Communication engineering quality monitoring analysis method and device based on artificial intelligence

Abstract

The invention provides a communication engineering quality monitoring analysis method and device based on artificial intelligence, and relates to the technical field of artificial intelligence and communication engineering, and the method comprises the steps: collecting communication engineering quality data; preprocessing the communication engineering quality data to obtain preprocessed data; inputting the preprocessed data into a communication engineering quality analysis decision model to obtain an analysis decision result corresponding to the communication engineering quality data; the communication engineering quality analysis decision model is generated by pre-training a machine learning model according to a mapping relationship between communication engineering quality sample data and a quality data analysis decision; and displaying the communication engineering quality data and the analysis decision result through an application display platform.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence and communication engineering technology, and in particular to a communication engineering quality monitoring and analysis method and device based on artificial intelligence. 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 rapidly developing field of communication technology, communication engineering management and monitoring are facing unprecedented challenges. These challenges are not only due to the continuous upgrading of technology, but also reflected in the tediousness and inefficiency of daily work and the serious lack of intelligent technology.

[0004] In the monitoring of communication engineering quality data, the traditional method uses manual methods to perform statistical analysis on various data. Due to the large differences in the formats of quality information of different categories and the uncertainty of human errors, the statistical results are poor in accuracy, and large-scale data statistics require a certain amount of time, resulting in a certain lag in the analysis results. In addition, traditional analysis methods can only perform fuzzy analysis on the characteristics and trends of communication engineering quality data. When there are missing values, outliers, duplicate values, etc. in the data, targeted processing cannot be performed. In addition, the dimensions of different data vary greatly, and statistical methods cannot distinguish data of different dimensions. Therefore, the analysis results will be inaccurate and the quality cannot be dynamically monitored.

[0005] With the rapid development of information technology, intelligent technology has gradually penetrated into various industries, bringing revolutionary changes to the traditional communication engineering industry. However, in the field of communication engineering quality monitoring, the application of intelligent technology is still relatively lagging behind. Many companies still remain in the traditional working mode and lack in-depth understanding and knowledge of intelligent technology, which undoubtedly restricts the innovation and development of the industry.

[0006] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects, accurately and quickly analyze the quality of communication projects, and provide effective decision-making. Summary of the invention

[0007] In order to solve the problems existing in the prior art, the present invention proposes a communication engineering quality monitoring and analysis method and device based on artificial intelligence.

[0008] In a first aspect of an embodiment of the present invention, a communication engineering quality monitoring and analysis method based on artificial intelligence is proposed, comprising:

[0009] Collect communication engineering quality data;

[0010] Preprocessing the communication engineering quality data to obtain preprocessed data;

[0011] The pre-processed data is input into a communication engineering quality analysis and decision model to obtain an analysis and decision result corresponding to the communication engineering quality data; the communication engineering quality analysis and decision model is generated by pre-training a machine learning model based on a mapping relationship between the communication engineering quality sample data and the quality data analysis and decision;

[0012] The communication engineering quality data and analysis and decision-making results are displayed through the application display platform.

[0013] In a second aspect of an embodiment of the present invention, a communication engineering quality monitoring and analysis device based on artificial intelligence is proposed, comprising:

[0014] Collection module, used to collect communication engineering quality data;

[0015] A preprocessing module, used to preprocess the communication engineering quality data to obtain preprocessed data;

[0016] An analysis and decision module is used to input the preprocessed data into a communication engineering quality analysis and decision model to obtain an analysis and decision result corresponding to the communication engineering quality data; the communication engineering quality analysis and decision model is generated by pre-training a machine learning model based on a mapping relationship between communication engineering quality sample data and quality data analysis and decision;

[0017] The display module is used to display the communication engineering quality data and analysis and decision results through an application display platform.

[0018] 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 artificial intelligence-based communication engineering quality monitoring and analysis method when executing the computer program.

[0019] 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 quality monitoring and analysis method based on artificial intelligence is implemented.

[0020] 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, an artificial intelligence-based communication engineering quality monitoring and analysis method is implemented.

