5G communication quality analysis method and system based on intelligent AI

Abstract

The present invention relates to the field of intelligent analysis, and discloses a method and system for realizing 5G communication quality analysis based on intelligent AI, wherein the method comprises: collecting multi-source communication data of a 5G communication system, fusing the multi-source communication data, and obtaining fused communication data; calculating the data anomaly coefficient of the fused communication data, removing the anomaly data of the fused communication data, and obtaining the target communication data; identifying the communication characteristics of the 5G communication system, marking the target communication data, obtaining the marked communication data, and establishing an AI communication quality analysis model for the 5G communication system; constructing a SHAP interpretation environment for the AI ​​communication quality analysis model, and calculating the SHAP value of the corresponding predicted value of the AI ​​communication quality analysis model; constructing a SHAP summary diagram for the AI ​​communication quality analysis model, and calculating the behavior reliability coefficient of the AI ​​communication quality analysis model, and when the behavior reliability coefficient meets the preset requirements, constructing a 5G communication quality analysis report for the 5G communication system. The present invention can improve the reliability of 5G communication quality analysis.

Description

Technical Field

[0001] The present invention relates to the field of intelligent analysis, and in particular to a method and system for implementing 5G communication quality analysis based on intelligent AI. Background Art

[0002] 5G communication quality analysis refers to the process of monitoring, evaluating and diagnosing 5G network performance to ensure that the network can provide high-quality services to meet user needs. Through high-quality 5G communication analysis, operators can provide more stable and efficient communication services to meet the needs of emerging applications such as high-definition video transmission, virtual reality, and autonomous driving.

[0003] Currently, 5G communication quality analysis mainly analyzes communication quality by analyzing the collected 5G communication data to train AI models. Due to the diversity of 5G communication data, complex AI models are often regarded as "black boxes" and their decision-making processes are difficult to explain, which affects trust and adoption, thereby reducing the reliability of 5G communication quality analysis. Summary of the invention

[0004] The present invention provides a method and system for implementing 5G communication quality analysis based on intelligent AI, the main purpose of which is to improve the reliability of 5G communication quality analysis.

[0005] To achieve the above objectives, the present invention provides a method for analyzing 5G communication quality based on intelligent AI, comprising:

[0006] Constructing a multi-source data acquisition channel for a 5G communication system, collecting multi-source communication data of the 5G communication system based on the multi-source data acquisition channel, and fusing the multi-source communication data to obtain fused communication data;

[0007] Calculating a data anomaly coefficient of the fused communication data, and removing abnormal data of the fused communication data based on the data anomaly coefficient to obtain target communication data;

[0008] Based on the target communication data, identifying the communication characteristics of the 5G communication system, marking the target communication data, obtaining marked communication data, and establishing an AI communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics;

[0009] Constructing a SHAP interpretation environment for the AI ​​communication quality analysis model, and calculating a SHAP value of a corresponding predicted value of the AI ​​communication quality analysis model based on the SHAP interpretation environment;

[0010] Based on the SHAP value, a SHAP summary graph of the AI ​​communication quality analysis model is constructed; based on the SHAP summary graph, a behavioral reliability coefficient of the AI ​​communication quality analysis model is calculated; when the behavioral reliability coefficient meets preset requirements, a 5G communication quality analysis report of the 5G communication system is constructed.

[0011] Optionally, the construction of a multi-source data acquisition channel for a 5G communication system includes:

[0012] Determining data collection requirements for the 5G communication system;

[0013] Based on the data collection requirement, determining a data collection source of the 5G communication system;

[0014] Configuring the acquisition interface of the data acquisition source;

[0015] Based on the acquisition interface, a multi-source data acquisition channel for the 5G communication system is constructed.

[0016] Optionally, fusing the multi-source communication data to obtain fused communication data includes:

[0017] Preprocessing the multi-source communication data to obtain preprocessed communication data;

[0018] extracting data features of the preprocessed communication data;

[0019] Based on the data features, outputting a data decision value of the preprocessed communication data using a preset modal data model;

[0020] Decision fusion is performed on the data decision values ​​to obtain the fused communication data.

