Intelligent pile machine control management method and device based on big data

Abstract

The invention provides a pile driver intelligent control management method and device based on big data, and relates to the technical field of pile driver management control, and the method comprises the steps: obtaining historical pile driving data of a pile driver in an operation process, and training a control model based on the historical pile driving data; construction tasks in a future scheduling period are obtained, the pile machines and the construction tasks are input into the control model to obtain equipment control information, and the equipment control information is input into the management scheduling model to be subjected to iterative analysis to be matched with a recommended distribution scheme of the pile machines; and according to the recommended distribution scheme, the pile driver is dispatched to a designated construction site to execute a construction task, state data of the pile driver in the construction process are monitored in real time, and equipment control information of the pile driver is adjusted according to feedback of the state data. Through statistics of pile machine equipment and operator information, a big database of historical piling data is constructed and analyzed, equipment control information can be intelligently adjusted according to different construction environments, and the working efficiency and construction quality of a pile machine are improved.

Description

Technical Field

[0001] The present application relates to the technical field of pile driver management and control, and in particular to a pile driver intelligent control and management method and device based on big data. Background Art

[0002] Pile driver control management refers to the systematic and intelligent monitoring and control of the pile driver construction process through a series of modern technical means and management methods to ensure construction efficiency, quality and safety. The contents involved mainly include automatic control system, sensor monitoring system, data acquisition and analysis system, remote control and management system, and safety protection mechanism.

[0003] Traditional management methods rely on manual management, and the differences in the professional and technical levels and qualities of managers make it impossible to effectively guarantee the timeliness and authenticity of the construction status of pile driver equipment and the construction process data. It is also difficult to ensure the efficiency of pile driver allocation and scheduling management and construction control, affecting the construction progress and quality. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of this application is to propose a pile driver intelligent control management method based on big data.

[0006] The second object of the present application is to provide a device.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth objective of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above objectives, the first embodiment of the present application proposes a pile driver intelligent control management method based on big data, including:

[0011] Determine the number of pile drivers that can participate in piling and the operator information, and record the equipment type, equipment serial number and operator list of each pile driver;

[0012] Acquire historical piling data of the pile driver during operation, and train a control model based on the historical piling data, wherein the control model is used to generate corresponding equipment control information of the pile driver under a specific construction environment;

[0013] Setting a scheduling cycle, obtaining construction tasks within a future scheduling cycle, inputting the pile driver and the construction tasks into the control model to obtain equipment control information, and inputting the equipment control information into the management scheduling model for iterative analysis to match a recommended allocation plan for the pile driver;

[0014] The pile driver is dispatched to a designated construction site to perform construction tasks according to the recommended allocation plan, status data of the pile driver during construction is monitored in real time, and equipment control information of the pile driver is adjusted according to feedback from the status data.

[0015] Optionally, the acquiring historical piling data of the pile driver during operation and training a control model based on the historical piling data includes:

[0016] Performing data preprocessing on the historical piling data, adding tags to the preprocessed historical piling data, and storing the historical piling data according to the tags;

[0017] Based on the type of the tag, extract the construction environment information and equipment control information from the historical piling data, build a pile driver evaluation system, quantify the historical piling data, and then analyze and obtain the weight value of each indicator in the historical piling data;

[0018] The construction environment information is defined as input data, the equipment control information is defined as output data, the control model is constructed and deployed to a distributed data processing framework, and the control model is trained in parallel using the historical piling data in a batch processing learning mode.

[0019] Optionally, the historical piling data includes construction environment information and equipment control information;

[0020] The construction environment information includes: geological parameters of the construction site and meteorological parameters during the construction process;

[0021] The equipment control information includes: pile driving depth, pile driving time, vibration frequency, hydraulic pressure, inclination angle, and pile driver type.

[0022] Optionally, the learning mode using batch processing uses the historical piling data to perform parallel training on the control model, including:

[0023] Establish a training set and a test set based on the historical piling data, and divide the training set into multiple data subsets, which are stored in a distributed file system respectively;

[0024] Using the core node, the structure of the control model, the data subset and the weight value are sent to the computing node;

[0025] Using a batch training method, a partial data subset on the computing node is input into the control model for training;

[0026] Instruct the computing node to update the weight value and return it to the core node;

[0027] The network weights of the control model are updated according to the core nodes, and the error between the expected output and the actual output is calculated, and the training process is controlled according to the error and the number of iterations;

[0028] Stop training and output the control model after training.

[0029] Optionally, the using a core node to send the structure of the control model, the data subset, and the weight value to a computing node includes:

[0030] Starting a distributed computing platform, and using a collection operator to input the data subset as a resilient distributed data set into the computing node;

[0031] The driver process reads the initial weight value in the control model, and uses the broadcast variable operator to send the weight value to each of the computing nodes;

[0032] Each of the computing nodes is controlled to construct a control model instance using the initial weight value.

[0033] Optionally, the step of inputting the equipment control information into a management scheduling model for iterative analysis to match a recommended allocation scheme for the pile driver includes:

[0034] Set the scheduling cycle in the pile driver management platform, obtain the construction tasks to be executed uploaded by the construction site, and count the number of construction tasks in the current scheduling cycle and future scheduling cycles;

[0035] Inputting the construction environment information corresponding to the construction site into the trained control model, and outputting the equipment control information corresponding to the pile driver under the construction environment information, wherein the equipment control information includes the piling time required to complete the construction task;

[0036] According to the piling time required for the pile driver to perform the construction task and the idle time during which the pile driver performs the construction task, a time loss function for a single pile driver to participate in the scheduling is set;

[0037] The management and scheduling model is constructed to reduce the time loss function as the goal, and through parameter assignment and population iterative optimization, a recommended allocation plan for pile drivers to perform construction tasks within the future scheduling period is generated.

