Automatic wharf container shipping operation time prediction method, system, equipment, medium and product
Through the automated terminal container loading operation time prediction method, the knowledge graph and BP neural network model are used to solve the problem of being unable to judge container operation time, and the efficiency and accuracy of terminal operation are improved.
Patent Information
- Application Number
- CN202410998932.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-19
AI Technical Summary
The prior art cannot effectively judge the container operating time, resulting in inefficiency of the terminal.
The automated terminal container loading operation time prediction method is adopted to build an automated terminal container operation knowledge graph and BP neural network model to obtain and preprocess container operation data and make time prediction.
It improves the scientificity, effectiveness, accuracy and timeliness of dock operations, and solves the problem of inefficiency.
Smart Images

Figure CN118982333A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of container terminal management, and in particular to a method, system, equipment, medium and product for predicting the time of container loading operation at an automated terminal. Background Art
[0002] Entering the 21st century, facing the sluggish global economic situation and the complex international and regional situation, it is more important and precious to inherit and carry forward the spirit of the Silk Road. With the continuous growth of world container shipping volume and the increasing size of container ships, the stability, efficiency, energy conservation, environmental protection and low cost of container loading and unloading have become the focus of port operators. Automated container terminals play an important role in reducing terminal labor costs, improving port throughput capacity, reducing energy consumption of loading and unloading operations, and enhancing the brand image of ports. They are an inevitable trend for future port development. The development of automated container terminals is changing with each passing day, and they have shown significant advantages in improving operating efficiency, reducing labor costs, and ensuring operating safety. However, with the continuous growth of global trade and the continuous increase in logistics demand, how to further improve the working efficiency of container terminals has become an important issue facing all terminals. Improving the working efficiency of container terminals is of great significance. First of all, efficient terminal operations can shorten the stay time of goods in the port and speed up the turnover of goods, thereby meeting the market's demand for fast and efficient logistics. This not only helps to enhance the competitiveness of ports, but also promotes the prosperity and development of global trade.
[0003] Secondly, improving the efficiency of terminal work helps reduce operating costs. By optimizing the operation process, reducing unnecessary waiting time and improving equipment utilization, the terminal can achieve more economical and efficient operation and reduce the handling cost per unit of cargo. For terminal companies, this means higher profit margins and stronger market competitiveness. In addition, improving the efficiency of terminal work can also help improve operational safety. The application of automation technology can reduce errors and accidents caused by human factors and improve the accuracy and stability of operations. At the same time, through intelligent monitoring and early warning systems, potential safety hazards can be discovered in time and corresponding measures can be taken to ensure the safe and smooth progress of terminal operations. Summary of the invention
[0004] The purpose of this application is to provide a method, system, equipment, medium and product for predicting the operation time of container loading at an automated terminal, so as to solve the current problem of inefficiency caused by the inability to judge the operation time of containers.
[0005] To achieve the above objectives, this application provides the following solutions:
[0006] In a first aspect, the present application provides a method for predicting the time of container loading operation at an automated terminal, comprising:
[0007] Obtaining container operation data; the container operation data is obtained from the constructed automated terminal container operation knowledge graph;
[0008] The container operation data is input into a container loading operation time prediction model, and a container loading operation time prediction value is output; the container loading operation time prediction model is obtained by training a BP neural network model using training samples; the training samples include container sample operation data and corresponding container loading operation time sample values;
[0009] The container loading operation time prediction model comprises an input layer, a hidden layer and an output layer which are connected in sequence.
[0010] Optionally, the process of constructing the automated terminal container operation knowledge graph specifically includes:
[0011] Based on each of the container operation data, a node type is defined; the node type includes a container node and an operation equipment node; wherein the container number is a unique identifier of the container node, and the number is a unique identifier of the operation equipment node;
[0012] Based on different node types, create corresponding nodes in the knowledge graph according to the corresponding unique identifiers;
[0013] The operation information in the container loading process is used as a relationship, and the relationship between nodes is created in the knowledge graph of the created nodes to obtain the knowledge graph of the automated terminal container operation; the operation information is the actual value of each container operation data.
