Communication engineering intelligent scheduling method and device based on big data analysis

Abstract

The invention provides a communication engineering intelligent scheduling method and device based on big data analysis, and relates to the technical field of communication engineering and big data analysis, and the method comprises the steps: collecting communication engineering data through a data collection device; preprocessing the communication engineering data to obtain preprocessed data; inputting the preprocessed data into a communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; wherein the communication engineering scheduling model is generated by pre-training a machine learning model according to a mapping relation between a communication engineering data sample and intelligent scheduling data; and displaying the intelligent scheduling data through an application display platform. According to the invention, a reasonable distribution mode can be provided for communication engineering resources, a message sharing mode is improved, the efficiency of communication cooperation is improved, and effective support is provided for resource scheduling decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of communication engineering and big data analysis, and in particular to a communication engineering intelligent scheduling method and device based on big data analysis. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] In the construction of communication projects, especially in the field of backbone network transmission projects, the complexity of the project is self-evident. An engineering project may involve dozens or even hundreds of construction sites, which are often scattered over a wide area, and the distance between engineering testers may reach thousands of kilometers. In this case, in order to successfully complete the testing or construction of a project, close collaboration between the various sites along the line becomes essential. This requires the establishment of an efficient communication and liaison mechanism between sites to ensure real-time information transmission, and also requires rapid response and seamless collaboration of staff at each site to enable the construction of communication projects to proceed as scheduled. However, in the actual construction of communication projects, there are many problems:

[0004] 1. Uneven resource allocation is a significant problem. Due to the large scale of the project, many resources and personnel are involved. If resources cannot be reasonably allocated according to actual needs, it may lead to excess resources in some links and shortage of resources in other links, thus affecting the progress of the entire project.

[0005] 2. Poor communication is also a common problem. Project scheduling requires collaboration between multiple departments and teams. If there is a lack of effective communication mechanisms and information sharing platforms, it may lead to untimely and inaccurate information transmission, and even misunderstandings and conflicts, affecting the coordination and overall efficiency of the project.

[0006] 3. The lack of accuracy and foresight in scheduling decisions is also an issue that needs attention. In the process of project scheduling, it is necessary to make quick and accurate decisions based on actual conditions to deal with various emergencies and changes. However, if the scheduling decisions lack foresight and accuracy, it may lead to project delays, waste of resources and even quality problems.

[0007] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects and effectively improve the resource allocation, communication efficiency and scheduling decision-making of communication engineering. Summary of the invention

[0008] In order to solve the problems existing in the prior art, the present invention proposes a communication engineering intelligent scheduling method and device based on big data analysis. Through the present invention, a reasonable allocation method for communication engineering resources can be provided, the message sharing method can be improved, the efficiency of communication and collaboration can be improved, and effective support can be provided for resource scheduling decisions.

[0009] In a first aspect of an embodiment of the present invention, a communication engineering intelligent scheduling method based on big data analysis is proposed, the method comprising:

[0010] Collect communication engineering data using data acquisition equipment;

[0011] Preprocessing the communication engineering data to obtain preprocessed data;

[0012] The pre-processed data is input into a communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; wherein the communication engineering scheduling model pre-trains and generates a machine learning model according to a mapping relationship between the communication engineering data samples and the intelligent scheduling data;

[0013] The intelligent scheduling data is displayed through an application display platform.

[0014] In a second aspect of an embodiment of the present invention, a communication engineering intelligent scheduling device based on big data analysis is proposed, the device comprising:

[0015] A collection module, used for collecting communication engineering data using data collection equipment;

[0016] A preprocessing module, used for preprocessing the communication engineering data to obtain preprocessed data;

[0017] A machine learning module, used for inputting the pre-processed data into a communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; wherein the communication engineering scheduling model pre-trains and generates a machine learning model according to a mapping relationship between the communication engineering data samples and the intelligent scheduling data;

[0018] The display module is used to display the intelligent scheduling data through an application display platform.

[0019] In a third aspect of an embodiment of the present invention, a computer device is proposed, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements an intelligent scheduling method for communication engineering based on big data analysis when executing the computer program.

[0020] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a communication engineering intelligent scheduling method based on big data analysis is implemented.