[0038] Optionally, the expression of the time loss function is:

[0039]

[0040] Where L represents the time loss function of pile driver resource usage;

[0041] K represents loss efficiency;

[0042] n p Indicates the number of pile drivers;

[0043] n t Indicates the number of construction tasks;

[0044] X ij It represents the piling time of the i-th pile driver performing the j-th construction task;

[0045] T ij represents the total time that the i-th pile driver participates in the j-th construction task;

[0046] Z j Represents the remaining time after the jth construction task is completed.

[0047] Optionally, the management scheduling model is constructed to reduce the time loss function as a goal, and to generate a recommended allocation plan for the pile driver to perform construction tasks in the future scheduling period through parameter assignment and population iterative optimization, including:

[0048] Initialize the algorithm parameter values ​​of the biogeographic optimization algorithm, initialize the population size and the number of cycles, randomly generate several habitats, and initialize all species groups, wherein the species groups include;

[0049] Calculate the fitness value, sort the fitness value of each habitat in descending order, and generate the number of species in the habitat and the corresponding immigration and emigration rate values ​​according to the sorting results;

[0050] Use the immigration rate parameters and the emigration rate parameters to complete the population migration action;

[0051] By calculating the immigration rate parameters and the emigration rate parameters, the probability value of a certain type of population appearing in the habitat is obtained, and the population variation rate value of the habitat is generated;

[0052] Use the population mutation rate value to perform mutation actions;

[0053] The mutation operation is continued until the preset maximum number of cycles is reached, and the output is used as the recommended allocation plan for the pile driver.

[0054] Optionally, the fitness calculation formula is:

[0055] minfitness = α × L(X) + β × Zmi n

[0056] In the formula, fitness represents fitness;

[0057] α and β both represent weight factors;

[0058] L(X) represents the use of the pile driver;

[0059] Zmi n It represents the remaining time of the minimized pile driver outside the construction task.

[0060] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a pile driver intelligent control and management device based on big data, comprising:

[0061] A data acquisition module is used to determine the number of pile drivers that can participate in piling and the operator information, and record the equipment type, equipment serial number and operator list of each pile driver;

[0062] A model training module, used for acquiring historical piling data of the pile driver during operation, and training a control model based on the historical piling data, wherein the control model is used for generating equipment control information corresponding to the pile driver under a specific construction environment;

[0063] A task allocation module is used to set a scheduling cycle, obtain construction tasks within a future scheduling cycle, input the pile driver and the construction tasks into the control model to obtain equipment control information, and input the equipment control information into the management scheduling model for iterative analysis to match the recommended allocation plan for the pile driver;

[0064] The task execution module is used to dispatch the pile driver to the designated construction site to perform the construction task according to the recommended allocation plan, monitor the status data of the pile driver during the construction process in real time, and adjust the equipment control information of the pile driver according to the feedback of the status data.

[0065] To achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0066] The memory stores computer-executable instructions;

[0067] The processor executes the computer-executable instructions stored in the memory to implement the method as described in any one of the first aspects.

[0068] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, in which computer-readable storage medium is stored computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method as described in any one of the first aspects.

[0069] To achieve the above-mentioned purpose, the fifth aspect of the present application proposes a computer program product, which implements any method in the first aspect when executed by a processor.

[0070] The big data-based intelligent control management method, device, electronic device and storage medium for a pile driver provided in this application can intelligently adjust the equipment control information according to different construction environments by collecting statistics on pile driver equipment and operator information, building a large database of historical piling data and analyzing it, thereby improving the working efficiency and construction quality of the pile driver.

[0071] By collecting statistics on pile driver equipment and operator information, building a large database of historical piling data and analyzing it, it is possible to intelligently adjust equipment control parameters according to different construction environments, thereby improving the work efficiency and construction quality of the pile driver. With the help of big data analysis, more accurate pile driver scheduling and control are achieved, which can dynamically optimize the allocation of construction tasks, adjust the construction progress with real-time feedback, and significantly reduce construction time and resource waste. In addition, the introduction of intelligent management and maintenance processes has also effectively extended the service life of the equipment and improved the reliability and efficiency of the overall operation.

[0072] By utilizing the Internet of Things, cloud computing, big data analysis and control models, it is possible to more accurately acquire and process a large amount of historical piling data. Through data cleaning, labeling, classified storage and weight analysis, the equipment control information of the pile driver in different construction environments can be systematically evaluated. The introduction of the BP neural network enables the model to adaptively learn and optimize, and predict and adjust the control parameters of the pile driver in real time, thereby improving construction accuracy and efficiency, reducing errors in human operation, optimizing resource allocation, and significantly improving the overall level of intelligence and adaptability of construction.

[0073] By setting the scheduling cycle and combining the control model with the biogeographic optimization algorithm, the intelligent and optimized scheduling of the pile driver in the future scheduling cycle is realized. It can match the pile driver with the construction task, take into account the construction environment and equipment type, and accurately predict the piling time required for the pile driver to complete the construction task. The optimization algorithm can effectively reduce the idle time and scheduling time loss of the pile driver, significantly improve the utilization rate of the pile driver resources, reduce the construction cycle and cost, and improve the overall construction efficiency and reliability.