[0014] Optionally, before inputting the container operation data into the container loading operation time prediction model, the method further includes: preprocessing the container operation data, specifically including:
[0015] Classifying the container operation data to obtain container operation numerical type data and container operation non-numerical type data;
[0016] The blank data in the container operation numerical type data and the container operation non-numerical type data are removed, and the non-numerical type data of the container operation is converted into numerical type data to obtain preprocessed container operation data, and the preprocessed container operation data is input into the container loading operation time prediction model.
[0017] Optionally, the training process of the container loading operation time prediction model specifically includes:
[0018] Acquire container sample operation data, preprocess the container sample operation data, and use the preprocessed container sample operation data as training samples;
[0019] Input the training samples into the BP neural network model and output the corresponding predicted value of container loading operation time;
[0020] A loss function is constructed according to the predicted value of the container loading operation time and the sample value of the container loading operation time, and the network parameters of the BP neural network model are adjusted by the loss function to obtain the container loading operation time prediction model.
[0021] Optionally, the number of neurons in the input layer is 12, the number of neurons in the output layer is 1, and the number of neurons in the hidden layer is determined by the number of neurons in the input layer and the number of neurons in the output layer.
[0022] Optionally, the expression for determining the number of neurons in the hidden layer is:
[0023]
[0024] Among them, q is the number of neurons in the hidden layer; a is the number of neurons in the output layer; b is the number of neurons in the input layer; c is an integer between 1 and 10.
[0025] In a second aspect, the present application provides an automated terminal container loading operation time prediction system, comprising:
[0026] A data acquisition module is used to acquire container operation data; the container operation data is acquired from a constructed automated terminal container operation knowledge graph;
[0027] The container loading operation time prediction module is used to input the container loading operation time prediction model into the container loading operation time prediction model, and output the container loading operation time prediction value; the container loading operation time prediction model is obtained by training the BP neural network model with training samples; the training samples include container sample operation data and corresponding container loading operation time sample values;
[0028] The container loading operation time prediction model comprises an input layer, a hidden layer and an output layer which are connected in sequence.
[0029] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-mentioned methods for predicting the time of container loading operations at an automated terminal.
[0030] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting container loading operation time at an automated terminal.
[0031] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting container loading operation time at an automated terminal.
[0032] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0033] The present application provides a method, system, equipment, medium and product for predicting the operation time of container loading at an automated terminal. By applying knowledge graphs and neural networks to the prediction of the operation time of container loading at a fully automated terminal, a method for predicting the operation time of container at a terminal based on natural language and machine learning is constructed. This method can replace manual judgment of container operation time, realize analysis and prediction of operation time, effectively improve the scientificity, effectiveness, accuracy and timeliness of terminal operations, and solve the problem of inefficiency caused by the inability to judge container operation time. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0035] Figure 1 This is an application environment diagram of a method for predicting the time of container loading operation at an automated terminal in one embodiment of the present application;
[0036] Figure 2 A schematic diagram of a flow chart of a method for predicting the time of container loading operation at an automated terminal provided in one embodiment of the present application;
[0037] Figure 3 A schematic diagram of a knowledge graph for automated container operations at a terminal provided in one embodiment of the present application;
[0038] Figure 4 A schematic diagram of a built BP convolutional neural network model provided in an embodiment of the present application;
[0039] Figure 5 A schematic diagram of functional modules of an automated terminal container loading operation time system provided by another embodiment of the present application;
[0040] Figure 6 A schematic diagram of the structure of a computer device provided in one embodiment of the present application.
[0041] Explanation of symbols:
[0042] 102-terminal, 104-server, 1-data acquisition module, 2-container loading operation time prediction module. DETAILED DESCRIPTION
[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0044] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0045] The method for predicting the time of container loading operation at an automated terminal provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the container operation data to the server 104. After the server 104 receives the container operation data, for the container operation data, the server 104 inputs the container operation data into the container loading operation time prediction model, and outputs the container loading operation time prediction value; the container loading operation time prediction model is obtained by training the BP neural network model using training samples; the training samples include container sample operation data and corresponding container loading operation time sample values. The server 104 can feed back the obtained container loading operation time prediction value to the terminal 102. In addition, in some embodiments, the automated terminal container loading operation time prediction method can also be implemented by the server 104 or the terminal 102 alone, such as the terminal 102 can directly predict the operation time for the container operation data, or the server 104 can obtain the container operation data from the data storage system and predict the operation time for the container operation data.