[0021] In a fifth aspect of an embodiment of the present invention, a computer program product is proposed. The computer program product includes a computer program. When the computer program is executed by a processor, a communication engineering intelligent scheduling method based on big data analysis is implemented.

[0022] The communication engineering intelligent scheduling method and device based on big data analysis proposed in the present invention collect communication engineering data using data acquisition equipment; pre-process the communication engineering data to obtain pre-processed data; input the pre-processed data into the communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; the communication engineering scheduling model pre-trains and generates a machine learning model according to the mapping relationship between the communication engineering data samples and the intelligent scheduling data; and displays the intelligent scheduling data through an application display platform; the overall solution of the present invention realizes communication engineering data analysis and scheduling decisions through a machine learning model, can quickly and accurately process massive communication engineering data, help the communication engineering scheduling system to achieve rapid response and decision-making, reduce the impact of human factors on decision-making results, and improve the accuracy and efficiency of scheduling decisions; the present invention can perform adaptive optimization based on historical data and real-time feedback, and through the analysis of massive historical data, can predict the changing trend of relevant indicators in a period of time in the future, and can provide strong technical support for communication engineering scheduling decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a communication engineering intelligent scheduling method based on big data analysis according to an embodiment of the present invention.

[0025] Figure 2 It is a schematic diagram of the architectural relationship of an exemplary scenario of the present invention.

[0026] Figure 3 It is a specific flow chart of the training model of one embodiment of the present invention.

[0027] Figure 4 It is a schematic diagram of the architecture of a communication engineering intelligent scheduling device based on big data analysis according to an embodiment of the present invention.

[0028] Figure 5 It is a schematic diagram of the architecture of a communication engineering intelligent scheduling device based on big data analysis according to another embodiment of the present invention.

[0029] Figure 6 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0031] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0032] According to an embodiment of the present invention, a communication engineering intelligent scheduling method and device based on big data analysis are proposed, which relate to the technical field of communication engineering and big data analysis.

[0033] The principle and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0034] Figure 1 FIG. 1 is a flow chart of a communication engineering intelligent scheduling method based on big data analysis according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0035] S101, collecting communication engineering data using a data acquisition device;

[0036] Data acquisition equipment is mainly used for collecting and uploading data related to communication engineering.

[0037] S102, preprocessing the communication engineering data to obtain preprocessed data;

[0038] Preprocessing methods may include outlier detection, missing value processing, data integration, data conversion, data cleaning, etc. In actual application scenarios, other preprocessing methods may be adopted according to actual conditions.

[0039] S103, inputting the preprocessed data into a communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; wherein the communication engineering scheduling model pre-trains and generates a machine learning model according to a mapping relationship between communication engineering data samples and intelligent scheduling data.

[0040] S104: Display the intelligent scheduling data through an application display platform.

[0041] In an actual application scenario, the intelligent scheduling method for communication engineering based on big data analysis proposed in the present invention has the following processing process: using data acquisition equipment to collect communication engineering data, preprocessing the communication engineering data to obtain preprocessed data, inputting the preprocessed data into a communication engineering scheduling model, obtaining intelligent scheduling data corresponding to the communication engineering data, and displaying the intelligent scheduling data through an application display platform; the present invention adopts a machine learning model to realize communication engineering data analysis and scheduling decision-making, which can quickly and accurately process massive communication engineering data, help the communication engineering scheduling system to achieve rapid response and decision-making, reduce the influence of human factors on decision-making results, and improve the accuracy and efficiency of scheduling decisions; the present invention can perform adaptive optimization according to historical data and real-time feedback, and through the analysis of massive historical data, it can predict the changing trend of relevant indicators in the future period of time, and can provide strong technical support for communication engineering scheduling decisions.

[0042] In order to explain the above-mentioned intelligent scheduling method for communication engineering based on big data analysis more clearly, each step is explained in detail below.

[0043] For S101, communication engineering data is collected using a data collection device.

[0044] Specifically, the data acquisition equipment includes at least one or more combinations of communication engineering application terminals, communication engineering test instruments, communication engineering professional data acquisition software, and enterprise internal subsystem platform API data interface;

[0045] In actual application scenarios, data acquisition equipment has no fixed form and only needs to have the ability to collect and upload communication engineering related data.

