Behavioral Network AI Artificial Intelligence Core System

Abstract

We provide a behavioral network AI artificial intelligence core system that enables immediate investigation of the cause of failures and reduces failures with unknown causes. [Solution] The behavioral network AI core system includes a leading indicator unit, a synchronization indicator unit, and a lagging indicator unit. The leading indicator unit includes multiple servers, and collects past node data and real-time node data of network equipment and terminal users via the servers to build a database. The synchronization indicator unit is communicatively connected to the leading indicator unit and has a machine analysis AI model, which analyzes and optimizes data and operations required for the network operation and maintenance process to generate multiple analysis results. The lagging indicator unit is communicatively connected to the synchronization indicator unit and issues inspection notifications or dispatches inspections based on the analysis results. The generative AI core system and machine learning are used to evolve fault response after reinforcement learning.

Description

[Technical Field]

[0001] The present invention relates to a behavioral network AI core system, and more particularly to a behavioral network AI core system that can improve network efficiency and stability while building an effective equipment fault detection platform. [Background technology]

[0002] In recent years, mobile communication technology has developed rapidly, and telecommunications carriers have installed base stations and provided mobile communication networks to users, allowing them to communicate using their mobile phones anytime, anywhere. With the spread of smartphones, the transmission function of mobile phone multimedia networks has increased, allowing people to use their mobile phones for various functions such as browsing the Internet, shopping, paying bills, and watching movies. Therefore, the demands for Internet signal quality have also increased, and when people experience poor Internet signal quality or weak reception, they often call the customer service hotline of their telecommunications carrier to file a complaint.

[0003] Research has shown that the main reasons for outages include the belief that filing a complaint will bring positive results and social benefits, the belief that users will receive some kind of compensation for service defects, the feeling of social responsibility to file a complaint in order to avoid similar situations or punish the service provider, and an innate tendency to "complain." On the other hand, some consumers do not complain even when they encounter bad service because they do not want to waste their mental energy and time complaining, or because they do not believe that their actions will bring positive results to themselves or others, do not know the procedures or channels for reporting complaints, or believe that they should not be compensated because it was their own mistake.

[0004] Since mobile communication technology is closely related to the convenience of daily life, users' demands for mobile networks are also increasing, and how to provide high-quality wireless communication services has become a common and difficult challenge for communication operators. Therefore, in order to overcome the above-mentioned shortcomings, the creator of this invention has devoted great energy and spirit to research and development, and has constantly made breakthroughs and innovations in this field, so as to solve the previous shortcomings with novel technical means, and not only provide society with better products but also promote the development of the industry. Summary of the Invention

[0005] In view of this, the inventor has conducted long-term research and development and has developed a behavioral network AI artificial intelligence core system that inspects and repairs equipment through the relevant maintenance department, clarifies the direction of inspection and repair, reduces inspection and repair time, and thereby enables immediate investigation of the cause of failures and reduces failures with unknown causes.

[0006] To achieve the above objectives, the present invention provides a behavioral network AI core system, comprising a leading indicator unit, a synchronization indicator unit, a lagging indicator unit, and a user interface. The leading indicator unit includes multiple servers, which collect past node data of multiple terminal users and real-time node data of multiple terminal users from multiple network devices and multiple servers through the servers to build a database. The past node data includes multiple past node data analyses, multiple past base station trajectory data, multiple service item data, multiple usage data, multiple past DNS domain history data, and multiple past test speed data. The synchronization indicator unit is communicably connected to the leading indicator unit and includes multiple machine analysis AI models, each of which is used to analyze and optimize data and operations required for network operation and maintenance processes to generate multiple analysis results. The lagging indicator unit is communicably connected to the synchronization indicator unit and performs node classification, inspection notification, or dispatch inspection based on the analysis results. The user interface is communicatively connected to the lagging indicator unit and is used to display the analysis results, node classification, inspection notification, or dispatch inspection. It also compares the network usage of the terminal user every 10 to 15 minutes. If the usage is lower than a predetermined value, it performs intelligent analysis for the terminal user and generates corresponding optimization suggestions or operation instructions. The intelligent analysis analyzes the GTP-C signal module according to the 3GPP-TS 29.274 specification, then analyzes the GTP-U signal module according to the 3GPP-TS 29.281 specification, and further authorizes billing in the database system and obtains data field information through RADIUS (Remote Authentication Dial-In User Service) authentication.