[0046] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.
[0047] In an exemplary embodiment, Figure 2 As shown, a method for predicting the time of container loading operation at an automated terminal is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps S1 to S2.
[0048] in:
[0049] Step S1, obtaining container operation data; the container operation data is obtained from the constructed automated terminal container operation knowledge graph.
[0050] Step S2, input the container operation data into the container loading operation time prediction model, and output the predicted value of the container loading operation time; the container loading operation time prediction model is obtained by training the BP neural network model with training samples; the training samples include container sample operation data and corresponding container loading operation time sample values; wherein the container loading operation time prediction model includes an input layer, a hidden layer and an output layer connected in sequence. The number of neurons in the input layer is 13, the number of neurons in the output layer is 1, and the number of neurons in the hidden layer is determined by the number of neurons in the input layer and the number of neurons in the output layer.
[0051] As an optional implementation, in step S1, the process of constructing the automated terminal container operation knowledge graph specifically includes:
[0052] Step S11, based on each of the container operation data, define the node type; the node type includes container nodes and operation equipment nodes; the container operation data includes container feature data and operation equipment feature data; the container feature data includes container number, container size, container type, empty weight, container status, import and export category, whether it is cold chain, whether it is dangerous goods, whether it is overweight and loading container area; the operation equipment feature data includes operation bridge crane number, operation automatic guided vehicle (AGV) number, operation track crane number, bridge crane operation time, AGV operation time and track crane operation time; wherein the container number is the unique identifier of the container node, the number is the unique identifier of the operation equipment node, and the remaining nodes are uniquely identified by their actual values. Using the unique identifier as an index can speed up the query efficiency of the knowledge graph.
[0053] Step S12, based on different node types, create corresponding nodes in the knowledge graph according to the corresponding unique identifiers.
[0054] Step S13, taking the operation information in the container loading operation process as a relationship, creating relationships between nodes in the knowledge graph of the created nodes, obtaining the knowledge graph of automated terminal container operations, and storing the knowledge graph of automated terminal container operations in the Neo4j graph database, converting the data into a format that can be processed by machines. Figure 3 As shown, I means import, the number corresponding to the operating AGV number is the specific number value of the AGV, the number corresponding to the operating bridge crane number is the specific number value of the operating bridge crane, the number corresponding to the operating track crane number is the specific number value of the operating track crane, HQ means height per square foot, E means empty weight, GP means the box type is ordinary cargo box, 55 is the unloading box area, IE means the box status is unavailable empty box, and N means non-dangerous goods.
[0055] Among them, two nodes and their corresponding relationships form a triple. The triples composed of nodes and relationships are generalized as <instance - relationship name - specific concept>, including but not limited to triples such as <bridge crane - number - specific bridge crane number>, <AGV - number - specific AGV number>, <rail crane - number - specific rail crane number>, etc.; the operation information is the actual value of each container operation data, specifically referring to various information generated during the loading process (operation process) of each container. For example, the operation process is: the container is placed on the AGV cart from a specific container yard through the quay crane, then transported to a specific location by the AGV, and then placed at a specific location on the ship by the bridge crane. The information generated during this process is the listed nodes. Another example, the operation information is: the container number is TU374232, the corresponding container size is 40, the container status is CE, the import / export type is I, whether it is a cold chain is N, whether it is a dangerous good is N, whether it is overweight is N, and the loading container yard is 40. Among them, the relationship name between the container number and TU374232 is the container size. Triples are established for the operation information. For example, if the container number and container type are obtained during the operation process, the corresponding triple is <container number - container type - BU>, and the triple obtained for the container status is <container number - container status - CF>, and so on. The established triple results are shown in Table 1.