[0021] The communication engineering quality monitoring and analysis method and device based on artificial intelligence proposed by the present invention collects communication engineering quality data; pre-processes the communication engineering quality data to obtain pre-processed data; the communication engineering quality analysis decision model is generated by pre-training the machine learning model according to the mapping relationship between the communication engineering quality sample data and the quality data analysis decision; the pre-processed data is input into the communication engineering quality analysis decision model to obtain the analysis and decision results corresponding to the communication engineering quality data; the communication engineering quality data and the analysis and decision results are displayed through the application display platform. The overall scheme uses the machine learning model to continuously learn and train a large amount of communication engineering quality data, which can identify the complex laws and trends in the communication engineering quality data, automatically perform monitoring tasks, and do not require manual intervention, which greatly improves the efficiency and accuracy of quality monitoring; the present invention can also combine the adaptive learning ability of the machine learning model, face the addition of new data and continuously improve and optimize, and continuously adapt to the new needs and challenges of communication engineering quality monitoring. And it can also predict potential problems in the communication engineering quality data, so that it can take preventive measures in advance, which helps to reduce the possibility of failure, improve the stability and reliability of the communication network, and provide strong technical support for communication engineering quality analysis and decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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.

[0023] Figure 1 It is a flow chart of a communication engineering quality monitoring and analysis method based on artificial intelligence according to an embodiment of the present invention.

[0024] Figure 2 It is a flowchart of model training according to an embodiment of the present invention.

[0025] Figure 3 It is a flowchart of iterative model training according to a specific embodiment of the present invention.

[0026] Figure 4A It is a schematic diagram of the architecture of a communication engineering quality monitoring and analysis device based on artificial intelligence according to an embodiment of the present invention.

[0027] Figure 4B It is a schematic diagram of the architecture of a communication engineering quality monitoring and analysis device based on artificial intelligence according to another embodiment of the present invention.

[0028] Figure 5 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] 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.

[0030] 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.

[0031] According to an embodiment of the present invention, a communication engineering quality monitoring and analysis method and device based on artificial intelligence are proposed, which relate to the technical field of artificial intelligence and communication engineering.

[0032] The principle and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0033] Figure 1 FIG. 1 is a flow chart of a method for monitoring and analyzing communication engineering quality based on artificial intelligence according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0034] S101, collecting communication engineering quality data;

[0035] S102, preprocessing the communication engineering quality data to obtain preprocessed data;

[0036] S103, inputting the preprocessed data into a communication engineering quality analysis and decision model to obtain an analysis and decision result corresponding to the communication engineering quality data; the communication engineering quality analysis and decision model is generated by pre-training a machine learning model based on a mapping relationship between the communication engineering quality sample data and the quality data analysis and decision;

[0037] S104, displaying the communication engineering quality data and analysis and decision results through an application display platform.

[0038] The present invention uses machine learning model analysis to continuously learn and train a large amount of communication engineering quality data, can identify complex laws and trends in communication engineering quality data, can automatically perform monitoring tasks without manual intervention, greatly improves the efficiency and accuracy of quality monitoring, and can also predict potential problems in communication engineering quality data, so that preventive measures can be taken in advance, which helps to reduce the possibility of failures, improve the stability and reliability of communication networks, and provide strong technical support for communication engineering quality analysis and decision-making. The present invention can also combine the adaptive learning ability of the machine learning model, continuously improve and optimize in the face of the addition of new data, and can continuously adapt to the new needs and challenges of communication engineering quality monitoring.

[0039] In order to explain the above-mentioned communication engineering quality monitoring and analysis method based on artificial intelligence more clearly, each step is explained in detail below.

[0040] In one embodiment, the collected communication engineering quality data includes at least: signal received power (RSRP), signal received quality (RSRQ), signal-to-noise ratio (SNR), transmission rate, bandwidth, coverage, spectrum efficiency, response time, packet loss rate and number of alarm messages.

[0041] Received Signal Power (RSRP) is a parameter that measures the received signal strength. It indicates the power level of the primary synchronization signal received by the device and can be used to evaluate the signal strength between the device and the base station. Generally, a higher RSRP value indicates a stronger signal strength, while a lower value may indicate a weak signal or interference.