[0007] In the behavioral network AI core system of the present invention, these servers cooperate with each other and include: a service process improvement server for collecting the past node data analysis of the terminal user and storing and managing the past node data analysis and the real-time node data related to faults; a location server for collecting a plurality of past base station trajectory data of the terminal user and storing and managing the past base station trajectory data and the real-time node data related to base station trajectories; a service server for collecting the service item data and the usage data of the terminal user and storing and managing the service item data, the usage data, and the real-time node data related to service items and usage; a domain server for collecting the past DNS domain history data of the terminal user and storing and managing the past DNS domain history data and the real-time node data related to DNS domain history data; and a network speed server for collecting the past test speed data of the terminal user and storing and managing the past test speed data and the real-time node data related to test speeds.

[0008] In the behavioral network AI core system of the present invention, the machine analysis AI model includes a process AI cognition-network big data module, which is communicatively connected to the database, obtains the past node data analysis in the database, performs calculations with the real-time node data via a RADIUS accounting model, analyzes one node data analysis result of a mode or association in the past trajectory data related to the real-time fault case data, and transmits the node data analysis result to the lagging indicator unit. Note that the "process AI cognition-network big data module" may also be referred to as a "process analysis module" in the specific embodiments and drawings of the present invention.

[0009] In the behavioral network AI core system of the present invention, the machine analysis AI model includes a location AI awareness-network big data model, which is communicatively connected to the database, obtains the past base station trajectory data in the database, performs calculations with the real-time node data via the RADIUS accounting model, analyzes whether there is a location analysis result for the same regional cluster, and transmits the location analysis result to the lagging indicator unit. Note that the "location AI awareness-network big data module" may also be referred to as the "location analysis module" in the specific embodiments and drawings of the present invention.

[0010] In the behavioral network AI core system of the present invention, the machine analysis AI model includes a service AI recognition-network big data module, which is communicatively connected to the database, obtains the service item data and the usage data in the database, performs calculations with the real-time node data via the RADIUS billing model, analyzes whether the terminal users use the same type of telecommunications service and whether there is one of the problems or failures related to a specific mobile phone model, and transmits the service analysis result to the lagging indicator unit. Note that the "service AI recognition-network big data module" may also be referred to as the "service analysis module" in the specific embodiments and drawings of the present invention.

[0011] In the behavioral network AI core system of the present invention, the machine analysis AI model includes a domain AI cognition-network big data module, which is communicatively connected to the database to obtain the terminal user's past DNS domain history data, calculates with the real-time node data via the RADIUS accounting model, analyzes whether a domain analysis result of the same network problem or performance abnormality appears when the terminal user uses the same application program or accesses the same domain, and transmits the domain analysis result to the lagging indicator unit. Note that the "domain AI cognition-network big data module" may also be referred to as the "domain analysis module" in the specific embodiments and drawings of the present invention.

[0012] In the behavioral network AI artificial intelligence core system of the present invention, the machine analysis AI model further includes a network speed AI recognition-network big data module, which is communicatively connected to the database, obtains the terminal user's past test speed data from the database, calculates with the implementation data via the RADIUS accounting model, analyzes a network speed analysis result of dependencies or similarities between different low-speed network connections, and transmits the network speed analysis result to the lagging indicator unit. Note that the "network speed AI recognition-network big data module" may also be referred to as the "network speed analysis module" in the specific embodiments and drawings of the present invention.

[0013] In the behavioral network AI core system of the present invention, the machine analysis AI model further includes an AI sensing and detection network node module, which is communicatively connected to the process analysis module, the location analysis module, the service analysis module, the domain analysis module, and the network speed analysis module, and receives the node data analysis results, the location analysis results, the service analysis results, the domain analysis results, and the network speed analysis results, and performs calculations via the RADIUS accounting model to predict a prediction result for low-speed or faulty equipment. Note that the "AI sensing and detection network node module" may also be referred to as the "node data analysis module" in specific embodiments and drawings of the present invention.

[0014] The behavioral network AI core system of the present invention further includes a self-learning module, which is communicatively connected to the synchronization indicator unit and automatically adjusts the parameters of the machine analysis AI model based on inspection history, thereby improving analysis accuracy and system efficiency.

[0015] The behavioral network AI artificial intelligence core system of the present invention further includes a fault prediction module, which is communicatively connected to the database and the synchronization indicator unit, and performs fault prediction based on the past node data and the real-time node data, analyzes past fault modes, network load and usage status through a machine learning algorithm, predicts possible network interruptions, performance degradation or other network faults, and transmits the prediction result to the lagging indicator unit to initiate maintenance preventive measures.