[0056] Table 1 Triple Establishment Results
[0057] Box No. is TLLU5772488 Box type is GP Empty weight is E Box Status is IE Import and export type is I Shipping container area is 55 Loading yard space is 5554A2 Operating bridge crane number is 124 Bridge crane start time is 2023 / 1 / 112:56:40 Bridge crane end operation time is 2023 / 1 / 112:59:55
[0058] Among them, the triple represents <concept name - is - concept value>. Looking at Table 1, it is <container status - is - IE>. GP represents a general cargo container, E represents an empty container, IE represents an unavailable empty container, and I represents import.
[0059] The purpose of constructing the container operation knowledge graph of the automated terminal in the above steps is: the container operation data can be visualized to observe the specific process relationships. At the same time, the length of the current operation time can be judged based on the same historical container operation data, and the berthing position of the newly arriving ship at the terminal can be recommended.
[0060] As an optional implementation manner, before inputting the container operation data into the container loading operation time prediction model, it further includes: preprocessing the container operation data, specifically including:
[0061] (1) Classify the container operation data, count the types of various feature data, and obtain container operation numerical type data and container operation non - numerical type data.
[0062] (2) removing blank data from the container operation numerical data and the container operation non-numerical data, and converting the container operation non-numerical data into numerical data to obtain preprocessed container operation data, and inputting the preprocessed container operation data into the container loading operation time prediction model.
[0063] Specifically, the conversion results of the container type data are shown in Table 2, the conversion results of the container status data are shown in Table 3, and the conversion results of the empty weight data are shown in Table 4. The data with numerical features include: container size, loading container area, loading yard container position, operation bridge crane number, operation AGV number, and operation track crane number; the data with non-numerical features include: container type, empty weight, container status, import and export category, whether it is dangerous goods, and whether it is overweight.
[0064] Table 2 Box type data conversion
[0065] Box type Converted data BU 1 FR 2 GP 3 HC 4 OT 5 RF 6 TK 7 TU 8
[0066] Among them, BU means bulk container, FR means flat container, GP means general container, HC means high cube container, OT means open top container, RF means refrigerated container, TK means tank container, and TU means channel container.
[0067] Table 3 Box status data conversion
[0068] Box Status Converted data CF 1 IE 2 IF 3 IZ 4 OE 5 OF 6 OZ 7 RE 8 RFU 9 T 10
[0069] Among them, CF means owned container, IE means unavailable empty container, IF means unavailable full container, IZ means cargo container, OE means available empty container, OF means available full container, OZ means available cargo container, RE means repairable empty container, and RFU means repairable full container.
[0070] Table 3 Empty weight data conversion results
[0071] Empty weight Converted data E 1 F 2
[0072] Among them, E represents an empty box and F represents a full box.
[0073] As an optional implementation, in step S2, the training process of the container loading operation time prediction model specifically includes:
[0074] Step S21, obtain container sample operation data, preprocess the container sample operation data, and use the preprocessed container sample operation data as training samples; the preprocessing method is data sorting and cleaning. The container sample operation data consists of various feature data in the container operation process and is stored in the automated terminal container operation knowledge graph.
[0075] Step S22, input the training samples into the BP neural network model, and output the corresponding container loading operation time prediction value.
[0076] Step S23, construct a loss function based on the predicted value of the container loading operation time and the sample value of the container loading operation time, adjust the network parameters of the BP neural network model through the loss function, and obtain the container loading operation time prediction model. The initial learning rate is 0.001, and the error target is 0.000001.
[0077] Specifically, the container type, empty weight, container status, import and export category, whether it is dangerous goods and whether it is overweight, container size, loading area, loading yard location, operation bridge crane number, operation AGV number and operation track crane number are used as BP neural network input, and the container loading operation time is the neural network output, so as to build a model to predict the container loading operation time.
[0078] Among them, when building a BP neural network model, the following steps are included:
[0079] 1) Determine the number of network layers. For any function in a closed interval, a three-layer (including one hidden layer) BP neural network can be used to complete the fitting, including the input layer, hidden layer and output layer connected in sequence.