[0021] Optionally, performing decision fusion on the data decision values ​​to obtain the fused communication data includes:

[0022] Determine a fusion function of the data decision value;

[0023] Based on the fusion function, the data decision values ​​are fused using the following formula to obtain fused communication data:

[0024]

[0025] in, Indicates fused communication data, Indicates that the data decision value corresponds to the preprocessed communication data The modal data model of the model type data, Indicates that the data decision value corresponds to the preprocessed communication data Model type data, Preprocessing communication data The data decision value of each model type data.

[0026] Optionally, calculating the data anomaly coefficient of the fused communication data includes:

[0027] marking the fused communication data to correspond to a given data point;

[0028] determining a data point neighborhood of the given data point;

[0029] Calculating the local density of the given data point based on the neighborhood of the data point;

[0030] Based on the local density, a data anomaly coefficient of the given data point is calculated.

[0031] Optionally, calculating the local density of the given data point based on the neighborhood of the data point includes:

[0032] Calculating a neighborhood radius of a neighborhood of the data point;

[0033] Calculate the reachable distance of the given data point;

[0034] Based on the neighborhood radius and the reachable distance, the local density of the given data point is calculated using the following formula:

[0035]

[0036] in, Represents a given data point The local density of Represents a given data point and adjacent data points The distance between Represents a given data point The indices of the adjacent data points, represents the number of given data points, Represents the neighborhood radius of a given data point.

[0037] Optionally, calculating the data anomaly coefficient of the given data point based on the local density includes:

[0038] Based on the local density, calculating the reachable density of the given data point;

[0039] Based on the reachable density, the data anomaly coefficient of the given data point is calculated using the following formula:

[0040]

[0041] in, Represents a given data point The data anomaly coefficient, Represents a given data point The number of data points directly connected to the corresponding data point in its neighborhood, Represents a given data point The indices of the adjacent data points, Represents a given data point Adjacent data points The accessible density, Represents a given data point The attainable density.

[0042] Optionally, the SHAP interpretation environment for constructing the AI ​​communication quality analysis model includes:

[0043] Constructing a SHAP library of the AI ​​communication quality analysis model;

[0044] Loading the AI ​​communication quality analysis model into the SHAP library to obtain a model SHAP library;

[0045] Select a model interpreter from the model SHAP library;

[0046] Based on the model interpreter, a SHAP interpretation environment of the AI ​​communication quality analysis model is constructed.

[0047] Optionally, calculating the behavior reliability coefficient of the AI ​​communication quality analysis model based on the SHAP summary graph includes:

[0048] Constructing a feature value combination corresponding to the input feature of the AI ​​communication quality analysis model;

[0049] Based on the SHAP summary graph, calculating the stability of the eigenvalue combination;

[0050] Based on the stability, the behavioral reliability coefficient of the AI ​​communication quality analysis model is evaluated.

[0051] In order to solve the above problems, the present invention also provides a 5G communication quality analysis system based on intelligent AI, the system comprising:

[0052] A communication data fusion module is used to build a multi-source data acquisition channel for a 5G communication system, collect multi-source communication data of the 5G communication system based on the multi-source data acquisition channel, and fuse the multi-source communication data to obtain fused communication data;

[0053] A data anomaly removal module, used for calculating a data anomaly coefficient of the fused communication data, and removing the abnormal data of the fused communication data based on the data anomaly coefficient to obtain target communication data;

[0054] An AI model building module is used to identify the communication characteristics of the 5G communication system based on the target communication data, mark the target communication data, obtain marked communication data, and establish an AI communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics;

[0055] A SHAP value calculation module, used to construct a SHAP interpretation environment of the AI ​​communication quality analysis model, and calculate a SHAP value of a corresponding predicted value of the AI ​​communication quality analysis model based on the SHAP interpretation environment;

[0056] The communication quality analysis module is used to construct a SHAP summary diagram of the AI ​​communication quality analysis model based on the SHAP value, calculate the behavioral reliability coefficient of the AI ​​communication quality analysis model based on the SHAP summary diagram, and construct a 5G communication quality analysis report of the 5G communication system when the behavioral reliability coefficient meets the preset requirements.