[0046] refer to Figure 2 , is a schematic diagram of the architecture relationship of an exemplary scenario of the present invention. Figure 2 As shown, the architecture includes data collection equipment 210, a transmission network 220, a data analysis platform 230 and an application display platform 240.

[0047] The data acquisition device 210 is used for collecting and uploading communication engineering related data.

[0048] Specifically, the communication engineering application terminal can be a base station, switch, router, etc. deployed at the communication engineering site, which collects data on network performance, user behavior and service quality. The collected data types include signal strength, data transmission rate, number of user connections, error rate, etc. The above data is used to provide real-time network operation status and user usage, which is an important basis for scheduling decisions.

[0049] Communication engineering test instruments can be devices used to test the performance of communication networks, such as network analyzers, signal generators, and spectrum analyzers. The types of data collected include signal quality data, such as frequency response, bandwidth, signal-to-noise ratio, etc. The above data can help operation and maintenance personnel evaluate and optimize network performance and ensure communication quality.

[0050] The communication engineering professional data acquisition software is a software tool used to collect data from communication equipment and systems. The collected data types include log files, configuration files, and performance indicators. It collects and organizes data in an automated way, reduces the need for manual operations, and improves the efficiency and accuracy of data collection.

[0051] The API data interface of the enterprise internal subsystem platform is an application programming interface, which is suitable for data exchange and communication between different systems. It mainly collects user data, communication data, and system status information. By collecting data interfaces, data between different systems is integrated to provide comprehensive data support for the intelligent scheduling system.

[0052] By collecting a variety of communication engineering data, efficient data analysis and intelligent decision-making can be supported, thereby optimizing the performance and service quality of the communication network.

[0053] The transmission network 220 is the basis for data transmission and is used to transmit communication engineering related data to the data analysis center for processing. Related data such as user behavior data, network performance data, and business operation data all need to be transmitted in real time, accurately, and efficiently through the transmission network.

[0054] Specifically, the communication engineering data collected by the data collection device is transmitted via a transmission network, the transmission network includes at least a wired network and a wireless network, and the communication engineering data includes at least user behavior data, network performance data and business operation data.

[0055] A wired network is a computer network connected by physical media such as twisted pair, coaxial cable or optical fiber. Data is transmitted through the physical media. The data is transmitted in the medium in the form of electromagnetic waves or optical signals.

[0056] Wireless network is a type of network that uses electromagnetic waves as a carrier to achieve data transmission. It does not require a physical medium connection. It can include personal wireless networks, local area wireless networks, and wide area wireless networks. The selection of different networks is determined according to the network coverage requirements and application scenarios.

[0057] The data analysis center 230 is used to receive, process and store communication engineering related data. The communication engineering related data transmitted to the data analysis center via the transmission network has different data types and formats due to different data acquisition devices. Different data need to be standardized and pre-processed before subsequent communication engineering intelligent scheduling big data analysis can be performed.

[0058] Specifically, the communication engineering data is standardized, wherein the standardization is to standardize the data whose values ​​differ by more than a preset value range and whose dimensions are different, to obtain data in the same range.

[0059] Since different data units and numerical ranges vary greatly when training big data analysis models, it is necessary to standardize the data before model training so that the data are within the same range. The specific method is to normalize the data with large differences in numerical values ​​and dimensions to the same value range.

[0060] The application display platform 240 is used to feed back the intelligent scheduling data output by the data analysis center to the user and present it.

[0061] For S102, the communication engineering data is preprocessed to obtain preprocessed data.

[0062] In one embodiment, when the data analysis center performs preprocessing, it includes at least preprocessing methods such as outlier detection, missing value processing, data integration, data conversion, and data cleaning.

[0063] The processing method used for the outlier detection includes at least one or more combinations of a box plot method and a standard score processing method (Z-score). The specific method needs to be determined based on the application scenario and requirements.