[0080] 2) Determine the number of neurons in each layer. The number of neurons in the input layer and output layer of the BP neural network is designed entirely according to the user's requirements. The box type, empty weight, box status, import and export category, whether it is a dangerous good or overweight, box size, loading area, loading yard position, operating bridge crane number, operating AGV number and operating rail crane number are used as input parameters, and the loading operation time of the container at the port is used as the target parameter. The number of neurons in the input layer of the network is determined to be 12, and the number of neurons in the output layer is determined to be 1. The hidden layer plays a vital role in the accuracy of the entire neural network. Improving the accuracy of the neural network can be achieved by increasing the number of neurons in the hidden layer. Determine the number of neurons in the hidden layer according to formula (1):
[0081]
[0082] Among them, q is the number of neurons in the hidden layer; a is the number of neurons in the output layer; b is the number of neurons in the input layer; c is an integer between 1 and 10.
[0083] 3) Build a BP convolutional neural network model. The input layer of the network is the influencing factors of container operations at the port, which respectively represent container type, empty weight, container status, import and export category, whether it is dangerous goods and whether it is overweight, container size, loading area, loading yard position, operation bridge crane number, operation AGV number and operation track crane number. The built BP convolutional neural network model is as follows: Figure 4 As shown, where w ij represents the connection weight between the i-th neuron in the input layer and the j-th neuron in the hidden layer, w jk represents the connection weight between the jth neuron in the hidden layer and the kth neuron in the output layer, where i=12, j=13, k=1. Each neuron in the hidden layer receives input signals from other neurons, and each signal is transmitted through a weighted connection, θ1, θ2, θ3, θ4…θ 12 represents the threshold of each neuron in the hidden layer, θ 13 represents the threshold of the output neuron, and o represents the predicted value of the container loading operation time, which is the output of the BP neural network. The neuron adds up these signals to get a total input value, and then compares the total input value with the threshold of the neuron, and obtains the final output through activation function processing. This output will be passed down layer by layer as the input of the subsequent neurons. The model selects the Sigmoid function as the activation function of the hidden layer neurons, and controls its output range between (0,1). The activation function of the output layer neurons is a linear function, and random numbers between the interval [-1,1] are selected as the initial weights and thresholds of the model, so that the input value of each neuron is close to 0.
[0084] Beneficial effects of this application:
[0085] This application constructs a knowledge graph of container operations at automated terminals based on container operation data, realizes joint modeling of container terminal loading business knowledge and existing resource big data information such as yard box data and equipment loading and unloading time data, and continuously optimizes the knowledge graph with data to build a new internal relationship model between business flows and data flows to meet the on-demand configuration of various business models and data resources. Starting from the business needs of container terminals, by judging the container operation time, the decision-making efficiency of the terminal can be improved, and then the reasonable allocation of various operating equipment can be carried out to improve the sorting efficiency of the terminal. Specifically:
[0086] 1) Applying knowledge graphs and neural networks to the prediction of container loading operation time at fully automated terminals, and building a terminal container operation time prediction method based on natural language and machine learning can greatly improve the decision-making efficiency in the automated terminal operation process and improve the level of intelligence.
[0087] 2) By building an automated terminal container operation time prediction system combined with knowledge graphs, it is possible to replace manual judgment of container operation time, realize operation time analysis and prediction, effectively improve the scientificity, effectiveness, accuracy and timeliness of terminal operations, and solve the problem of reduced efficiency caused by the inability to judge container operation time.
[0088] Based on the same inventive concept, the embodiment of the present application also provides an automated terminal container loading operation time prediction system for implementing the automated terminal container loading operation time prediction method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more automated terminal container loading operation time prediction system embodiments provided below can refer to the limitations of the automated terminal container loading operation time prediction method above, and will not be repeated here.
[0089] In an exemplary embodiment, Figure 5 As shown, a system for predicting the time of container loading operation at an automated terminal is provided, comprising:
[0090] The data acquisition module 1 is used to acquire container operation data; the container operation data is acquired from the constructed automated terminal container operation knowledge graph.
[0091] The container loading operation time prediction module 2 is used to input the container loading operation time prediction model into the container loading operation time prediction model, and output the container loading operation time prediction value; the container loading operation time prediction model is obtained by training the BP neural network model with training samples; the training samples include container sample operation data and corresponding container loading operation time sample values.