[0057] The embodiment of the present invention can collect multi-source data by constructing a multi-source data collection channel of a 5G communication system, thereby improving the reliability of the data; the embodiment of the present invention can achieve data fusion by fusing the multi-source communication data to obtain fused communication data, thereby improving the reliability of the data; the embodiment of the present invention can screen out abnormal data by calculating the data anomaly coefficient of the fused communication data, thereby improving the accuracy of the data and increasing the reliability of the subsequent data analysis; further, the embodiment of the present invention can quickly evaluate the communication quality by establishing the AI ​​communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics, and further, the SHAP interpretation environment of the AI ​​communication quality analysis model constructed by the embodiment of the present invention can be used as a tool for calculating the behavioral reliability of the AI ​​communication quality analysis model, and the SHAP value of the corresponding predicted value of the AI ​​communication quality analysis model calculated by the embodiment of the present invention based on the SHAP interpretation environment can be used as a data basis for the subsequent model behavior analysis, and finally, the embodiment of the present invention calculates the behavioral reliability coefficient of the AI ​​communication quality analysis model based on the SHAP summary diagram, which can help determine the stability and reliability of the model. Therefore, the method and system for realizing 5G communication quality analysis based on intelligent AI proposed in the present invention can improve the reliability of 5G communication quality analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A flowchart of a method for analyzing 5G communication quality based on intelligent AI provided by an embodiment of the present invention;

[0059] Figure 2A functional module diagram of a 5G communication quality analysis system based on intelligent AI provided in one embodiment of the present invention;

[0060] Figure 3 A schematic diagram of the structure of an electronic device for implementing a 5G communication quality analysis system based on intelligent AI provided by an embodiment of the present invention;

[0061] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0062] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0063] The embodiment of the present application provides a method for analyzing 5G communication quality based on intelligent AI. The execution subject of the method for analyzing 5G communication quality based on intelligent AI includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for analyzing 5G communication quality based on intelligent AI can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0064] Reference Figure 1 As shown, it is a flow chart of a method for analyzing 5G communication quality based on intelligent AI provided by an embodiment of the present invention. In this embodiment, the method for analyzing 5G communication quality based on intelligent AI includes:

[0065] S1. Construct a multi-source data acquisition channel for a 5G communication system, collect multi-source communication data of the 5G communication system based on the multi-source data acquisition channel, and fuse the multi-source communication data to obtain fused communication data.

[0066] The embodiment of the present invention can collect multi-source data by constructing a multi-source data collection channel of a 5G communication system, thereby improving the reliability of the data. The multi-source data collection channel refers to a channel for collecting data from multiple sources and different types.

[0067] As an embodiment of the present invention, the construction of a multi-source data acquisition channel for a 5G communication system includes: determining a data acquisition requirement of the 5G communication system; based on the data acquisition requirement, determining a data acquisition source of the 5G communication system; configuring an acquisition interface of the data acquisition source; and based on the acquisition interface, constructing a multi-source data acquisition channel for the 5G communication system.

[0068] Among them, the data collection requirements refer to the requirements for collecting data, such as data type, data frequency, data accuracy and other requirements; the data collection source refers to the source of collected data, including: base stations, user equipment, core network equipment, transmission equipment and other sources; the collection interface refers to the interface for implementing data collection, such as SNMP, NetFlow, API and other interfaces.

[0069] In the embodiment of the present invention, the multi-source communication data refers to a multi-source data set collected through a multi-source data collection channel, wherein the multi-source communication data refers to a data set from multiple sources and of different types.

[0070] Optionally, the embodiment of the present invention can achieve data fusion by fusing the multi-source communication data to obtain fused communication data, thereby improving data reliability. The fused communication data refers to a data set after multi-modal fusion of the fused communication data.

[0071] As an embodiment of the present invention, the fusing of the multi-source communication data to obtain fused communication data includes: preprocessing the multi-source communication data to obtain preprocessed communication data; extracting data features of the preprocessed communication data; based on the data features, outputting data decision values ​​of the preprocessed communication data using a preset modal data model; and performing decision fusion on the data decision values ​​to obtain the fused communication data.