[0042] Received Signal Quality (RSRQ) is a measure of received signal quality, representing the ratio of the primary synchronization signal received by the device to the interference level of adjacent channels. A higher RSRQ value indicates better signal quality, while a lower value may indicate poor signal quality or the presence of interference.

[0043] The signal-to-noise ratio (SNR) is a parameter that measures the ratio between the signal and the background noise, indicating the relationship between the signal strength received by the device and the background noise level. A higher SNR value indicates better signal quality, while a lower value may indicate that the signal is affected by greater interference or noise.

[0044] The transmission rate refers to the amount of data transmitted per unit time during the data transmission process; bandwidth refers to the maximum data rate that a channel can transmit, or the amount of data that can be transmitted within a certain period of time; coverage refers to the geographical area or spatial range that can be covered under specific conditions; spectrum efficiency refers to the amount of data that can be transmitted per unit spectrum bandwidth, reflecting the utilization efficiency of spectrum resources; the larger the value of each of the above indicators, the better the quality of the communication project.

[0045] Response time refers to the time interval from when the user issues a request instruction to when the communication engineering system responds. The time interval includes the transmission time of the request, the processing time of the server or device, and the transmission time of the response.

[0046] Packet loss rate refers to the ratio of the number of lost data packets to the number of sent data groups during data transmission.

[0047] The number of alarm information refers to the number of alarm notification information currently existing in the communication engineering system;

[0048] The smaller the values ​​of the above indicators, the better the quality of the communication project.

[0049] After the aforementioned indicators are collected, they need to be transmitted to a data processing and computing center through a transmission channel for processing. For example, data transmission can be based on a mobile cellular network.

[0050] The Data Processing and Computing Center pre-processes the received communication engineering data, and performs intelligent detection, analysis, and decision-making to evaluate network performance, provide real-time signal quality and trend analysis, and help users understand network status and adjust parameters in a timely manner.

[0051] During the data preprocessing process, since the communication quality data is transmitted based on the wireless environment, various noises will be mixed in the transmission process, which will cause additive interference. Therefore, in the specific implementation, it is also necessary to perform Gaussian filtering on the communication engineering quality data in order to remove the impact of Gaussian white noise on the communication quality data.

[0052] Specifically, the preprocessing method includes at least data cleaning, data dimensionality reduction, and data conversion.

[0053] During data cleaning, missing values ​​are processed by deletion, filling in the mean, mode, median, etc.; outliers are identified through box plot method and deleted or replaced; duplicate values ​​are identified and deleted in the data set by comparing duplicate records to avoid interference with the analysis results.

[0054] When reducing the data dimension, the original characteristics of the data and the characteristics of the training sample data are maintained, and the data dimension is reduced, including:

[0055] Construct a mathematical model of dimensionality reduction (X, F), a multidimensional data space collection N represents the number of samples, sample x i It has K-dimensional features, mapped to F; the expression is:

[0056] F: X→Y, x→y=F(x);

[0057] Among them, x and y are samples in the space set X and space set Y respectively; Sample y i With k-dimensional features, where k< <K;

[0058] The specific meaning of the above process is to transform the spatial set X into high-dimensional samples x through the mapping rule F i Convert to the space set Y to form a low-dimensional sample y i , thus completing the data dimensionality reduction.

[0059] During data conversion, data of different data types and formats are converted into data types and formats suitable for input into the machine learning model. The data conversion method includes at least smoothing and function mapping.

[0060] For example, for data with large differences in data types and formats, the data is converted from one form or structure to another required form or structure. The communication engineering quality data is converted into the format required by the machine learning model through smoothing, function mapping, etc., to meet the input and processing of the model.

[0061] In one embodiment, the present invention uses a multi-layer perceptron (MLP) to build a machine learning model to achieve monitoring, analysis and decision-making of communication engineering quality, uses a large amount of communication engineering data to train the communication engineering quality analysis and decision-making model, and evaluates the model performance by calculating the accuracy error. In the online stage, the communication engineering quality analysis and decision-making model completed by pre-training analyzes the communication engineering quality data to achieve real-time monitoring capabilities.

