above-mentioned method for optimizing the operating efficiency of a maritime port is implemented.
[0093] As a preferred embodiment, the electronic device further includes a display 703 for displaying the process of the processor 701 executing the method for optimizing the maritime port operation efficiency.
[0094] Among them, the processor 701 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 701 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC). It can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may also be a microprocessor or the processor may also be any conventional processor, etc.
[0095] The memory 702 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a secure digital (SD card), a flash card, etc. The memory 702 is used to store programs, and the processor 701 executes the program after receiving the execution instruction. The process definition method disclosed in any of the embodiments of the present invention may be applied to the processor 701 or implemented by the processor 701.
[0096] The display 703 may be an LED display screen, a liquid crystal display, or a touch-sensitive display, etc. The display 703 is used to display various information of the electronic device 700 .
[0097] Understandably, Figure 7 The structure shown is only a schematic diagram of the structure of the electronic device 700. The electronic device 700 may also include Figure 7 More or fewer components as shown. Figure 7 Each component shown in the figure can be implemented by hardware, software or a combination thereof.
[0098] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for optimizing the operating efficiency of a maritime port.
[0099] Generally speaking, the computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable media except for the signal itself that is temporarily propagating.
[0100] Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.
[0101] The above are only preferred specific implementations of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.
Claims
1. A method for optimizing the operating efficiency of a maritime port, characterized in that: include: Performing time synchronization and weight distribution on the acquired port multi-source data to obtain weighted multi-source data, and performing data cleaning and integration on the weighted multi-source data to obtain port integrated data; The port integration data is input into a well-trained maritime port operation efficiency optimization model, key optimization points of the port integration data are predicted to obtain the operation data to be optimized, time series analysis and prediction are performed on the operation data to be optimized to obtain operation pressure prediction results and adjustment demand prediction results, and a port scheduling optimization strategy is generated according to the operation pressure prediction results and the adjustment demand prediction results.
2. The method for optimizing the operating efficiency of a maritime port according to claim 1, characterized in that: The port multi-source data includes vessel data, cargo data, environmental data and loading and unloading data. The vessel data includes vessel position and vessel speed. The cargo data includes cargo number, cargo weight and cargo destination. The environmental data includes temperature, humidity and wind speed environmental parameters. The loading and unloading data includes loading and unloading activity type, loading and unloading time and loading and unloading information.
3. The method for optimizing the operating efficiency of a maritime port according to claim 1, characterized in that: The method of performing time synchronization and weight distribution on the acquired port multi-source data to obtain weighted multi-source data includes: Obtaining clock errors between various types of data sources in the port multi-source data, and establishing a time synchronization function according to the clock errors; Determine the importance score of each data type in the port multi-source data based on historical data analysis, application value analysis and operational data feedback, and determine the data weight of each data type in the port multi-source data according to the importance score; The port multi-source data is time synchronized according to the time synchronization function, and the port multi-source data is weighted according to the data weight to obtain weighted multi-source data.
4. The method for optimizing the operating efficiency of a maritime port according to claim 1, characterized in that: The step of cleaning and integrating the weighted multi-source data to obtain port integrated data includes: Based on the data lake architecture, the weighted multi-source data is integrated to obtain integrated port operation data; The integrated port operation data is cleaned and transformed to obtain port integrated data.
5. The method for optimizing the operating efficiency of a maritime port according to claim 1, characterized in that: The step of predicting key optimization points of the port integrated data to obtain the operation data to be optimized includes: Extracting key features from the port integrated data to obtain operational feature data; Performing feature mapping on the operation feature data to obtain event mapping features, and clustering similar event mapping features to obtain operation mode groups; A key optimization point prediction is performed based on the operation mode group and the port integrated data to obtain a key operation period, and the operation data to be optimized is determined based on the key operation period and the port integrated data.
6. The method for optimizing the operating efficiency of a maritime port according to claim 1, characterized in that: The time series analysis and prediction of the operation data to be optimized to obtain the operation pressure prediction result and the adjustment demand prediction result includes: Performing time series forecasting of operating pressure according to the operating data to be optimized to obtain an operating pressure forecast result; An external impact estimate is performed based on the operation data to be optimized to obtain an adjusted demand forecast result.
7. The method for optimizing the operating efficiency of a maritime port according to claim 1, characterized in that: The generating of the port scheduling optimization strategy according to the operation pressure prediction result and the adjustment demand prediction result comprises: The port scheduling optimization calculation is performed according to the operation pressure prediction result and the adjustment demand prediction result to obtain the optimal ship arrival sequence, the optimal ship departure sequence and the cargo loading and unloading priority.
8. A device for optimizing the operating efficiency of a maritime port, characterized in that: include A data integration unit, used for performing time synchronization and weight distribution on the acquired port multi-source data to obtain weighted multi-source data, and performing data cleaning and integration on the weighted multi-source data to obtain port integrated data; The scheduling optimization unit is used to input the port integration data into a well-trained maritime port operation efficiency optimization model, predict key optimization points of the port integration data to obtain operation data to be optimized, predict port operation pressure of the operation data to be optimized to obtain operation pressure prediction results and adjustment demand prediction results, and generate a port scheduling optimization strategy according to the operation pressure prediction results and the adjustment demand prediction results.
9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for optimizing maritime port operation efficiency according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for optimizing maritime port operation efficiency according to any one of claims 1 to 7 is implemented.