[0072] Among them, the pre-processed communication data refers to the data set after the multi-source communication data is subjected to data cleaning, data supplementation and other operations, the data features refer to the characteristic attributes of the pre-processed communication data, such as statistical features, trend analysis, pattern recognition and other features, the modal data model refers to the model for processing different modal data, and the data decision value refers to the output obtained after the data of each modality is processed by its corresponding model. This output is usually a decision value, which can be a classification label, probability value or any other form of decision result.

[0073] Further, in an optional embodiment of the present invention, the step of performing decision fusion on the data decision values ​​to obtain the fused communication data includes: determining a fusion function of the data decision values; and based on the fusion function, performing decision fusion on the data decision values ​​using the following formula to obtain the fused communication data:

[0074]

[0075] in, Indicates fused communication data, Indicates that the data decision value corresponds to the preprocessed communication data The modal data model of the model type data, Indicates that the data decision value corresponds to the preprocessed communication data Model type data, Preprocessing communication data The data decision value of each model type data.

[0076] S2. Calculate a data anomaly coefficient of the fused communication data, and remove abnormal data of the fused communication data based on the data anomaly coefficient to obtain target communication data.

[0077] The embodiment of the present invention can screen out abnormal data by calculating the data anomaly coefficient of the fused communication data, thereby improving the accuracy of the data and increasing the reliability of subsequent data analysis. The data anomaly coefficient refers to the degree of abnormality of the fused communication data.

[0078] As an embodiment of the present invention, the calculation of the data anomaly coefficient of the fused communication data includes: marking the fused communication data corresponding to a given data point; determining the data point neighborhood of the given data point; based on the data point neighborhood, calculating the local density of the given data point; based on the local density, calculating the data anomaly coefficient of the given data point.

[0079] The given data point refers to a data point selected in the fused communication data, the data point neighborhood refers to an area adjacent to the given data point, and the local density refers to the number of neighbors around the given data point.

[0080] Further, in an optional embodiment of the present invention, the calculating the local density of the given data point based on the neighborhood of the data point includes: calculating the neighborhood radius of the neighborhood of the data point; calculating the reachable distance of the given data point; and calculating the local density of the given data point based on the neighborhood radius and the reachable distance using the following formula:

[0081]

[0082] in, Represents a given data point The local density of Represents a given data point and adjacent data points The distance between Represents a given data point The indices of the adjacent data points, represents the number of given data points, Represents the neighborhood radius of a given data point.

[0083] The neighborhood radius refers to the radius used to define the neighborhood size of each data point, and the reachable distance refers to the shortest distance from one data point to another data point.

[0084] Further, in an optional embodiment of the present invention, the calculating the data anomaly coefficient of the given data point based on the local density includes: calculating the reachable density of the given data point based on the local density; and calculating the data anomaly coefficient of the given data point based on the reachable density using the following formula:

[0085]

[0086] in, Represents a given data point The data anomaly coefficient, Represents a given data point The number of data points directly connected to the corresponding data point in its neighborhood, Represents a given data point The indices of the adjacent data points, Represents a given data point Adjacent data points The accessible density, Represents a given data point The attainable density.

[0087] The reachable density refers to the average local density of neighbors around a given data point.

[0088] In the embodiment of the present invention, the target communication data refers to a data set after removing abnormal data from the fused communication data. Specifically, the abnormal data refers to data whose data abnormality coefficient reaches a preset abnormality threshold.

[0089] S3. Based on the target communication data, identify the communication characteristics of the 5G communication system, mark the target communication data, obtain marked communication data, and establish an AI communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics.

[0090] In an embodiment of the present invention, the communication characteristics refer to characteristic attributes of communication in a 5G communication system, such as high speed, low latency, high connection density, large network capacity, and the like.

[0091] Optionally, the embodiment of the present invention obtains labeled communication data by labeling the target communication data, which can be used as training data for a later model. The labeled communication data refers to a data set after the target communication data is specifically labeled. In detail, the target communication data can be labeled by defining indicators of communication quality, such as signal strength, bit error rate, delay, data transmission rate, etc., and according to these indicators, the communication data is labeled to mark the quality level of each data point (such as good, medium, poor).