[0062] refer to Figure 2 , the model training process is:

[0063] S201, constructing an initial model, wherein the initial model is a machine learning model constructed by a multi-layer perceptron;

[0064] The multilayer perceptron (MLP) consists of an input layer, one or more hidden layers, and an output layer. Each layer consists of multiple neurons, and the neurons are connected by weights. The model can continuously adapt to new data and environmental changes, improving its performance and reliability in communication engineering quality monitoring.

[0065] S202, collecting communication engineering quality sample data, and dividing them into a training data set and a test data set;

[0066] When dividing the data set, different ratios can be used, for example, dividing the sample data in a ratio of 7:3 or 8:2.

[0067] S203, using the training data set to train the initial model, learn features and rules from the training data set, identify anomalies or problems in the communication process, and provide analysis and decision support, map communication engineering quality data to quality data analysis and decision, and obtain a communication engineering quality analysis and decision model;

[0068] By training the model using a training data set, the model learns features and patterns from the data and identifies anomalies or problems in the communication process. During the training process, the model calculates the output through forward propagation and adjusts the weights through back propagation to minimize the prediction error.

[0069] S204, evaluating the communication engineering quality analysis and decision model using a test data set, evaluating the performance of the communication engineering quality analysis and decision model under current parameters by calculating the model output accuracy, and completing the training if the performance meets the standard, and continuing to iterate the model if the performance does not meet the standard;

[0070] The trained model is evaluated using the test data set, and the model performance is evaluated by calculating the accuracy of the model output (for example, accuracy, recall, F1 score, etc.). If the model performance meets the predetermined standard, the training is completed; otherwise, the model needs to be further iterated, which may include adjusting the model structure, increasing training data, adjusting the learning rate, etc.

[0071] S205, after using the communication engineering quality analysis and decision model to perform real-time monitoring, analysis and decision-making, the output analysis and decision-making results are used as sample data for model iterative training to continuously learn and train the model.

[0072] Deploy the trained model to the actual environment for real-time communication engineering quality monitoring, analysis and decision-making. The output of the model can be used as new sample data for continuous learning and training of the model. Iterative training helps the model adapt to new data patterns and environmental changes, and improves the accuracy and robustness of the model.

[0073] In actual application scenarios, refer to Figure 3 , is a flow chart of iterative model training of a specific embodiment of the present invention. Figure 3 As shown, the specific methods include:

[0074] S301, performing feature selection on the pre-processed communication engineering quality data according to the input requirements of the communication engineering quality analysis and decision model, so as to make it suitable for the input of the communication engineering quality analysis and decision model.

[0075] Specifically, the average values ​​of RSRP, RSRQ, SNR, transmission rate, bandwidth, coverage, spectrum efficiency, response time, packet loss rate and number of alarm messages within a unit sampling time are used as data features.

[0076] S302, when constructing a communication engineering quality analysis and decision model, by learning features and rules from a large amount of data, anomalies or problems in the communication process are identified, thereby achieving communication engineering quality monitoring and decision support.

[0077] The specific steps to build a communication engineering quality analysis and decision model are:

[0078] (1) Determine the input layer, hidden layer, and output layer in the MLP network architecture, the number of nodes in each layer, and the weights and thresholds from the input layer to the hidden layer and from the hidden layer to the output layer after initialization.

[0079] (2) The hidden layer is the key to the MLP network architecture and determines the performance of communication engineering quality analysis. The formula for determining the hidden layer nodes is as follows:

[0080]

[0081] Where n 1 is the number of hidden layer nodes; n is the number of input layer nodes; m is the number of output layer nodes; c is a constant, ranging from [1, 10].

[0082] (3) The activation function is selected as the Sigmoid function. The activation function determines how the output of the neuron responds to the input, and its expression is as follows:

[0083]

[0084] In the formula, S() represents the Sigmoid function, e is the base of the natural logarithm; x' represents the input of the function, which is the weighted sum of the neuron input.

[0085] S303, select the pre-built MLP network structure for communication engineering quality analysis and decision-making, and perform model training on the labeled training data set, so that the model can learn the characteristics and rules in the communication engineering quality data, so that the communication engineering quality data can be analyzed and decided online, and the real-time monitoring capability can be obtained.