[0064] Specifically, the box plot is a very intuitive and easy-to-understand outlier detection method, which is drawn based on quartiles and describes the distribution of data through the minimum value, first quartile (Q1, i.e. 25% quantile), median (Q2, i.e. 50% quantile), third quartile (Q3, i.e. 75% quantile) and maximum value of the data. Outliers are usually defined as values ​​less than Q1-1.5×IQR (IQR, interquartile range, i.e. Q3-Q1) or greater than Q3+1.5×IQR. The box plot method is simple and intuitive, and is suitable for outlier detection of univariate data.

[0065] Specifically, the Z-score method is a method for detecting outliers based on the standard deviation of the data distribution. For each data point, it calculates the difference between the point and its mean, and then divides it by the standard deviation. The result is the Z-score of the point. In a normal distribution, about 99.7% of the data points have Z-score values ​​between -3 and 3, so data points with an absolute Z-score greater than 3 are generally considered outliers. The Z-score method takes into account the overall distribution of the data and is applicable to most types of data.

[0066] The processing methods used for missing value processing include at least one or more combinations of data deletion processing methods, measurement reporting data processing methods and predictive filling data processing methods; wherein, the data deletion processing method is to select to delete by row or by column the data containing missing values ​​according to the missing situation; the measurement filling processing method is to fill the missing data according to the attributes of the data using the central measurement values ​​including the mean, median and mode; the predictive filling processing method is to use the missing attributes as the dependent variable, establish a classification or regression model, and model the missing values.

[0067] The data integration is to integrate and merge the data from different communication engineering data sources to form a unified form of data for storage.

[0068] The data conversion includes at least data normalization processing and data discretization processing; wherein, the data normalization processing is to scale the data proportionally so that the data falls into a set interval, such as [-1,1] or [0,1]; the data discretization processing is to segment the continuous data so that the data falls into a discrete interval.

[0069] The data cleaning is to remove data that does not meet the standards for completeness, accuracy, relevance, and duplicate data.

[0070] For S103, the preprocessed data is input into a communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; wherein the communication engineering scheduling model pre-trains and generates a machine learning model according to a mapping relationship between communication engineering data samples and intelligent scheduling data.

[0071] refer to Figure 3 , the specific process of training the model is:

[0072] S301, converting the communication engineering sample data into a sample data set, and dividing it into a training set, a validation set, and a test set;

[0073] S302, constructing an initial model, wherein the initial model is a machine learning model constructed using a back propagation neural network;

[0074] S303, using the training set to train the initial model, combining the intelligent scheduling data, performing mapping learning from communication engineering data to intelligent scheduling data on the initial model, and using the verification set and the test set to perform verification and testing to obtain a communication engineering scheduling model; wherein, when training the model, by adjusting the internal parameter weights of the neural network, through iterative processing, evaluation and optimization of the model, the error between the predicted output and the actual output is minimized.

[0075] Specifically, after preprocessing and standardizing various types of communication engineering data, the data analysis center will perform data analysis intelligent scheduling decision operations. Data analysis intelligent scheduling decision-making involves processes such as model construction, model training, model evaluation, and online intelligent decision scheduling. This step can gradually improve the performance and effect of the communication engineering intelligent scheduling system, and provide more accurate and intelligent decision support for enterprises and teams.

[0076] In the embodiment of the present invention, a back propagation neural network is used to construct a machine learning model. Using the back propagation neural network to analyze communication engineering data to realize intelligent scheduling is a continuous learning process. The learning process of the back propagation neural network is as follows:

[0077] (1) The preprocessed data is input into the back propagation neural network, and the initial weights and thresholds of the neural network are randomly selected in the specified interval to initialize the network.

[0078] (2) Determine the number of input layer N, hidden layer H, and output layer nodes M based on requirements and application scenarios.

[0079] For the hidden layer node h, the input α h It can be expressed as:

[0080] α h =∑w ih ·x i ;

[0081] In the formula, w ih represents the weight from input layer node i to hidden layer node h, x i Represents any set of training sample data.

[0082] (3)α h After being mapped by the transfer function in the hidden layer, the hidden layer output b is obtained. h , expressed as:

[0083] b h =f(α h +θ h )=f(∑w ih ·x i +θ h );

[0084] In the formula, θ h is the threshold of the hidden layer node h, f is the activation function. As the core component of the neural network, the activation function determines the output of the neuron. Different activation functions have different characteristics, and it is necessary to select the appropriate activation function according to the specific task.