[0074] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0076] Figure 1A schematic diagram of a flow chart of a pile driver intelligent control management method based on big data provided in an embodiment of the present application;

[0077] Figure 2 A schematic diagram of the structure of a pile driver intelligent control and management device based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0078] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0079] A pile driver is a construction machine used for foundation and base engineering. It is mainly used for piling and drilling to ensure the stability and safety of the foundation of a building. It includes pile drivers, bored pile drivers and screw pile drivers. A pile driver drives piles into the foundation through the hammering force, vibration force or static pressure of a pile hammer. Hammer pile drivers use the free fall energy of a heavy hammer, vibrating pile drivers use high-frequency vibration, and static pressure pile drivers use a hydraulic system to apply static pressure. A bored pile driver drives a drill bit or drill rod into the foundation through rotation or impact to form a pile hole. A rotary drilling rig uses the rotation of a drill bit to cut the soil, while an impact drill uses impact force and cutting to form a hole. A screw pile driver drills piles into the foundation through the rotation of the spiral drill bit. The spiral drill bit cuts the soil and brings it out of the hole when it rotates.

[0080] Pile driver control management refers to the systematic and intelligent monitoring and control of the pile driver construction process through a series of modern technical means and management methods to ensure construction efficiency, quality and safety. The contents involved mainly include automatic control system, sensor monitoring system, data acquisition and analysis system, remote control and management system, and safety protection mechanism.

[0081] Existing pile driver control and management technologies include a variety of control and monitoring methods. For example, PLC and DCS technologies in the automation control system realize automatic control; sensor technology can monitor various working parameters of the pile driver in real time; data acquisition and analysis systems can collect and analyze construction data in real time, providing a scientific basis for optimizing construction plans; wireless communication technology realizes the functions of remote control and management. However, there is currently a lack of effective management methods for the dispatching and allocation or construction status of pile driver equipment on the construction site. Pile foundation construction management mostly registers and manages engineering materials and construction processes through paper forms, and tracks and manages the progress, quality and safety of pile foundation construction. Traditional management methods rely on manual management, and the differences in the professional and technical level and quality of management personnel make it impossible to effectively guarantee the timeliness and authenticity of the construction status of pile driver equipment and the construction process data, and it is difficult to ensure the efficiency of pile driver allocation, dispatching management and construction control, which affects the construction progress and quality.

[0082] To address this problem, the present invention provides a method for intelligent control and management of pile drivers based on big data. Figure 1 The following is a flow chart of a method for intelligent control and management of a pile driver based on big data provided in an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0083] Step S1, determining the number of pile drivers that can participate in piling and the operator information, and recording the equipment type, equipment serial number and operator list of each pile driver;

[0084] In this embodiment, the collection of pile driver equipment information includes:

[0085] 1. Equipment quantity statistics: Collect the number of currently available pile driving equipment, including all pile driving equipment that can participate in construction in the current or future scheduling cycle.

[0086] 2. Equipment type classification: Different types of pile drivers are classified and sorted according to their models, functions and technical parameters. Common types include rotary drilling rigs, impact drilling rigs, etc.

[0087] 3. Equipment serial number registration: Assign a unique serial number to each device for identification and tracking in the management platform; the serial number usually includes information such as device model, manufacturer information and device number.

[0088] 4. Equipment status record: record the current status of each pile driver, such as "available", "under maintenance", "faulty", etc., to determine whether it can participate in current or future construction tasks.

[0089] Operator information collection includes:

[0090] 1. Personnel statistics: Count the number of all operators who can currently operate the pile driver equipment, including all personnel who hold relevant qualifications and are able to work within the current or future scheduling cycle.

[0091] 2. Personnel qualification verification: Verify the qualification certificates of operators to ensure that they have the skills and experience required for operation. Record each operator's qualification level, years of operating experience, and other information.

[0092] 3. Personnel list registration: register the basic information of each operator (such as name, work number, contact information) in the pile driver management platform, and associate it with the pile driver equipment they operate.

[0093] Step S2, obtaining historical piling data of the pile driver during operation, and training a control model based on the historical piling data, wherein the control model is used to generate corresponding equipment control information of the pile driver under a specific construction environment;

[0094] Step S3, setting a scheduling cycle, obtaining construction tasks within a future scheduling cycle, inputting the pile driver and the construction tasks into the control model to obtain equipment control information, and inputting the equipment control information into the management scheduling model for iterative analysis to match the recommended allocation plan of the pile driver;

[0095] In this embodiment, a management and scheduling model based on a biogeographic optimization algorithm is constructed, and the optimal allocation plan for scheduling pile drivers to perform construction tasks in the future is matched through parameter assignment and population iterative optimization.

[0096] Among them, the Biogeography-Based Optimization (BBO) algorithm is an intelligent optimization algorithm based on the principles of biogeography. It simulates the natural process of species migration and distribution between different habitats to find the optimal solution. BBO shows good performance in dealing with complex optimization problems, especially in global optimization ability and diversity maintenance.

[0097] Step S4, dispatching the pile driver to the designated construction site to perform the construction task according to the recommended allocation plan, monitoring the status data of the pile driver during the construction process in real time, and adjusting the equipment control information of the pile driver according to the feedback of the status data.

[0098] In this embodiment, after determining the optimal recommended allocation plan, the system will issue instructions to the relevant pile driver operators or automatic control systems according to the specific requirements of the construction task and the type of pile driver. The pile driver will be dispatched to the designated construction site. After the pile driver arrives at the construction site, the operator or automatic system will perform an initialization check on the equipment to ensure that the parameters of the pile driver are set correctly, the equipment is in good condition, and meets the construction requirements.