[0086] The communication engineering quality analysis decision model is trained using the cross-validation method, which divides the training set into K parts, (K-1) parts are used for training, and 1 part is used for validation. Then each part is used as the test set in turn, and the model performance is obtained after multiple trainings.

[0087] S304, evaluating the constructed communication engineering quality monitoring and communication engineering quality analysis decision model.

[0088] Specifically, an independent test dataset is used to evaluate the trained model, and the performance of the communication engineering quality analysis decision model under the current parameters is evaluated by calculating the mean square error (MSE) recognition accuracy index.

[0089] The MSE calculation formula is as follows:

[0090]

[0091] In the formula, MSE represents mean square error, M is the number of samples, y is the training data; y k' This is the analysis and decision result of the communication engineering quality analysis decision model. By evaluating the MSE index, the parameters in the model are dynamically adjusted to minimize the loss function.

[0092] S305, in the online stage, the real-time communication engineering quality data is preprocessed using the same method, and then input into the pre-trained communication engineering quality analysis and decision model for analysis and decision-making, and the optimal quality monitoring result under the configuration is output.

[0093] The model output analysis and decision results can be quality scores, anomaly detection, fault prediction, etc., which can be provided to operation and maintenance personnel or automated monitoring systems in the form of real-time reports, alerts or direct intervention.

[0094] During the online phase, an automated monitoring system can be set up to track the performance of the model and the quality of the data, and to promptly notify the operation and maintenance personnel when the model performance deteriorates or the data becomes abnormal.

[0095] S306, with the continuous generation of new communication engineering quality data and the continuous iteration of the model, the communication engineering quality analysis and decision-making model is continuously learned and improved.

[0096] After evaluating the output of the model, the accuracy and effectiveness can be determined. Based on the evaluation results, the model can be fine-tuned or retrained to improve its performance in future predictions. Through continuous learning, the output results of the online phase are compared with the actual observed results, feedback data is collected, and the model is continuously learned and improved using this data to adapt to changes in the quality of communication engineering.

[0097] Specifically, more communication engineering data or historical data can be collected to retrain the communication engineering quality analysis decision model to further improve the recognition accuracy and generalization ability of the model.

[0098] In one embodiment, after obtaining the analysis and decision results, the communication engineering quality data and the analysis and decision results may be displayed through an application display platform.

[0099] Specifically, the analysis and decision results corresponding to the communication engineering quality data output by the communication engineering quality analysis and decision model are displayed in a visual way in the form of numbers, charts, reports, etc., so that users can quickly and intuitively understand the key information and trends in the data. For example, the software platform is used to implement it. In addition to the result presentation, it also provides a human-computer interaction interface, so that managers can manage and download the communication engineering quality analysis results.

[0100] The present invention utilizes the MLP network model to continuously learn and train a large amount of communication engineering quality data, so as to identify the complex laws and trends in the communication engineering quality data, and can automatically perform monitoring tasks without human intervention, thereby greatly improving the efficiency and accuracy of quality monitoring.

[0101] When analyzing decisions, the model can also be used to predict potential problems in communication engineering quality data, so that preventive measures can be taken in advance, which helps reduce the possibility of failures and improve the stability and reliability of communication networks. The MLP network model has adaptive learning capabilities and can be continuously improved and optimized with the addition of new data, and can continuously adapt to new needs and challenges of communication engineering quality monitoring.

[0102] 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.

[0103] After introducing the method of the exemplary embodiment of the present invention, next, refer to FIG. 4A to FIG. 4B An artificial intelligence-based communication engineering quality monitoring and analysis device according to an exemplary embodiment of the present invention is introduced.

[0104] The implementation of the communication engineering quality monitoring and analysis device based on artificial intelligence 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.