[0092] The container loading operation time prediction model comprises an input layer, a hidden layer and an output layer which are connected in sequence.
[0093] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 6As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a video tag processing method is implemented.
[0094] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0095] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0096] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0097] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0098] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0099] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0100] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0101] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A method for predicting the time of container loading operation at an automated terminal. It is characterized in that The method for predicting the time of container loading operation at an automated terminal comprises: Obtaining container operation data; the container operation data is obtained from the constructed automated terminal container operation knowledge graph; The container operation data is input into a container loading operation time prediction model, and a container loading operation time prediction value is output; the container loading operation time prediction model is obtained by training a BP neural network model using training samples; the training samples include container sample operation data and corresponding container loading operation time sample values; The container loading operation time prediction model comprises an input layer, a hidden layer and an output layer which are connected in sequence.
2. The method for predicting the time of container loading operation at an automated terminal according to claim 1, It is characterized in that The construction process of the automated terminal container operation knowledge graph specifically includes: Based on each of the container operation data, a node type is defined; the node type includes a container node and an operation equipment node; wherein the container number is a unique identifier of the container node, and the number is a unique identifier of the operation equipment node; Based on different node types, create corresponding nodes in the knowledge graph according to the corresponding unique identifiers; The operation information in the container loading process is used as a relationship, and the relationship between nodes is created in the knowledge graph of the created nodes to obtain the knowledge graph of the automated terminal container operation; the operation information is the actual value of each container operation data.
3. The method for predicting the time of container loading operation at an automated terminal according to claim 1, It is characterized in that Before inputting the container operation data into the container loading operation time prediction model, the method further includes: preprocessing the container operation data, specifically including: Classifying the container operation data to obtain container operation numerical type data and container operation non-numerical type data; The blank data in the container operation numerical type data and the container operation non-numerical type data are removed, and the non-numerical type data of the container operation is converted into numerical type data to obtain preprocessed container operation data, and the preprocessed container operation data is input into the container loading operation time prediction model.
4. The method for predicting the time of container loading operation at an automated terminal according to claim 1, It is characterized in that The training process of the container loading operation time prediction model specifically includes: Acquire container sample operation data, preprocess the container sample operation data, and use the preprocessed container sample operation data as training samples; Input the training samples into the BP neural network model and output the corresponding predicted value of container loading operation time; A loss function is constructed according to the predicted value of the container loading operation time and the sample value of the container loading operation time, and the network parameters of the BP neural network model are adjusted by the loss function to obtain the container loading operation time prediction model.
5. The method for predicting the time of container loading operation at an automated terminal according to claim 1, It is characterized in that The number of neurons in the input layer is 12, the number of neurons in the output layer is 1, and the number of neurons in the hidden layer is determined by the number of neurons in the input layer and the number of neurons in the output layer.
6. The method for predicting the time of container loading operation at an automated terminal according to claim 5, It is characterized in that The expression for determining the number of neurons in the hidden layer is: Among them, q is the number of neurons in the hidden layer; a is the number of neurons in the output layer; b is the number of neurons in the input layer; c is an integer between 1 and 10.
7. An automated terminal container loading operation time prediction system, It is characterized in that The automated terminal container loading operation time prediction system comprises: A data acquisition module is used to acquire container operation data; the container operation data is acquired from a constructed automated terminal container operation knowledge graph; The container loading operation time prediction module is used to input the container loading operation time prediction model into the container loading operation time prediction model, and output the container loading operation time prediction value; the container loading operation time prediction model is obtained by training the BP neural network model with training samples; the training samples include container sample operation data and corresponding container loading operation time sample values; The container loading operation time prediction model comprises an input layer, a hidden layer and an output layer which are connected in sequence.
8. A computer device, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting the time of container loading operations at an automated terminal as claimed in any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for predicting the time of container loading operation at an automated terminal according to any one of claims 1 to 6 is implemented.
10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the method for predicting the time of container loading operation at an automated terminal according to any one of claims 1 to 6 is implemented.