[0099] Various sensors installed on the pile driver (such as displacement sensors, pressure sensors, vibration sensors, etc.) will continuously collect data generated during the construction process, such as the location of the pile driver, the depth of pile driving, the verticality of the pile body, etc. These data are transmitted to the construction management platform in real time through the Internet of Things technology. The management platform uses big data technology to analyze real-time data and evaluate whether the construction progress is in line with the planned schedule. If an abnormal progress is detected (such as construction too slow or too fast), the system will immediately issue an alarm.

[0100] Based on real-time monitoring data, the system automatically compares the current construction status with the preset standards. If deviations are found, the system automatically adjusts the control parameters of the pile driver through a feedback mechanism. For example, if the piling speed is too slow, the system may adjust the piling force or frequency; if the pile body is detected to be deflected, the system may adjust the inclination angle of the pile driver. In addition, the system dynamically adjusts the control parameters of the pile driver by learning historical construction data and current environmental conditions to adapt to different construction environments and soil conditions. This adaptive adjustment can improve the accuracy and efficiency of construction and reduce human intervention.

[0101] After the construction is completed, it is necessary to record the construction records of the pile driver completing the construction tasks and perform pile driver equipment maintenance.

[0102] Optionally, the step S2 acquires historical piling data of the pile driver during operation, and trains a control model based on the historical piling data, including:

[0103] Step S21, performing data preprocessing on the historical piling data, adding tags to the preprocessed historical piling data, and storing the historical piling data according to the tag classification;

[0104] Step S22, based on the type of the tag, extracting construction environment information and equipment control information from the historical piling data, building a pile driver evaluation system, quantifying the historical piling data, and then analyzing and obtaining the weight value of each indicator in the historical piling data;

[0105] Step S24, defining the construction environment information as input data, defining the equipment control information as output data, constructing the control model and deploying it to a distributed data processing framework, and using a batch processing learning mode to perform parallel training on the control model using the historical piling data.

[0106] In this embodiment, in step S21, outliers and noise are removed through data preprocessing and data cleaning.

[0107] Specifically, the main purpose of data cleaning is to remove outliers, noise, duplicate data and missing data to make the data more reliable. The cleaning methods include: 1. Outlier detection and removal: Calculate the mean and standard deviation of each data field, and mark the values ​​that deviate from the mean by 2-3 times the standard deviation as outliers. For example, the normal range of hydraulic pressure may be 150-250 bar. If the pressure of a pile driver is detected to be 400 bar, it can be regarded as abnormal data. 2. Missing value processing: If the amount of missing data is large, interpolation can be used to estimate the missing values ​​based on the changing trend of the previous and next time points. 3. Noise processing: Apply sliding window smoothing filtering or weighted averaging to eliminate sharp fluctuations in short periods of time. For example, in the continuous recording of vibration frequency, remove some randomly generated high-frequency spikes.

[0108] The main task of preprocessing is to convert and normalize the data to make the data more analyzable. The present invention normalizes data of different dimensions so that they have the same numerical range, which is convenient for subsequent analysis. For example, the numerical range of pile driving depth may be 0-30 meters, while the range of hydraulic pressure is 100-300 bar. By normalizing the range of all data to [0,1], it is possible to avoid excessive influence of a certain type of data on model training. For continuous time series data (such as vibration frequency or pressure), the data can be smoothed through a time window to eliminate small-scale fluctuations and improve the stability of the data.

[0109] After data cleaning and preprocessing, historical data needs to be labeled for subsequent analysis and application. The purpose of labeling is to classify multidimensional data by category or feature.

[0110] Label classification method:

[0111] Classification by construction environment: Classify the data according to construction environment parameters, for example, meteorological parameters (such as temperature, humidity, wind speed, etc.) or geological parameters (such as soil type, water content, etc.).

[0112] Tag 1: Temperature > 30℃

[0113] Label 2: Humidity < 40%

[0114] Tag 3: Sandy soil, moisture content > 15%

[0115] Classification by equipment control information: Classify the data according to equipment control information (pile driving depth, pile driving time, vibration frequency, hydraulic pressure, inclination angle, etc.). For example:

[0116] Tag 1: Piling depth > 20 meters

[0117] Tag 2: Hydraulic pressure > 200 bar

[0118] Tag 3: Vibration frequency>100Hz

[0119] Classification by construction task type: Depending on the complexity and objectives of the construction task, the piling data may be labeled as "high complexity", "standard complexity", etc.

[0120] Finally, the cleaned, preprocessed and labeled piling data will be classified and stored according to the label type to form a multi-dimensional historical data set. The present invention performs hierarchical storage according to labels such as construction environment and equipment control information. For example: 1. Construction environment level: piling data of different meteorological parameters and geological conditions. 2. Equipment control level: combination of parameters such as piling depth and vibration frequency. At the same time, in order to quickly retrieve historical data, an index structure is established for each classified data set to facilitate subsequent query and analysis, that is, a distributed storage system (such as HDFS or NoSQL database) is used to store piling data to ensure the efficiency and scalability of the system.

[0121] In step S22 of this embodiment, specifically, based on the extracted construction environment information and equipment control information, an evaluation system is constructed to evaluate the performance of the pile driver under different construction environments, which can be divided into the following dimensions:

[0122] 1. Construction environment dimensions: geological parameters, meteorological conditions, etc.;

[0123] 2. Equipment operation dimensions: piling depth, piling time, hydraulic pressure, vibration frequency, etc.;

[0124] 3. Economic benefit dimension: piling efficiency, equipment loss, etc.