[0016] In order to clarify the objectives, advantages, and features of the present invention, the present invention will be described in more detail below in conjunction with the accompanying drawings and specific examples. Note that all of the accompanying drawings are very simplified and not drawn to scale, and are only used to conveniently and clearly assist in explaining the objectives of the embodiments of the present invention. Furthermore, the structures shown in the accompanying drawings are often parts of the actual structure. In particular, since the focus to be shown in each of the accompanying drawings is different, different proportions may be used. [Brief explanation of the drawings]

[0017] [Figure 1] FIG. 1 is a schematic diagram of a behavioral network AI core system according to a first embodiment of the present invention. [Figure 2] FIG. 2 is a schematic diagram of a leading indicator unit according to a first embodiment of the present invention. [Figure 3] FIG. 3 is a schematic diagram of a synchronization index unit according to a first embodiment of the present invention. [Figure 4] FIG. 4 is a schematic diagram illustrating the operation process of the lagging indicator unit according to the first embodiment of the present invention. [Figure 5] FIG. 5 is a schematic diagram of a behavioral network AI core system according to a second embodiment of the present invention. [Figure 6] FIG. 6 is a schematic diagram of a behavioral network AI core system according to a third embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] In order to allow those in the relevant technical fields to understand the objectives, technical features and advantages of the present invention and to enable the present invention to be implemented, the technical features and embodiments of the present invention will be specifically described herein in conjunction with the accompanying drawings, and preferred examples will be listed and described.

[0019] As used in this invention, the singular forms "a" and "the" include plural referents, the term "or" is generally used in the sense of including "and / or," and the term "connected" is to be interpreted broadly to mean fixed connection, detachable connection, or integral connection, either mechanical or electrical connection, direct connection, indirect connection via an intermediate medium, internal communication between two devices, or an interactive relationship between two devices. Those skilled in the art will understand what the above terms specifically mean in this invention depending on the context.

[0020] Referring to FIG. 1, it is a schematic diagram of a behavioral network AI core system according to a first embodiment of the present invention.

[0021] As shown in FIG. 1, the present invention provides a behavioral network AI artificial intelligence core system 1, which includes a leading indicator unit 10, a synchronous indicator unit 20, a lagging indicator unit 30, and a user interface 40.

[0022] Please refer to Fig. 2. Fig. 2 is a schematic diagram of a leading indicator unit according to a first embodiment of the present invention.

[0023] As shown in Figure 2, the leading indicator unit 10 includes multiple servers 11, which collect past node data of multiple network devices, multiple terminal users, and real-time node data of multiple terminal users to build a database 101. Among them, the past node data includes multiple past node data analyses, multiple past base station trajectory data, multiple service item data, multiple usage data, multiple past DNS domain history data, and multiple past test speed data.

[0024] These servers 11 include a service process improvement server 111, a location server 112, a service server 113, a domain server 114, and a network speed server 115. The service process improvement server 111 is configured to collect past node data analysis related to terminal users, including time, location, gate number, fault cause, etc., and the service process improvement server 111 stores and manages these past node data analysis and real-time node data related to faults.

[0025] The location server 112 is used to collect multiple past base station trajectory data of the terminal user, including time, gate number, base station address, or latitude and longitude, etc., and the location server 112 stores and manages these past base station trajectory data and real-time node data related to the base station trajectory.

[0026] The service server 113 is configured to collect the terminal user's service item data and usage data gate number, including card number, machine number, service category, etc., and the service server 113 stores and manages these service item data, usage data, and real-time node data related to the service items and usage.

[0027] The domain server 114 is configured to collect these past DNS domain history data for the terminal user, including past DNS domain history (e.g., Google.com), and the domain server 114 stores and manages these past DNS domain history data and real-time node data related to the DNS domain history data.

[0028] The network speed server 115 is configured to collect these past test speed data of terminal users, including past test speeds (e.g., Speed test App), and the network speed server 115 stores and manages the past test speed data and real-time node data related to the test speeds.

[0029] Please refer to Fig. 3. Fig. 3 is a schematic diagram of a synchronization index unit according to a first embodiment of the present invention.

[0030] As shown in FIG. 3, the synchronization indicator unit 20 is communicatively connected to the leading indicator unit 10 and includes a plurality of machine analysis AI models 21, each of which is used to analyze and optimize data and operations required in the network operation and maintenance process to generate a plurality of analysis results.