[0105] Based on the same inventive concept, the present invention also proposes a communication engineering quality monitoring and analysis device based on artificial intelligence, such as Figure 4A As shown, the device comprises:

[0106] The collection module 410 is used to collect communication engineering quality data;

[0107] A preprocessing module 420 is used to preprocess the communication engineering quality data to obtain preprocessed data;

[0108] The analysis and decision module 430 is used to input the pre-processed data into the communication engineering quality analysis and decision model to obtain the analysis and decision results corresponding to the communication engineering quality data; the communication engineering quality analysis and decision model is generated by pre-training the machine learning model according to the mapping relationship between the communication engineering quality sample data and the quality data analysis and decision;

[0109] The display module 440 is used to display the communication engineering quality data and analysis and decision results through an application display platform.

[0110] In one embodiment, the communication engineering quality data includes at least: signal reception power, signal reception quality, signal-to-noise ratio, transmission rate, bandwidth, coverage, spectrum efficiency, response time, packet loss rate and number of alarm messages.

[0111] In one embodiment, reference Figure 4B , the device further includes: a transmission module 450;

[0112] The transmission module 450 transmits the collected communication engineering quality data through a data transmission channel; wherein the data transmission channel adopts a mobile cellular network.

[0113] In one embodiment, the preprocessing method includes at least data cleaning, data dimensionality reduction, and data conversion.

[0114] In one embodiment, during data cleaning, missing values ​​are processed by deletion, filling the mean value, mode, median, etc.; outliers are identified by box plot method and deleted or replaced; duplicate values ​​are identified by comparing duplicate records and deleted from the data set;

[0115] When reducing the data dimension, the original characteristics of the data and the characteristics of the training sample data are maintained, and the data dimension is reduced, including:

[0116] Construct a mathematical model of dimensionality reduction (X, F), a multidimensional data space collection N represents the number of samples, sample x i It has K-dimensional features, mapped to F; the expression is:

[0117] F: X→Y, x→y=F(x);

[0118] Among them, x and y are samples in the space set X and space set Y respectively; Sample y i With k-dimensional features, where k< <K;

[0119] During data conversion, data of different data types and formats are converted into data types and formats suitable for input into the machine learning model. The data conversion method includes at least smoothing and function mapping.

[0120] In one embodiment, the training process of the communication engineering quality analysis decision model is as follows:

[0121] Building an initial model, wherein the initial model is a machine learning model built by a multi-layer perceptron;

[0122] Collect communication engineering quality sample data and divide them into training data set and test data set;

[0123] The initial model is trained using the training data set, features and rules are learned from the training data set, anomalies or problems in the communication process are identified, analysis and decision support are provided, and mapping learning is performed from communication engineering quality data to quality data analysis and decision making, thereby obtaining a communication engineering quality analysis and decision making model;

[0124] The communication engineering quality analysis and decision model is evaluated using a test data set, and the performance of the communication engineering quality analysis and decision model under current parameters is evaluated by calculating the model output accuracy. If the performance meets the standard, the training is completed; if the performance does not meet the standard, the model continues to be iteratively trained;

[0125] After using the communication engineering quality analysis and decision-making model for real-time monitoring, analysis and decision-making, the output analysis and decision-making results will be used as sample data for model iterative training to carry out continuous learning and training of the model.

[0126] It should be noted that although several modules of the communication engineering quality monitoring and analysis device based on artificial intelligence 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.

[0127] Based on the above invention concept, Figure 5 As shown, the present invention also proposes a computer device 500, including a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520, wherein the processor 520 implements the aforementioned communication engineering quality monitoring and analysis method based on artificial intelligence when executing the computer program 530.

[0128] 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 quality monitoring and analysis method based on artificial intelligence is implemented.

[0129] 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 quality monitoring and analysis method based on artificial intelligence.

[0130] The communication engineering quality monitoring and analysis method and device based on artificial intelligence proposed in the present invention collect communication engineering quality data; pre-process the communication engineering quality data to obtain pre-processed data; the communication engineering quality analysis decision model is generated by pre-training the machine learning model according to the mapping relationship between communication engineering quality sample data and quality data analysis decision; the pre-processed data is input into the communication engineering quality analysis decision model to obtain the analysis and decision results corresponding to the communication engineering quality data; the communication engineering quality data and the analysis and decision results are displayed through an application display platform. The overall solution adopts machine learning model analysis to continuously learn and train a large amount of communication engineering quality data, which can identify complex laws and trends in communication engineering quality data, and can automatically perform monitoring tasks without human intervention, which greatly improves the efficiency and accuracy of quality monitoring, and can also predict potential problems in communication engineering quality data, so that preventive measures can be taken in advance, which helps to reduce the possibility of failures, improve the stability and reliability of communication networks, and provide strong technical support for communication engineering quality analysis decisions.