[0125] Each dimension can be further broken down into specific indicators.

[0126] The analytic hierarchy process (AHP) is a decision analysis tool used to determine the weights of each indicator in a multidimensional evaluation system. Its steps include constructing a judgment matrix, calculating weights, and consistency testing.

[0127] First, it is necessary to construct a judgment matrix for pairwise comparison based on the importance of each indicator. For each dimension of the indicator, evaluate its relative importance and assign a corresponding score (usually using a scale of 1-9). Assuming there are three indicators: pile driving depth (A), hydraulic pressure (B), and pile driving time (C), a judgment matrix can be constructed as shown in Table 1.

[0128] A B C A 1 3 5 B 1 / 3 1 2 C 1 / 5 1 / 2 1

[0129] Table 1

[0130] The values ​​of the matrix elements represent the importance comparison between the corresponding two indicators. For example, the pile driving depth (A) is 3 times more important than the hydraulic pressure (B).

[0131] By performing eigenvalue decomposition on the judgment matrix, the weight of each indicator is calculated. The specific steps are: normalize each column of the judgment matrix and calculate the proportion of each column element to the total column. Calculate the average value of each row to obtain the weight value of each indicator. Finally, in order to ensure the rationality of the judgment matrix, it is usually necessary to perform a consistency test and calculate the consistency ratio (CR). If the CR value is less than 0.1, the judgment matrix has satisfactory consistency, otherwise it needs to be adjusted.

[0132] Optionally, the control model in step S24 is a BP neural network. The BP neural network is a multi-layer feedforward neural network consisting of an input layer, a hidden layer and an output layer. The weights between neurons in each layer are adjusted by back propagation. It is one of the most widely used neural network models. It can learn and store a large number of input-output mapping relationships without revealing the mathematical equations describing these relationships in advance.

[0133] This embodiment uses BP neural network to establish the association prediction model of pile driver equipment control information, where the number of nodes in the input layer is set to 8; the number of nodes in the hidden layer is set to 10. The number of neurons in the output layer should be equal to the number of dimensions of the equipment control information. For example, if the control information contains three parameters: pile driving speed, torque, and pile driving time, the output layer should have 3 neurons.

[0134] In this embodiment, the BP neural network model plays a core decision-making tool for predicting the control information of the pile driver equipment under different construction environments through historical data. The model optimizes the control of the pile driver in various environments by learning the complex nonlinear relationship in the historical pile driving data. The main function of the BP neural network model is to predict the optimal control parameters of the pile driver (such as pile driving time, pile driving depth, vibration frequency, etc.) under given construction environment conditions, so as to ensure the efficient and stable completion of the pile driving task.

[0135] Optionally, the historical piling data includes construction environment information and equipment control information;

[0136] The construction environment information includes: geological parameters of the construction site and meteorological parameters during the construction process;

[0137] The equipment control information includes: pile driving depth, pile driving time, vibration frequency, hydraulic pressure, inclination angle, and pile driver type.

[0138] Optionally, the step S24 adopts a batch processing learning mode to perform parallel training on the control model using the historical piling data, including:

[0139] Step S241, establishing a training set and a test set according to the historical piling data, and dividing the training set into multiple data subsets, which are stored in a distributed file system respectively;

[0140] Step S242, using the core node (Master node) to send the structure of the control model, the data subset and the weight value to the computing node (Worker node);

[0141] Step S243, using a batch training method, inputting a subset of the data on the computing node into the control model for training;

[0142] Step S244, instructing the computing node to update the weight value and return it to the core node;

[0143] Step S245, updating the network weight of the control model according to the core node, calculating the error between the expected output and the actual output, and controlling the training process according to the error and the number of iterations;

[0144] In this embodiment, it is determined whether the error and the number of iterations meet the requirements. If they do, the training is terminated. If they do not, the training is continued back to step S242.

[0145] Step S246, stop training and output the control model after training.

[0146] As can be seen from the above, the present invention is based on distributed computing and batch processing technology, and is used to perform efficient parallel training of control models. By distributing training tasks to multiple computing nodes, the training speed and processing capacity are improved, and it is particularly suitable for processing large-scale data sets. The main principle is to divide the entire training data set into multiple data subsets, which are stored in a distributed file system respectively, so that data processing and training processes can be carried out in parallel, improving computing efficiency.

[0147] In a distributed computing framework, core nodes coordinate the work, while compute nodes perform the actual training calculations. The model training process is broken down into multiple parallel tasks, with compute nodes training subsets of data and returning results, thus speeding up the overall training process. Ultimately, batch processing, which divides the data into small batches for training, helps speed up training and reduces the memory required for a single training, making it easier to process in a distributed environment.

[0148] Optionally, the step S242 uses the core node to send the structure of the control model, the data subset and the weight value to the computing node, including:

[0149] Step S2421, starting a distributed computing platform (such as Apache Spark), and using a collect operator to input the data subset as a resilient distributed data set into the computing node;

[0150] Step S2422, the driver process reads the initial weight value in the control model, and uses the broadcast variable operator to send the weight value to each of the computing nodes;

[0151] Step S2423, controlling each of the computing nodes to construct a control model instance using the initial weight value.

[0152] In this embodiment, Apache Spark is a fast, general-purpose distributed computing system designed to quickly process large-scale data sets. Unlike traditional disk-based processing frameworks (such as Hadoop MapReduce), Spark uses data in memory for calculations, so it is faster and is particularly suitable for iterative calculations and interactive queries. Resilient Distributed Datasets (RDDs) are the core abstraction of Spark, used to represent an immutable distributed data set. RDDs are the basic data structure in distributed computing and provide a rich set of operation interfaces, such as mapping, filtering, aggregation, etc.