[0085] (4) Hidden layer output h After the transfer function mapping of the transmission layer, the output y of the output layer node j is obtained j , expressed as:

[0086] y j =f(∑w hj b h +θ j );

[0087] In the formula, w hj represents the weight of the hidden layer node h and the weight of the output layer node j, θ j is the threshold of output layer node j.

[0088] (5) The output error is:

[0089]

[0090] (6) The weights and thresholds of the modified model are:

[0091]

[0092] In the formula, η is the learning rate, δ M =y j (1-y j )(t j -y j ) is the gradient value of the output layer neurons. is the gradient value of the hidden layer neurons.

[0093] (7) Calculate the global error of the neural network:

[0094]

[0095] Before the sample data training is completed, the above steps (3) to (7) are run repeatedly until the maximum number of training times is reached or the error accuracy requirement is met.

[0096] The back-propagation neural network is a multi-layer feedforward neural network that uses the back-propagation algorithm to train the weights and biases of the network to reduce prediction errors. When the weights are updated, the weights and biases in the network can be updated according to the partial derivatives and the learning rate in the hope of reducing the error during the next forward propagation.

[0097] The training process includes initialization, randomly initializing network weights and biases; iterative training, iterating the training data set multiple times, and in each iteration, all training samples will be used to update the network weights; in each iteration, each sample will undergo a forward propagation and back propagation process; parameter adjustment, adjusting hyperparameters such as learning rate, number of iterations, number of hidden layers, and number of neurons to optimize network performance; evaluation and testing, using validation sets and test sets to evaluate network performance to ensure that the model is not overfitting.

[0098] In the embodiment of the present invention, the training process is an iterative process for minimizing the error between the predicted output and the actual output by adjusting the internal parameter weights of the neural network.

[0099] Specifically, the processed communication engineering data is divided into a training set and a test set. The training set is mainly used for model learning and adjusting model structure and parameters, and the test set is mainly used to evaluate the capabilities of the pre-trained model, overfitting detection, and verification of model performance.

[0100] In the process of evaluation and optimization, the performance and effect of the intelligent scheduling system need to be evaluated, and adjustments and optimizations need to be made according to the actual application situation. Feedback mechanisms are used to continuously improve the model and scheduling system to adapt to changing environments and needs.

[0101] Data analysis and intelligent scheduling is an online real-time process. The data acquisition equipment collects communication engineering data in real time online and uploads it to the data analysis center through the transmission network. After preprocessing in the same way, it is input into the trained back propagation neural network model for data analysis, and the scheduling data is output to the server after intelligent decision-making.

[0102] For S104, the intelligent scheduling data is displayed through an application display platform.

[0103] Specifically, the application display platform is used to feed back the intelligent scheduling data to the user and display it in the form of charts, images and / or animations, making the data easier to understand and use. The application display platform serves as a front end (i.e., a server) so that users can interact with the data through the platform, for example, zooming, filtering and comparing different data sets. The intelligent scheduling data is fed back to the data acquisition device through the transmission network.

[0104] It should be noted that, although the operations of the method of the present invention are described in a specific order in the above embodiments and the accompanying drawings, this does not require or imply that the operations must be performed in the specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0105] After introducing the method of the exemplary embodiment of the present invention, next, refer to Figure 4 An intelligent scheduling device for communication engineering based on big data analysis according to an exemplary embodiment of the present invention is introduced.

[0106] The implementation of the intelligent scheduling device for communication engineering based on big data analysis can refer to the implementation of the above method, and the repetitions will not be repeated. The terms "module" or "unit" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0107] Based on the same inventive concept, the present invention also proposes a communication engineering intelligent scheduling device based on big data analysis, such as Figure 4 As shown, the device comprises:

[0108] The acquisition module 410 is used to acquire communication engineering data using a data acquisition device;

[0109] A preprocessing module 420, used for preprocessing the communication engineering data to obtain preprocessed data;

[0110] The machine learning module 430 is used to input the pre-processed data into the communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; wherein the communication engineering scheduling model pre-trains the machine learning model according to the mapping relationship between the communication engineering data samples and the intelligent scheduling data;

[0111] The display module 440 is used to display the intelligent scheduling data through an application display platform.