[0131] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of laws and regulations.

[0132] 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.

[0133] 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.

[0134] 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 comprising 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.

[0135] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0136] 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 quality monitoring and analysis method based on artificial intelligence, characterized in that: include: Collect communication engineering quality data; Preprocessing the communication engineering quality data to obtain preprocessed data; The pre-processed data is input into a communication engineering quality analysis and decision model to obtain an analysis and decision result corresponding to the communication engineering quality data; the communication engineering quality analysis and decision model is generated by pre-training a machine learning model based on a mapping relationship between the communication engineering quality sample data and the quality data analysis and decision; The communication engineering quality data and analysis and decision-making results are displayed through the application display platform.

2. The method according to claim 1, characterized in that The communication engineering quality data includes at least: signal reception power, signal reception quality, signal-to-noise ratio, transmission rate, bandwidth, coverage, spectrum efficiency, response time, packet loss rate and number of alarm messages.

3. The method according to claim 1, characterized in that The method further includes: The collected communication engineering quality data is transmitted through a data transmission channel; wherein the data transmission channel adopts a mobile cellular network.

4. The method according to claim 1, characterized in that: The preprocessing method at least includes data cleaning, data dimension reduction, and data conversion.

5. The method according to claim 4, characterized in that When cleaning data, missing values ​​are processed by deleting, filling the mean, mode, median, etc.; outliers are identified by box plot method and deleted or replaced; duplicate values ​​are identified and deleted in the data set by comparing duplicate records; When reducing the data dimension, the original characteristics of the data and the characteristics of the training sample data are maintained, and the data dimension is reduced, including: Construct a mathematical model of dimensionality reduction (X, F), a multidimensional data space collection N represents the number of samples, sample x i It has K-dimensional features, mapped to F; the expression is: F: X→Y, x→y=F(x); Among them, x and y are samples in the space set X and space set Y respectively; Sample y i With k-dimensional features, where k< <K; During data conversion, data of different data types and formats are converted into data types and formats suitable for input into the machine learning model. The data conversion method includes at least smoothing and function mapping.

6. The method according to claim 1, characterized in that The communication engineering quality analysis and decision model is generated by pre-training a machine learning model based on the mapping relationship between communication engineering quality sample data and quality data analysis and decision making, and includes: Building an initial model, wherein the initial model is a machine learning model built by a multi-layer perceptron; Collect communication engineering quality sample data and divide them into training data set and test data set; The initial model is trained using the training data set, features and rules are learned from the training data set, anomalies or problems in the communication process are identified, analysis and decision support are provided, and mapping learning is performed from communication engineering quality data to quality data analysis and decision making, thereby obtaining a communication engineering quality analysis and decision making model; The communication engineering quality analysis and decision model is evaluated using a test data set, and the performance of the communication engineering quality analysis and decision model under current parameters is evaluated by calculating the model output accuracy. If the performance meets the standard, the training is completed; if the performance does not meet the standard, the model continues to be iteratively trained; After using the communication engineering quality analysis and decision-making model for real-time monitoring, analysis and decision-making, the output analysis and decision-making results will be used as sample data for model iterative training to carry out continuous learning and training of the model.

7. A communication engineering quality monitoring and analysis device based on artificial intelligence, characterized in that: include: Collection module, used to collect communication engineering quality data; A preprocessing module, used for preprocessing the communication engineering quality data to obtain preprocessed data; An analysis and decision module is used to input the preprocessed data into a communication engineering quality analysis and decision model to obtain an analysis and decision result corresponding to the communication engineering quality data; the communication engineering quality analysis and decision model is generated by pre-training a machine learning model based on a mapping relationship between communication engineering quality sample data and quality data analysis and decision; The display module is used to display the communication engineering quality data and analysis and decision results 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