[0092] Furthermore, the embodiment of the present invention establishes an AI communication quality analysis model of the 5G communication system based on the labeled communication data and the communication characteristics, which can quickly evaluate the communication quality. Among them, the AI ​​communication quality analysis model refers to a model that can analyze the 5G communication quality. In detail, the AI ​​communication quality analysis model can be implemented by selecting a neural network as the model architecture, then training the AI ​​model with labeled communication data and using an optimization algorithm and a loss function to minimize the difference between the model prediction and the actual label.

[0093] S4. Construct a SHAP interpretation environment for the AI ​​communication quality analysis model, and calculate a SHAP value of a corresponding predicted value of the AI ​​communication quality analysis model based on the SHAP interpretation environment.

[0094] The SHAP interpretation environment for constructing the AI ​​communication quality analysis model in the embodiment of the present invention can be used as a tool for calculating the reliability of the behavior of the AI ​​communication quality analysis model. The SHAP interpretation environment refers to an environment that can interpret the behavior of the AI ​​communication quality analysis model.

[0095] As an embodiment of the present invention, the construction of the SHAP interpretation environment of the AI ​​communication quality analysis model includes: constructing a SHAP library of the AI ​​communication quality analysis model; loading the AI ​​communication quality analysis model into the SHAP library to obtain a model SHAP library; selecting a model interpreter of the model SHAP library; and based on the model interpreter, constructing the SHAP interpretation environment of the AI ​​communication quality analysis model.

[0096] Among them, the SHAP library refers to a library used to explain the predictions of machine learning models, the model SHAP library refers to the library to be analyzed obtained by loading the AI ​​communication quality analysis model into the SHAP library, and the model interpreter refers to a tool or method for explaining the predictions of machine learning models; the interpreter provides a way to understand how the model makes specific predictions and the contribution of each feature to the prediction.

[0097] Optionally, the SHAP value of the corresponding predicted value of the AI ​​communication quality analysis model calculated based on the SHAP interpretation environment in an embodiment of the present invention can be used as a data basis for later model behavior analysis. The SHAP value refers to the degree of influence of each feature on the model prediction result. In detail, the calculation of the SHAP value of the corresponding predicted value of the AI ​​communication quality analysis model can be achieved by creating an interpreter instance through the SHAP interpretation environment.

[0098] S5. Based on the SHAP value, construct a SHAP summary graph of the AI ​​communication quality analysis model; based on the SHAP summary graph, calculate the behavioral reliability coefficient of the AI ​​communication quality analysis model; when the behavioral reliability coefficient meets the preset requirements, construct a 5G communication quality analysis report of the 5G communication system.

[0099] In the embodiment of the present invention, the SHAP summary graph refers to a graph formed by plotting all values ​​in the SHAP value array together. Specifically, the SHAP summary graph can be constructed by the shap.summary_plot function in the SHAP library.

[0100] Optionally, in an embodiment of the present invention, based on the SHAP summary graph, calculating the behavioral reliability coefficient of the AI ​​communication quality analysis model can help determine the stability and reliability of the model. The behavioral reliability coefficient refers to the reliability of the prediction results of the AI ​​communication quality analysis model.

[0101] Optionally, as an embodiment of the present invention, calculating the behavioral reliability coefficient of the AI ​​communication quality analysis model based on the SHAP summary graph includes: constructing a eigenvalue combination corresponding to the input features of the AI ​​communication quality analysis model; calculating the stability of the eigenvalue combination based on the SHAP summary graph; and evaluating the behavioral reliability coefficient of the AI ​​communication quality analysis model based on the stability.

[0102] The feature value combination refers to dividing the value of each feature into different combinations. For example, for a binary feature, its value can be divided into two combinations of 0 and 1; for a continuous feature, its value can be grouped according to a certain interval, and the stability refers to the stability of the SHAP value under different feature value combinations. In detail, the behavior reliability coefficient is obtained by weighted calculation of the stability.

[0103] Finally, in the embodiment of the present invention, when the behavior reliability coefficient meets the preset requirements, a 5G communication quality analysis report of the 5G communication system is constructed to realize accurate analysis of the quality of the communication system.