[0112] In one embodiment, the data acquisition equipment includes at least one or more combinations of a communication engineering application terminal, a communication engineering test instrument, a communication engineering professional data acquisition software, and an enterprise internal subsystem platform API data interface;

[0113] Use data acquisition equipment to collect communication engineering data, including:

[0114] The communication engineering data collected by the data collection device is transmitted via a transmission network, wherein the transmission network includes at least a wired network and a wireless network, and the communication engineering data includes at least user behavior data, network performance data and business operation data.

[0115] In one embodiment, reference Figure 5 , the device further includes: a standardization processing module 450;

[0116] The communication engineering data is standardized, wherein the standardization is to standardize the data whose values ​​differ by more than a preset value range and whose dimensions differ, to obtain data in the same range.

[0117] In one embodiment, the preprocessing module 420 is specifically used for:

[0118] The preprocessing method at least includes outlier detection, missing value processing, data integration, data conversion, and data cleaning.

[0119] In one embodiment, the processing method used for the outlier detection includes at least one or more combinations of a box plot method and a standard score processing method;

[0120] The processing method adopted for the missing value processing at least includes one or more combinations of a deletion data processing method, a measurement reporting data processing method and a prediction filling data processing method; wherein the deletion data processing method is to select to delete the data containing missing values ​​by row or by column according to the missing situation; the measurement filling processing method is to fill the missing data with the central measurement value including the mean, median and mode according to the attributes of the data; the prediction filling processing method is to take the missing attribute as the dependent variable, establish a classification or regression model, and model the missing values;

[0121] The data integration is to integrate and merge data from different communication engineering data sources to form a unified form of data for storage;

[0122] The data conversion at least includes data normalization processing and data discretization processing; wherein the data normalization processing is to scale the data so that the data falls into a set interval; the data discretization processing is to segment the continuous data so that the data falls into a discrete interval;

[0123] The data cleaning is to remove data that does not meet the standards for completeness, accuracy, relevance, and duplicate data.

[0124] In one embodiment, the machine learning module 430 is specifically used to:

[0125] The communication engineering sample data is converted into a sample data set, and divided into a training set, a validation set, and a test set;

[0126] Constructing an initial model, wherein the initial model is a machine learning model constructed using a back-propagation neural network;

[0127] The initial model is trained using the training set, and in combination with the intelligent scheduling data, the initial model is subjected to mapping learning from communication engineering data to intelligent scheduling data, and the verification set and the test set are used for verification and testing to obtain a communication engineering scheduling model; wherein, when training the model, the error between the predicted output and the actual output is minimized by adjusting the internal parameter weights of the neural network, through iterative processing, evaluation and optimization of the model.

[0128] It should be noted that although several modules of the communication engineering intelligent scheduling device based on big data analysis are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules described above can be concretized in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules to be concretized.

[0129] Based on the above invention concept, Figure 6 As shown, the present invention also proposes a computer device 600, including a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and executable on the processor 620, wherein the processor 620 implements the aforementioned intelligent scheduling method for communication engineering based on big data analysis when executing the computer program 630.

[0130] Based on the aforementioned inventive concept, the present invention proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the aforementioned communication engineering intelligent scheduling method based on big data analysis is implemented.

[0131] Based on the aforementioned inventive concept, the present invention proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements a communication engineering intelligent scheduling method based on big data analysis.

[0132] The communication engineering intelligent scheduling method and device based on big data analysis proposed in the present invention collect communication engineering data using data acquisition equipment; pre-process the communication engineering data to obtain pre-processed data; input the pre-processed data into the communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; the communication engineering scheduling model pre-trains and generates a machine learning model according to the mapping relationship between the communication engineering data samples and the intelligent scheduling data; and displays the intelligent scheduling data through an application display platform; the overall solution of the present invention realizes communication engineering data analysis and scheduling decisions through a machine learning model, can quickly and accurately process massive communication engineering data, help the communication engineering scheduling system to achieve rapid response and decision-making, reduce the impact of human factors on decision-making results, and improve the accuracy and efficiency of scheduling decisions; the present invention can perform adaptive optimization based on historical data and real-time feedback, and through the analysis of massive historical data, can predict the changing trend of relevant indicators in a period of time in the future, and can provide strong technical support for communication engineering scheduling decisions.