[0153] Distributed File System (HDFS) is used to store large-scale data. HDFS divides data into multiple blocks and stores them in a distributed manner on different nodes in the cluster, providing high fault tolerance and high throughput.

[0154] The collect operator is used to collect all elements in a distributed dataset (such as RDD or DataFrame) into the local memory of the Driver process. This is an action operator that triggers the execution of a computation chain.

[0155] In step S2422, the Driver process is the main program of the Spark application, which is responsible for executing user-defined code. The Driver process communicates with the cluster through SparkContext, assigns tasks to worker nodes in the cluster, and collects execution results. The Driver process is also responsible for scheduling tasks, managing task dependencies, and maintaining the life cycle of the Spark application.

[0156] The broadcast operator is used to copy a smaller data set (called a broadcast variable) to all executor nodes. This can avoid the situation where each task repeatedly passes the same data set from the Driver node to the Worker node in a distributed environment. By broadcasting data to each node, the network transmission overhead can be greatly reduced and computing performance can be improved.

[0157] Optionally, the step S3 inputs the equipment control information into a management scheduling model for iterative analysis to match the recommended allocation scheme of the pile driver, including:

[0158] Step S31, setting a scheduling cycle in the pile driver management platform, obtaining the construction tasks to be executed uploaded by the construction site, and counting the number of construction tasks in the current scheduling cycle and the future scheduling cycle;

[0159] Step S32, inputting the construction environment information corresponding to the construction site into the trained control model, and outputting the equipment control information corresponding to the pile driver under the construction environment information, wherein the equipment control information includes the piling time required to complete the construction task;

[0160] Step S33, setting a time loss function for a single pile driver to participate in scheduling according to the piling time required for the pile driver to perform the construction task and the idle time during which the pile driver performs the construction task;

[0161] Step S34, constructing the management scheduling model, with the goal of reducing the time loss function, through parameter assignment and population iterative optimization, to generate a recommended allocation plan for the pile driver to perform construction tasks in the future scheduling period.

[0162] Optionally, the expression of the time loss function is:

[0163]

[0164] Where L represents the time loss function of pile driver resource usage;

[0165] K represents loss efficiency;

[0166] n p Indicates the number of pile drivers;

[0167] n t Indicates the number of construction tasks;

[0168] X ij It represents the piling time of the i-th pile driver performing the j-th construction task;

[0169] T ij represents the total time that the i-th pile driver participates in the j-th construction task;

[0170] Z j Represents the remaining time after the jth construction task is completed.

[0171] Optionally, the step S34 constructs the management scheduling model, and generates a recommended allocation plan for the pile driver to perform construction tasks in the future scheduling period through parameter assignment and population iterative optimization with the goal of reducing the time loss function, including:

[0172] Step S341, initializing the algorithm parameter values ​​of the biogeographic optimization algorithm, initializing the population size and the number of cycles, and randomly generating a number of habitats to initialize all species groups, wherein the species groups include;

[0173] In this embodiment, the algorithm parameter values ​​include a maximum mutation rate parameter, a maximum immigration rate parameter, a maximum emigration rate parameter, and a maximum habitat carrying capacity.

[0174] Step S342, calculating the fitness value, sorting the fitness value of each habitat in descending order, and generating the number of species in the habitat and the corresponding immigration and emigration rate value according to the sorting result;

[0175] In this embodiment, the fitness calculation formula is:

[0176] min fitness = α × L (X) + B × Z min

[0177] In the formula, fitness represents fitness;

[0178] α and β both represent weight factors;

[0179] L(X) represents the use of the pile driver;

[0180] Zmi n It represents the remaining time of the minimized pile driver outside the construction task.

[0181] Step S343, using the immigration rate parameter and the emigration rate parameter to complete the population migration action;

[0182] Step S344, by calculating the immigration rate parameter and the emigration rate parameter, the probability value of a certain type of population appearing in the habitat is obtained, and the population mutation rate value of the habitat is generated;

[0183] Step S345, performing a mutation action using the population mutation rate value;

[0184] Step S346, continue the mutation operation until the preset maximum number of cycles is reached, and output it as the recommended allocation plan for the pile driver.

[0185] In this embodiment, the recommended allocation plan includes the specific construction task allocation of each pile driver and its specific arrangement within the scheduling cycle, ensuring that the construction task is completed efficiently in the shortest time.

[0186] The process of setting system parameters includes the following values:

[0187] 1. Algorithm parameter values

[0188] 1.1. Habitat size: represents the size of the search space, which corresponds to the number of pile driver allocation schemes. For the pile driver scheduling problem, the habitat size needs to be large enough to cover all possible allocation schemes.

[0189] 1.2. Migration Rate: controls the probability of a species migrating from one habitat to another. In pile driver scheduling, the migration rate determines the information transfer between different pile driver allocation schemes and affects the diversity of solutions.

[0190] 1.3. Migration Out Rate: controls the probability of species in a habitat migrating to other habitats. In pile driver allocation, the migration out rate helps explore new solution spaces and prevents falling into local optimal solutions.

[0191] 1.4. Mutation Rate: Indicates the frequency of species changes in a habitat. Setting the mutation rate is critical for exploring the solution space and finding the optimal allocation solution.