[0104] The embodiment of the present invention can collect multi-source data by constructing a multi-source data collection channel of a 5G communication system, thereby improving the reliability of the data; the embodiment of the present invention can achieve data fusion by fusing the multi-source communication data to obtain fused communication data, thereby improving the reliability of the data; the embodiment of the present invention can screen out abnormal data by calculating the data anomaly coefficient of the fused communication data, thereby improving the accuracy of the data and increasing the reliability of the subsequent data analysis; further, the embodiment of the present invention can quickly evaluate the communication quality by establishing the AI ​​communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics, and further, the SHAP interpretation environment of the AI ​​communication quality analysis model constructed by the embodiment of the present invention can be used as a tool for calculating the behavioral reliability of the AI ​​communication quality analysis model, and the SHAP value of the corresponding predicted value of the AI ​​communication quality analysis model calculated by the embodiment of the present invention based on the SHAP interpretation environment can be used as the data basis for the later model behavior analysis, and finally, the embodiment of the present invention calculates the behavioral reliability coefficient of the AI ​​communication quality analysis model based on the SHAP summary diagram, which can help determine the stability and reliability of the model. Therefore, the method for realizing 5G communication quality analysis based on intelligent AI proposed in the present invention can improve the reliability of 5G communication quality analysis.

[0105] like Figure 2 As shown, it is a functional module diagram of a 5G communication quality analysis system based on intelligent AI provided by one embodiment of the present invention.

[0106] The 5G communication quality analysis system 200 based on intelligent AI of the present invention can be installed in an electronic device. According to the functions implemented, the 5G communication quality analysis system 200 based on intelligent AI may include a communication data fusion module 201, a data anomaly deletion module 202, an AI model building module 203, a SHAP value calculation module 204 and a communication quality analysis module 205. The module of the present invention may also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0107] In this embodiment, the functions of each module / unit are as follows:

[0108] The communication data fusion module 201 is used to build a multi-source data acquisition channel of the 5G communication system, collect multi-source communication data of the 5G communication system based on the multi-source data acquisition channel, and fuse the multi-source communication data to obtain fused communication data;

[0109] The data anomaly removal module 202 is used to calculate the data anomaly coefficient of the fused communication data, and remove the abnormal data of the fused communication data based on the data anomaly coefficient to obtain the target communication data;

[0110] The AI ​​model building module 203 is used to identify the communication characteristics of the 5G communication system based on the target communication data, mark the target communication data, obtain marked communication data, and establish an AI communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics;

[0111] The SHAP value calculation module 204 is used to construct a SHAP interpretation environment of the AI ​​communication quality analysis model, and calculate the SHAP value of the corresponding prediction value of the AI ​​communication quality analysis model based on the SHAP interpretation environment;

[0112] The communication quality analysis module 205 is used to construct a SHAP summary diagram of the AI ​​communication quality analysis model based on the SHAP value, calculate the behavioral reliability coefficient of the AI ​​communication quality analysis model based on the SHAP summary diagram, and construct a 5G communication quality analysis report of the 5G communication system when the behavioral reliability coefficient meets the preset requirements.

[0113] In detail, the modules described in the system 200 for implementing 5G communication quality analysis based on intelligent AI in the embodiment of the present invention adopt the same technical means as the method for implementing 5G communication quality analysis based on intelligent AI described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0114] An embodiment of the present invention provides an electronic device for implementing a 5G communication quality analysis method based on intelligent AI.

[0115] See also Figure 3 As shown, the electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as a 5G communication quality analysis method program based on intelligent AI.

[0116] Among them, the processor may be composed of an integrated circuit in some embodiments, for example, it may be composed of a single packaged integrated circuit, or it may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, and a combination of various control chips, etc. The processor is the control core (Control Unit) of the electronic device, which uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes the programs or modules stored in the memory (for example, executing a 5G communication quality analysis program based on intelligent AI, etc.), and calls the data stored in the memory to execute various functions of the electronic device and process data.

[0117] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the memory may also include both an internal storage unit and an external storage device of the electronic device. The memory can be used not only to store application software and various types of data installed in the electronic device, such as the code for implementing a 5G communication quality analysis program based on intelligent AI, but also to temporarily store data that has been output or is to be output.