[0031] These machine analysis AI models 21 include a process analysis module 211, which is communicatively connected to the database 101, retrieves the past node data analysis from the database 101, performs calculations with the real-time node data, analyzes the node data analysis result for a mode or correlation in the past trajectory data related to the real-time fault case data, and transmits the node data analysis result to the lagging indicator unit 30. Based on past fault cases, the module analyzes and finds the mode or correlation in the past trajectory data related to these fault cases. Specifically, by comparing the client's fault history with past network usage history (e.g., base station location, domain visit history, etc.), potential problems and trends can be discovered, helping to predict and understand future issues. For example, if faults frequently occur in a specific location, analyzing the past trajectory data (e.g., Internet speed, base station status, etc.) for that location can identify whether the problem is related to the faulty network or device. This correlation analysis helps improve the efficiency and accuracy of network operations and enhance user experience.

[0032] Next, these machine analysis AI models 21 include a location analysis module 212, which is communicatively connected to the database 101, retrieves the historical base station trajectory data from the database 101, performs calculations with the real-time node data via the RADIUS accounting model, analyzes whether there is a location analysis result for a cluster in the same region, and transmits the location analysis result to the lagging indicator unit 30. When analyzing outages and other related data, it checks for outages concentrated in the same region. The purpose of this location analysis module 212 is to identify whether users in a particular region frequently raise similar questions or outages, forming a cluster phenomenon. For example, if multiple users in a city report similar network issues, such as slow network speeds or poor signal, these outages may form a concentrated area on a map called a "cluster." This information can help service providers identify and resolve network issues in specific regions, thereby improving service quality.

[0033] Further, the machine analysis AI model 21 includes a service analysis module 213, which is communicatively connected to the database 101 to retrieve the service item data and usage data from the database 101, perform calculations with the real-time node data via the RADIUS billing model, analyze whether the same type of telecommunications service is used among the terminal users, and whether there is a problem or fault related to a specific mobile phone model, and transmit the service analysis results to the lagging indicator unit 30. The service analysis module 213 analyzes the fault data or problem reports to check whether there are multiple fault or problem reports from users using the same type of service, such as a monthly rental service for a fixed monthly fee, a prepaid service for a pre-charged communication service, a value-added service for music or video subscriptions, or a roaming service for a communication service used in different regions or countries. This helps identify whether there are common problems or defects in a certain type of service. The service analysis module 213 also checks whether there are multiple fault or problem reports from users using the same mobile phone model. For example, if many users use the same model of mobile phone and report similar problems, this may indicate a specific problem with that mobile phone model. The results of this service analysis will help identify whether the cause of the problem is related to a specific service type or mobile phone model, and will help resolve the problem, improve service quality, and fix product defects.

[0034] Furthermore, the machine analysis AI model 21 includes a domain analysis module 214, which is communicatively connected to the database 101 to acquire historical DNS domain data of the terminal users and perform calculations with the real-time node data via the RADIUS accounting model to analyze whether the same network problem or performance abnormality occurs when the terminal users use the same application program or access the same domain, and transmits the domain analysis result to the lagging indicator unit. The domain analysis module 214 checks whether the same network problem or performance abnormality occurs when multiple users use the same application or access the same domain (such as a website or server). Specifically, the domain analysis module 214 analyzes whether multiple users experience network connection problems, slowdowns, or service interruptions while using a specific app (e.g., social media, games, or video streaming applications). Next, the domain analysis module 214 checks whether multiple users experience similar network problems when accessing a specific domain (such as a website server or a cloud service provider domain). The results of this domain analysis can help you determine whether a network problem is related to a specific application or domain, and then troubleshoot network problems related to that specific application or domain.

[0035] The machine analysis AI model 21 further includes a network speed analysis module 215, which is communicatively connected to the database 101 to obtain the terminal user's past test speed data from the database 101, and performs calculations with the implementation and operation data via the RADIUS accounting model to analyze a network speed analysis result for dependencies or similarities between different slow network connections, and transmits the network speed analysis result to the lagging indicator unit 30. The network speed analysis module 215 analyzes whether any dependencies or correlations exist between "similar slow network speeds." Specifically, it analyzes the data on slow network speeds to determine whether a slow network speed causes other nearby network speeds to slow down, or whether there is any mutual influence or correlation between them, and whether there is any correlation or interdependence between the slow network speeds.