[0192] 2. Population size and number of cycles

[0193] 2.1. Population size: represents the number of habitats used in the algorithm. A larger population size can provide more potential solutions and increase the probability of finding the global optimal solution.

[0194] 2.2. Number of loops: indicates the number of iterations executed by the algorithm. More loops usually improve the quality of the solution, but also increase the computational cost. It should be set according to the complexity of the problem and the computing resources.

[0195] The functions of the algorithm applied to pile driver allocation include:

[0196] 1. Optimize the pile driver allocation plan

[0197] 1.1. Fitness value calculation: The algorithm evaluates different pile driver allocation schemes by calculating fitness values ​​(such as construction time, equipment utilization, scheduling efficiency, etc.). A scheme with a higher fitness value indicates a better resource allocation effect.

[0198] 1.2. Habitat migration: Through migration in and out operations, the algorithm can exchange information between different allocation schemes and gradually improve the allocation scheme of the pile driver to achieve better scheduling.

[0199] 2. Avoid local optimum

[0200] 2.1. Mutation operation: Mutation operation can introduce new solutions, help the algorithm avoid falling into the local optimal solution, and increase the possibility of finding the global optimal solution. In pile driver scheduling, this ability helps find the optimal resource allocation solution.

[0201] 3. Balance resource utilization and scheduling efficiency

[0202] Optimize scheduling time: By adjusting the allocation of pile drivers, the algorithm can reduce construction time and cost and improve scheduling efficiency. The variation and migration of habitats can continuously optimize the use of pile drivers and task allocation.

[0203] 4. Respond to dynamic changes

[0204] Real-time adjustment: In actual construction, tasks and environmental conditions may change. The BBO algorithm can quickly respond to these changes and optimize the scheduling of pile drivers by recalculating fitness values ​​and adjusting migration strategies.

[0205] In summary, with the help of the above technical solution of this embodiment, by collecting statistics on pile driver equipment and operator information, building a large database of historical pile driving data and analyzing it, it is possible to intelligently adjust the equipment control information according to different construction environments, improve the work efficiency and construction quality of the pile driver; with the help of big data analysis, more accurate pile driver scheduling and control are achieved, which can dynamically optimize the allocation of construction tasks, adjust the construction progress in real time, and significantly reduce the waste of construction time and resources; in addition, the introduction of intelligent management and maintenance processes also effectively extends the service life of the equipment and improves the reliability and efficiency of the overall operation. By utilizing the Internet of Things, cloud computing, big data analysis and control models, a large amount of historical pile driving data can be more accurately acquired and processed, and the equipment control information of the pile driver under different construction environments can be systematically evaluated through data cleaning, labeling, classification storage and weight analysis; the introduction of the control model enables the model to adaptively learn and optimize, predict and adjust the control parameters of the pile driver in real time, thereby improving the construction accuracy and efficiency, reducing the errors of human operation, optimizing resource allocation, and significantly improving the overall level of intelligence and adaptability of construction. By setting the scheduling cycle and combining the control model with the biogeographic optimization algorithm, the intelligent and optimized scheduling of the pile driver in the future scheduling cycle is realized. It can match the pile driver with the construction task, take into account the construction environment and equipment type, and accurately predict the piling time required for the pile driver to complete the construction task. The optimization algorithm can effectively reduce the idle time and scheduling time loss of the pile driver, significantly improve the utilization rate of the pile driver resources, reduce the construction cycle and cost, and improve the overall construction efficiency and reliability.

[0206] In order to implement the above embodiments, the present application also proposes a pile driver intelligent control and management device based on big data. Figure 2 The following is a schematic diagram of the structure of a pile driver intelligent control and management device based on big data provided in an embodiment of the present application. Figure 2 As shown, the device comprises:

[0207] The data collection module 210 is used to determine the number of pile drivers that can participate in piling and the operator information, and record the equipment type, equipment serial number and operator list of each pile driver;

[0208] A model training module 220, for acquiring historical piling data of the pile driver during operation, and training a control model based on the historical piling data, wherein the control model is used to generate corresponding equipment control information of the pile driver under a specific construction environment;

[0209] The task allocation module 230 is used to set a scheduling cycle, obtain construction tasks in a future scheduling cycle, input the pile driver and the construction tasks into the control model to obtain equipment control information, and input the equipment control information into the management scheduling model for iterative analysis to match the recommended allocation plan of the pile driver;

[0210] The task execution module 240 is used to dispatch the pile driver to the designated construction site to perform the construction task according to the recommended allocation plan, monitor the status data of the pile driver during the construction process in real time, and adjust the equipment control information of the pile driver according to the feedback of the status data.

[0211] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0212] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0213] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0214] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0215] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0216] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0217] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0218] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0219] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0220] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0221] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0222] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0223] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0224] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A pile driver intelligent control management method based on big data, characterized in that: The following steps are involved: Determine the number of pile drivers that can participate in piling and the operator information, and record the equipment type, equipment serial number and operator list of each pile driver; Acquire historical piling data of the pile driver during operation, and train a control model based on the historical piling data, wherein the control model is used to generate corresponding equipment control information of the pile driver under a specific construction environment; Setting a scheduling cycle, obtaining construction tasks within a future scheduling cycle, inputting the pile driver and the construction tasks into the control model to obtain equipment control information, and inputting the equipment control information into the management scheduling model for iterative analysis to match a recommended allocation plan for the pile driver; The pile driver is dispatched to a designated construction site to perform construction tasks according to the recommended allocation plan, status data of the pile driver during construction is monitored in real time, and equipment control information of the pile driver is adjusted according to feedback from the status data.