[0118] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0119] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0120] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0121] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0122] The intelligent AI-based 5G communication quality analysis program stored in the memory of the electronic device is a combination of multiple instructions. When running in the processor, it can achieve:

[0123] Constructing a multi-source data acquisition channel for a 5G communication system, collecting multi-source communication data of the 5G communication system based on the multi-source data acquisition channel, and fusing the multi-source communication data to obtain fused communication data;

[0124] Calculating a data anomaly coefficient of the fused communication data, and removing abnormal data of the fused communication data based on the data anomaly coefficient to obtain target communication data;

[0125] Based on the target communication data, identifying the communication characteristics of the 5G communication system, marking the target communication data, obtaining marked communication data, and establishing an AI communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics;

[0126] Constructing a SHAP interpretation environment for the AI ​​communication quality analysis model, and calculating a SHAP value of a corresponding predicted value of the AI ​​communication quality analysis model based on the SHAP interpretation environment;

[0127] Based on the SHAP value, a SHAP summary graph of the AI ​​communication quality analysis model is constructed; based on the SHAP summary graph, a behavioral reliability coefficient of the AI ​​communication quality analysis model is calculated; when the behavioral reliability coefficient meets preset requirements, a 5G communication quality analysis report of the 5G communication system is constructed.

[0128] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0129] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0130] The present invention further provides 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 of an electronic device, the computer program can implement:

[0131] Constructing a multi-source data acquisition channel for a 5G communication system, collecting multi-source communication data of the 5G communication system based on the multi-source data acquisition channel, and fusing the multi-source communication data to obtain fused communication data;

[0132] Calculating a data anomaly coefficient of the fused communication data, and removing abnormal data of the fused communication data based on the data anomaly coefficient to obtain target communication data;

[0133] Based on the target communication data, identifying the communication characteristics of the 5G communication system, marking the target communication data, obtaining marked communication data, and establishing an AI communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics;

[0134] Constructing a SHAP interpretation environment for the AI ​​communication quality analysis model, and calculating a SHAP value of a corresponding predicted value of the AI ​​communication quality analysis model based on the SHAP interpretation environment;

[0135] Based on the SHAP value, a SHAP summary graph of the AI ​​communication quality analysis model is constructed; based on the SHAP summary graph, a behavioral reliability coefficient of the AI ​​communication quality analysis model is calculated; when the behavioral reliability coefficient meets preset requirements, a 5G communication quality analysis report of the 5G communication system is constructed.