[0036] The machine analysis AI model 21 further includes a node data analysis module 216, which is communicatively connected to the process analysis module 211, the location analysis module 212, the service analysis module 213, the domain analysis module 214, and the network speed analysis module 215. The node data analysis module 216 receives the node data analysis results, the location analysis results, the service analysis results, the domain analysis results, and the network speed analysis results, and calculates them through the RADIUS accounting model to predict a low-speed, fault-free device. The machine analysis AI model 21 also compares the behavioral network usage of the terminal user every 10 to 15 minutes. If the usage is lower than a predetermined value, intelligent analysis is performed on the terminal user to generate corresponding optimization suggestions or operation instructions.

[0037] As shown in FIG. 4, FIG. 4 is a schematic diagram illustrating the working process of the lagging indicator unit of the first embodiment of the present invention.

[0038] As shown in FIG. 4, the lagging indicator unit 30 is communicatively connected to the synchronization indicator unit 20 and performs node classification, inspection notification, or dispatch inspection based on the analysis results. The user interface 40 is communicatively connected to the lagging indicator unit 30 and is used to display the analysis results, node classification, inspection notification, or dispatch inspection. The node classification classifies different repair items according to obstacles, such as base station inspection, equipment inspection, or system inspection. The inspection notification is then divided into the following two cases: If an inspection notification is not required, a dispatch and inspection are performed directly to the base station, equipment, or system. If communication with the customer is required, the information is transferred to a service process improvement system, and after communication with the customer, dispatch and inspection are performed.

[0039] Referring to FIG. 5, FIG. 5 is a schematic diagram of a behavioral network AI artificial intelligence core system according to a second embodiment of the present invention.

[0040] As shown in FIG. 5, the second embodiment of the present invention has almost the same architecture as the first embodiment, but differs in that the second embodiment includes a self-learning module 50 communicatively connected to the synchronization index unit 20, and automatically adjusts the parameters of these machine analysis AI models 21 based on the inspection history to improve analysis accuracy and system efficiency.

[0041] Referring to FIG. 6, FIG. 6 is a schematic diagram of a behavioral network AI core system of Example 3 of the present invention.

[0042] As shown in FIG. 6 , the third embodiment of the present invention has substantially the same structure as the first embodiment, but differs in that the third embodiment further includes a fault prediction module 60 communicatively connected to the database 101 and the synchronization indicator unit 20, for performing fault prediction based on historical node data and real-time node data, analyzing historical fault modes, network load and usage status through machine learning algorithms, predicting possible network interruptions, performance degradation or other network faults, and sending the prediction result to the delay indicator module 20 to initiate preventive maintenance measures.

[0043] The behavioral network AI artificial intelligence core system of the present invention applies an AI adaptive network maintenance optimization model to effectively predict equipment failures to ensure user needs are met as much as possible. As described above, the content of the present invention has been illustrated by the above-mentioned embodiments, but the present invention is not limited to these embodiments. Those skilled in the art may further modify and alter the present invention without departing from the spirit and scope of the present invention. For example, the technical contents exemplified in the above-mentioned embodiments may be combined or modified to form new embodiments, and these embodiments are naturally considered to be part of the present invention. Therefore, the scope of protection sought by the present invention also includes the scope of the patent applications described below and their definitions. [Explanation of symbols]

[0044] 1. Behavioral Network AI Artificial Intelligence Core System 10 Leading Indicator Unit 101 Database 11 Server 111 Service Process Improvement Server 112 Location Server 113 Service Server 114 Domain Server 115 Network Speed Server 20 Synchronous Index Unit 21 Machine Analysis AI Model 211 Process Analysis Module 212 Location Analysis Module 213 Service Analysis Module 214 Domain Analysis Module 215 Network Speed Analysis Module 216-node data analysis module 30 lagging indicator units 40 User Interface 50 Self-Study Modules 60 Failure Prediction Module

Claims

1. A leading indicator unit includes a plurality of servers, and collects past node data of a plurality of terminal users and real-time node data of a plurality of terminal users through the servers to build a database; a synchronization indicator unit communicably connected to the leading indicator unit, the synchronization indicator unit having a plurality of machine analysis AI models, each machine analysis AI model being used to analyze and optimize data and operations required for a network operation and maintenance process, so as to generate a plurality of analysis results; a lagging indicator unit communicably connected to the synchronization indicator unit, for performing node classification, inspection notification, or dispatch inspection based on the analysis result; A behavioral network AI artificial intelligence core system comprising: a user interface communicatively connected to the lagging indicator unit and used to display the analysis results, node classification, inspection notification, or dispatch inspection; Compare the network usage of the terminal user every 10 to 15 minutes, and if the usage is lower than a predetermined value, provide intelligent analysis to the terminal user and give corresponding optimization suggestions or operation instructions; The intelligent analysis analyzes the GTP-C signal module according to the 3GPP-TS 29.274 specification, then analyzes the GTP-U signal module according to the 3GPP-TS 29.281 specification, and further authorizes the accounting of the database system through RADIUS authentication to obtain the data field information; The behavioral network AI artificial intelligence core system, wherein the past node data includes multiple past node data analyses, multiple past base station trajectory data, multiple service item data, multiple usage data, multiple past DNS domain history data, and multiple past test speed data.