[0133] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of laws and regulations.

[0134] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The present invention is described with reference to flowcharts and / or block diagrams of methods and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0136] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0138] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A communication engineering intelligent scheduling method based on big data analysis, characterized in that: The method includes: Collect communication engineering data using data acquisition equipment; Preprocessing the communication engineering data to obtain preprocessed data; Inputting the preprocessed data into a communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; wherein the communication engineering scheduling model pre-trains and generates a machine learning model according to a mapping relationship between the communication engineering data samples and the intelligent scheduling data; The intelligent scheduling data is displayed through an application display platform.

2. The method according to claim 1, characterized in that The data acquisition equipment at least includes one or more combinations of communication engineering application terminals, communication engineering test instruments, communication engineering professional data acquisition software and enterprise internal subsystem platform API data interface; Use data acquisition equipment to collect communication engineering data, including: The communication engineering data collected by the data collection device is transmitted via a transmission network, wherein the transmission network includes at least a wired network and a wireless network, and the communication engineering data includes at least user behavior data, network performance data and business operation data.

3. The method according to claim 1, characterized in that The method further includes: The communication engineering data is standardized, wherein the standardization is to standardize the data whose values ​​differ by more than a preset value range and whose dimensions differ, to obtain data in the same range.

4. The method according to claim 1, characterized in that: Preprocessing the communication engineering data to obtain preprocessed data includes: The preprocessing method at least includes outlier detection, missing value processing, data integration, data conversion, and data cleaning.

5. The method according to claim 4, characterized in that The processing method used for the outlier detection at least includes one or more combinations of a box plot method and a standard score processing method; The processing method adopted for the missing value processing at least includes one or more combinations of a deletion data processing method, a measurement reporting data processing method and a prediction filling data processing method; wherein the deletion data processing method is to select to delete the data containing missing values ​​by row or by column according to the missing situation; the measurement filling processing method is to fill the missing data with the central measurement value including the mean, median and mode according to the attributes of the data; the prediction filling processing method is to take the missing attribute as the dependent variable, establish a classification or regression model, and model the missing values; The data integration is to integrate and merge data from different communication engineering data sources to form a unified form of data for storage; The data conversion at least includes data normalization processing and data discretization processing; wherein the data normalization processing is to scale the data so that the data falls into a set interval; the data discretization processing is to segment the continuous data so that the data falls into a discrete interval; The data cleaning is to remove data that does not meet the standards for completeness, accuracy, relevance, and duplicate data.

6. The method according to claim 1, characterized in that The communication engineering scheduling model is generated by pre-training a machine learning model according to a mapping relationship between communication engineering data samples and intelligent scheduling data, including: The communication engineering sample data is converted into a sample data set, and divided into a training set, a validation set, and a test set; Constructing an initial model, wherein the initial model is a machine learning model constructed using a back-propagation neural network; The initial model is trained using the training set, and in combination with the intelligent scheduling data, the initial model is subjected to mapping learning from communication engineering data to intelligent scheduling data, and the verification set and the test set are used for verification and testing to obtain a communication engineering scheduling model; wherein, when training the model, the error between the predicted output and the actual output is minimized by adjusting the internal parameter weights of the neural network, through iterative processing, evaluation and optimization of the model.

7. A communication engineering intelligent scheduling device based on big data analysis, characterized in that: The device includes: A collection module, used for collecting communication engineering data using data collection equipment; A preprocessing module, used for preprocessing the communication engineering data to obtain preprocessed data; A machine learning module, used for inputting the pre-processed data into a communication engineering scheduling model to obtain intelligent scheduling data corresponding to the communication engineering data; wherein the communication engineering scheduling model pre-trains and generates a machine learning model according to a mapping relationship between the communication engineering data samples and the intelligent scheduling data; The display module is used to display the intelligent scheduling data through an application display platform.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images