[0136] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0137] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0139] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0140] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0141] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for analyzing 5G communication quality based on intelligent AI, characterized in that: The method comprises: Construct a multi-source data acquisition channel for a 5G communication system, collect multi-source communication data of the 5G communication system based on the multi-source data acquisition channel, fuse the multi-source communication data to obtain fused communication data, wherein the fusing the multi-source communication data to obtain fused communication data includes: preprocessing the multi-source communication data to obtain preprocessed communication data, extracting data features of the preprocessed communication data, based on the data features, outputting data decision values ​​of the preprocessed communication data using a preset modal data model, performing decision fusion on the data decision values ​​to obtain the fused communication data, wherein the performing decision fusion on the data decision values ​​to obtain the fused communication data includes: determining a fusion function of the data decision value, and based on the fusion function, performing decision fusion on the data decision value using the following formula to obtain fused communication data: in, Indicates fused communication data, Indicates that the data decision value corresponds to the preprocessed communication data The modal data model of the model type data, Indicates that the data decision value corresponds to the preprocessed communication data Model type data, Indicates the preprocessing communication data The data decision value of each model type data; Calculate the data anomaly coefficient of the fused communication data, and based on the data anomaly coefficient, remove the abnormal data of the fused communication data to obtain the target communication data, wherein the calculation of the data anomaly coefficient of the fused communication data includes: marking the fused communication data corresponding to a given data point, determining the data point neighborhood of the given data point, calculating the local density of the given data point based on the data point neighborhood, and calculating the data anomaly coefficient of the given data point based on the local density, wherein the calculation of the local density of the given data point based on the data point neighborhood includes: calculating the neighborhood radius of the data point neighborhood, calculating the reachable distance of the given data point, and calculating the local density of the given data point using the following formula based on the neighborhood radius and the reachable distance: in, Represents a given data point The local density of Represents a given data point and adjacent data points The distance between Represents a given data point The indices of the adjacent data points, represents the number of given data points, represents a neighborhood radius of a given data point, wherein the calculating the local density of the given data point based on the neighborhood of the data point comprises: calculating the neighborhood radius of the neighborhood of the data point, calculating the reachable distance of the given data point, and calculating the local density of the given data point based on the neighborhood radius and the reachable distance using the following formula: in, Represents a given data point The local density of Represents a given data point and adjacent data points The distance between Represents a given data point The indices of the adjacent data points, represents the number of given data points, Represents the neighborhood radius of a given data point; Based on the target communication data, identifying the communication characteristics of the 5G communication system, marking the target communication data, obtaining marked communication data, and establishing an AI communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics; Constructing a SHAP interpretation environment for the AI ​​communication quality analysis model, and calculating a SHAP value of a corresponding predicted value of the AI ​​communication quality analysis model based on the SHAP interpretation environment; Based on the SHAP value, a SHAP summary graph of the AI ​​communication quality analysis model is constructed; based on the SHAP summary graph, a behavioral reliability coefficient of the AI ​​communication quality analysis model is calculated; when the behavioral reliability coefficient meets preset requirements, a 5G communication quality analysis report of the 5G communication system is constructed, wherein the calculation of the behavioral reliability coefficient of the AI ​​communication quality analysis model based on the SHAP summary graph includes: constructing a characteristic value combination of the AI ​​communication quality analysis model corresponding to the input features, calculating the stability of the characteristic value combination based on the SHAP summary graph, and evaluating the behavioral reliability coefficient of the AI ​​communication quality analysis model based on the stability.

2. The method for analyzing 5G communication quality based on intelligent AI according to claim 1, characterized in that: The multi-source data acquisition channel for building a 5G communication system includes: Determining data collection requirements for the 5G communication system; Based on the data collection requirement, determining a data collection source of the 5G communication system; Configuring the acquisition interface of the data acquisition source; Based on the acquisition interface, a multi-source data acquisition channel for the 5G communication system is constructed.

3. The method for analyzing 5G communication quality based on intelligent AI according to claim 1, characterized in that: The SHAP interpretation environment for constructing the AI ​​communication quality analysis model includes: Constructing a SHAP library of the AI ​​communication quality analysis model; Loading the AI ​​communication quality analysis model into the SHAP library to obtain a model SHAP library; Select a model interpreter from the model SHAP library; Based on the model interpreter, a SHAP interpretation environment of the AI ​​communication quality analysis model is constructed.

4. A 5G communication quality analysis system based on intelligent AI, characterized in that: Used to execute the method for analyzing 5G communication quality based on intelligent AI according to any one of claims 1 to 3, the system comprising: A communication data fusion module is used to build a multi-source data acquisition channel for a 5G communication system, collect multi-source communication data of the 5G communication system based on the multi-source data acquisition channel, and fuse the multi-source communication data to obtain fused communication data; A data anomaly removal module, used for calculating a data anomaly coefficient of the fused communication data, and removing the abnormal data of the fused communication data based on the data anomaly coefficient to obtain target communication data; An AI model building module is used to identify the communication characteristics of the 5G communication system based on the target communication data, mark the target communication data, obtain marked communication data, and establish an AI communication quality analysis model of the 5G communication system based on the marked communication data and the communication characteristics; A SHAP value calculation module, used to construct a SHAP interpretation environment of the AI ​​communication quality analysis model, and calculate a SHAP value of a corresponding predicted value of the AI ​​communication quality analysis model based on the SHAP interpretation environment; The communication quality analysis module is used to construct a SHAP summary diagram of the AI ​​communication quality analysis model based on the SHAP value, calculate the behavioral reliability coefficient of the AI ​​communication quality analysis model based on the SHAP summary diagram, and construct a 5G communication quality analysis report of the 5G communication system when the behavioral reliability coefficient meets the preset requirements.

Images