2. The method according to claim 1, characterized in that The obtaining of historical piling data of the pile driver during operation and training of a control model based on the historical piling data includes: Performing data preprocessing on the historical piling data, adding tags to the preprocessed historical piling data, and storing the historical piling data according to the tags; Based on the type of the tag, extract the construction environment information and equipment control information from the historical piling data, build a pile driver evaluation system, quantify the historical piling data, and then analyze and obtain the weight value of each indicator in the historical piling data; The construction environment information is defined as input data, the equipment control information is defined as output data, the control model is constructed and deployed to a distributed data processing framework, and the control model is trained in parallel using the historical piling data in a batch processing learning mode.

3. The method according to claim 2, characterized in that Historical piling data includes construction environment information and equipment control information; The construction environment information includes: geological parameters of the construction site and meteorological parameters during the construction process; The equipment control information includes: pile driving depth, pile driving time, vibration frequency, hydraulic pressure, inclination angle, and pile driver type.

4. The method according to claim 3, characterized in that The learning mode using batch processing uses the historical pile driving data to perform parallel training on the control model, including: Establish a training set and a test set based on the historical piling data, and divide the training set into multiple data subsets, which are stored in a distributed file system respectively; Using the core node, the structure of the control model, the data subset and the weight value are sent to the computing node; Using a batch training method, a partial data subset on the computing node is input into the control model for training; Instruct the computing node to update the weight value and return it to the core node; The network weights of the control model are updated according to the core nodes, and the error between the expected output and the actual output is calculated, and the training process is controlled according to the error and the number of iterations; Stop training and output the control model after training.

5. The method according to claim 4, characterized in that The using the core node to send the structure of the control model, the data subset and the weight value to the computing node includes: Starting a distributed computing platform, and using a collection operator to input the data subset as a resilient distributed data set into the computing node; The driver process reads the initial weight value in the control model, and uses the broadcast variable operator to send the weight value to each of the computing nodes; Each of the computing nodes is controlled to construct a control model instance using the initial weight value.

6. The method according to claim 5, characterized in that The step of inputting the equipment control information into a management scheduling model for iterative analysis to match the recommended allocation scheme of the pile driver includes: Set the scheduling cycle in the pile driver management platform, obtain the construction tasks to be executed uploaded by the construction site, and count the number of construction tasks in the current scheduling cycle and future scheduling cycles; Inputting the construction environment information corresponding to the construction site into the trained control model, and outputting the equipment control information corresponding to the pile driver under the construction environment information, wherein the equipment control information includes the piling time required to complete the construction task; According to the piling time required for the pile driver to perform the construction task and the idle time during which the pile driver performs the construction task, a time loss function for a single pile driver to participate in the scheduling is set; The management and scheduling model is constructed to reduce the time loss function as the goal, and through parameter assignment and population iterative optimization, a recommended allocation plan for pile drivers to perform construction tasks within the future scheduling period is generated.

7. The method according to claim 6, characterized in that The expression of the time loss function is: Where L represents the time loss function of pile driver resource usage; K represents loss efficiency; n p Indicates the number of pile drivers; n t Indicates the number of construction tasks; X ij It represents the piling time of the i-th pile driver performing the j-th construction task; T ij represents the total time that the i-th pile driver participates in the j-th construction task; Z j Represents the remaining time after the jth construction task is completed.

8. The method according to claim 7, characterized in that The management and scheduling model is constructed to reduce the time loss function as the goal, and to generate a recommended allocation plan for the pile driver to perform construction tasks in the future scheduling period through parameter assignment and population iterative optimization, including: Initialize the algorithm parameter values ​​of the biogeographic optimization algorithm, initialize the population size and the number of cycles, randomly generate several habitats, and initialize all species groups, wherein the species groups include; Calculate the fitness value, sort the fitness value of each habitat in descending order, and generate the number of species in the habitat and the corresponding immigration and emigration rate values ​​according to the sorting results; Use the immigration rate parameters and the emigration rate parameters to complete the population migration action; By calculating the immigration rate parameters and the emigration rate parameters, the probability value of a certain type of population appearing in the habitat is obtained, and the population variation rate value of the habitat is generated; Use the population mutation rate value to perform mutation actions; The mutation operation is continued until the preset maximum number of cycles is reached, and the output is used as the recommended allocation plan for the pile driver.

9. The method according to claim 8, characterized in that The fitness calculation formula is: minfitness=α×L(X)+β×Zmi n In the formula, fitness represents fitness; α and β both represent weight factors; L(X) represents the use of the pile driver; Zmi n It represents the remaining time of the minimized pile driver outside the construction task.

10. A pile driver intelligent control and management device based on big data, characterized in that: include: A data acquisition module is used to determine the number of pile drivers that can participate in piling and the operator information, and record the equipment type, equipment serial number and operator list of each pile driver; A model training module, used for acquiring historical piling data of the pile driver during operation, and training a control model based on the historical piling data, wherein the control model is used for generating equipment control information corresponding to the pile driver under a specific construction environment; A task allocation module is used to set a scheduling cycle, obtain construction tasks within a future scheduling cycle, input the pile driver and the construction tasks into the control model to obtain equipment control information, and input the equipment control information into the management scheduling model for iterative analysis to match the recommended allocation plan for the pile driver; The task execution module is used to dispatch the pile driver to the designated construction site to perform the construction task according to the recommended allocation plan, monitor the status data of the pile driver during the construction process in real time, and adjust the equipment control information of the pile driver according to the feedback of the status data.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 9 when being executed by a processor.

Images