2. The server a service process improvement server for collecting the past node data analysis of the terminal user, and storing and managing the past node data analysis and the real-time node data related to a fault; a location server for collecting a plurality of past base station trajectory data of the terminal user, and storing and managing the past base station trajectory data and the real-time node data related to the base station trajectory; a service server for collecting the service item data and the usage data of the terminal user, and storing and managing the service item data, the usage data, and the real-time node data related to the service items and usage; a domain server for collecting the past DNS domain history data of the terminal user, and storing and managing the past DNS domain history data and the real-time node data related to the DNS domain history data; The behavioral network AI artificial intelligence core system of claim 1, further comprising: a network speed server for collecting the past test speed data of the terminal user, and storing and managing the past test speed data and the real-time node data related to the test speed.

3. The behavioral network AI artificial intelligence core system of claim 1, characterized in that the machine analysis AI model includes a process analysis module, which is communicatively connected to the database, obtains the past node data analysis in the database, performs calculations with the real-time node data through a RADIUS billing model, analyzes one node data analysis result of a mode or association in the past trajectory data related to the real-time fault case data, and transmits the node data analysis result to the lagging indicator unit.

4. The behavioral network AI artificial intelligence core system of claim 3, characterized in that the machine analysis AI model includes a location analysis model, which is communicatively connected to the database, obtains the past base station trajectory data in the database, performs calculations with the real-time node data via the RADIUS billing model, analyzes whether there is one location analysis result of the same regional cluster, and transmits the location analysis result to the lagging indicator unit.

5. The behavioral network AI artificial intelligence core system of claim 3, characterized in that the machine analysis AI model includes a service analysis module, which is communicatively connected to the database, obtains the service item data and the dosage data in the database, performs calculations with the real-time node data via the RADIUS billing model, analyzes whether the terminal users use the same type of telecommunications service and whether there is one of the problems or failures related to a specific mobile phone model, and transmits the service analysis result to the lagging indicator unit.

6. The behavioral network AI artificial intelligence core system of claim 3, characterized in that the machine analysis AI model includes a domain analysis module, which is communicatively connected to the database, obtains the terminal user's past DNS domain history data, performs calculations with the real-time node data through the RADIUS billing model, analyzes whether one domain analysis result of the same network problem or performance abnormality appears when the terminal user uses the same application program or accesses the same domain, and transmits the domain analysis result to the lagging indicator unit.

7. The behavioral network AI artificial intelligence core system of claim 3, characterized in that the machine analysis AI model further includes a network speed analysis module, which is communicatively connected to the database, obtains the terminal user's past test speed data in the database, calculates with the implementation and operation data via the RADIUS billing model, analyzes one network speed analysis result of dependencies or similarities between different low-speed network connections, and transmits the network speed analysis result to the lagging indicator unit.

8. The behavioral network AI artificial intelligence core system of claim 1, characterized in that the machine analysis AI model further includes a node data analysis module, which is communicatively connected to the process analysis module, the location analysis model, the service analysis module, the domain analysis module and the network speed analysis module, and receives and calculates the node data analysis results, the location analysis results, the service analysis results, the domain analysis results and the network speed analysis results, and predicts one of the prediction results of slow or faulty equipment.

9. The behavioral network AI artificial intelligence core system of claim 2, further comprising a self-learning module, which is communicatively connected to the synchronization indicator unit and automatically adjusts parameters of the machine analysis AI model based on inspection history to improve analysis accuracy and system efficiency.

10. 2. The behavioral network AI artificial intelligence core system of claim 1, further comprising a fault prediction module, the fault prediction module being communicatively connected to the database and the synchronization indicator unit, for making fault predictions based on the past node data and the real-time node data, analyzing past failure modes, network loads and usage conditions through machine learning algorithms, predicting possible network interruptions, performance degradation or other network faults, and transmitting the prediction results to the lagging indicator unit to initiate maintenance preventive measures.

Images