Mobile communication network hidden fault positioning method and device, and electronic equipment

Abstract

The invention discloses a method and a device for positioning hidden faults of a mobile communication network, and electronic equipment. The method comprises the following steps: firstly, acquiring component element data of all network nodes, wherein the component elements can be basic elements or signaling elements obtained by decomposing a target model; the target model is a business model following a consistency principle. Next, composing element data of the network nodes is synthesized to obtain a target model value of each network node; and then, according to the difference of the target model values among the network nodes at the same time and at the same level, judging whether a network hidden fault exists or not. Specifically, if the difference between the target model value of a certain network node and the target model values of other network nodes at the same time and at the same level exceeds a preset threshold value, it is judged that the network node has a network hidden fault. Through the method, the hidden fault in the mobile communication network can be quickly positioned, so that the stability and the reliability of the network are effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method, an apparatus, and an electronic device for locating hidden faults in a mobile communication network. Background Art

[0002] The mobile communication network of an operator is large in scale and complex in structure. A multi-level and multi-node network architecture is usually adopted to ensure the stability and reliability of the network. Such an architecture generally includes multiple levels such as a core network, a transmission network, and an access network, and each level contains multiple network nodes. These nodes are interconnected through various protocols and interfaces to form a complex network system. When using user behavior analysis technology, by deeply analyzing the data related to user services, the usage habits and behavior patterns of users can be understood, so as to provide better services.

[0003] However, faults inevitably occur in the mobile communication network. The current technology mainly detects network faults by monitoring the alarms, performance indicators, and logs of network devices. For example, by monitoring indicators such as the alarm information, CPU utilization rate, memory usage rate, and network traffic of network devices, it can be judged whether there is a fault in the device. In addition, analyzing the alarms, logs, and user signaling of network devices can also help to find abnormal behaviors and fault information.

[0004] Nevertheless, there are still some problems and limitations in the existing technology for fault discovery. First of all, these technologies mainly rely on the monitoring and analysis of the alarm information, performance indicators, and logs of network devices. This method can usually only detect obvious faults. For some hidden faults, for example, the differences between the service model data of other network nodes and the data of other nodes caused by the hidden problems of a certain node device, the existing technology is difficult to effectively identify. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to propose a method, an apparatus, and an electronic device for locating hidden faults in a mobile communication network in view of the above-mentioned deficiencies of the existing technology. This method can quickly and accurately identify the hidden faults in the mobile communication network, thereby ensuring the stability and reliability of the network.

[0006] In a first aspect, the present invention provides a method for locating hidden faults in a mobile communication network, and the method includes the following steps:

[0007] Step S1: Obtain the composition element data of all network nodes;

[0008] Wherein, the composition element data is obtained by decomposing a target model; the target model is a service model that conforms to the consistency principle and is pre-constructed according to the operator network topology and the service types carried by network nodes at each level.

[0009] Step S2: Synthesize the component element data of the network node to obtain the target model value of the network node;

[0010] Step S3: Determine whether there is a network hidden fault according to the difference between the target model values of network nodes at the same time and at the same level;

[0011] Among them, if the difference between the target model value of a certain network node and the target model values of other network nodes at the same time and at the same level exceeds the preset threshold, it is determined that there is a network hidden fault in this network node, thereby completing the location of the network hidden fault.

[0012] Further, the component element data in the step S1 specifically includes: basic element data and signaling element data;

[0013] The basic element data is obtained from a professional network management or an integrated network system; the signaling element data is obtained from a service provider through an open API interface for capabilities.

[0014] Further, the target model is the average call duration per user model and / or the average Internet access rate per user model;

[0015] When the target model is the average Internet access traffic per user model, the component element data of the network node includes the total interface traffic and the number of Internet users;

[0016] The step S2 is specifically:

[0017] Synthesize the total interface traffic and the number of Internet users to obtain the average Internet access traffic per user model value of the network node, and its synthesis formula is as follows:

[0018] Average Internet access traffic per user model value = total interface traffic / number of Internet users.

[0019] Further, after the step S3, the method further includes a step S4:

[0020] Step S4: Feedback the network hidden fault to the terminal APP so that professional personnel can handle the network hidden fault.

[0021] Further, in the step S3, the difference between the target model values specifically includes: error difference, standard deviation difference or variance difference between the target model values;

[0022] When the difference between the target model values is the standard deviation difference, the step S3 specifically includes the following steps:

[0023] Step S31: Calculate the standard deviation between the target model values, and its calculation formula is as follows:

[0024]

[0025] Among them, Y is the standard deviation; μ is the average value of the target model values; N is the number of target model values, and N is a natural number greater than 1; X i is the target model value of the i-th target model, where i ∈ N;

[0026] Step S32: Calculate the deviation coefficient according to the standard deviation difference;

[0027] The deviation coefficient C v is calculated as follows:

[0028] C v = (Y / μ) * 100%;

[0029] Among them, Y is the standard deviation; μ is the average value of the target model values;

[0030] Step S33: Determine whether the deviation coefficient exceeds a preset deviation threshold:

[0031] If the deviation coefficient exceeds the preset deviation threshold, it is determined that there is a latent fault in the corresponding network node.

[0032] In a second aspect, the present invention provides a positioning device for latent faults in a mobile communication network. The device includes:

[0033] An acquisition unit, configured to acquire the constituent element data of all network nodes;

[0034] Among them, the constituent element data is obtained by decomposing the target model; the target model is a service model that conforms to the consistency principle and is pre-constructed according to the operator network topology and the service types carried by network nodes at each level;

[0035] A synthesis unit, connected to the acquisition unit, configured to synthesize the constituent element data of the network nodes to obtain the target model value of the network nodes;

[0036] A determination unit, connected to the synthesis unit, configured to determine whether there is a latent network fault according to the difference between the target model values of network nodes at the same time and at the same level;

[0037] Among them, if the difference between the target model value of a certain network node and the target model values of other network nodes at the same time and at the same level exceeds a preset threshold, the determination unit determines that there is a latent network fault in the network node, thereby completing the positioning of the latent network fault.

[0038] Further, the acquisition unit includes:

[0039] The first acquisition unit, connected to the synthesis unit, is configured to acquire the basic element data of all network nodes from a professional network management system or an integrated network system, so that the synthesis unit synthesizes the basic element data of the network nodes to obtain the target model value of the network nodes;

[0040] The second acquisition unit, connected to the synthesis unit, is configured to acquire the signaling element data of all network nodes from a service provider through an open API interface, so that the synthesis unit synthesizes the signaling element data of the network nodes to obtain the target model value of the network nodes.

[0041] Further, the synthesis unit includes:

[0042] The first synthesis unit, connected to the acquisition unit, is configured to synthesize the average call duration per user model;

[0043] The second synthesis unit, connected to the acquisition unit, is configured to synthesize the average Internet access rate per user model;

[0044] Wherein, the following formula is stored in the first synthesis unit:

[0045] Average Internet traffic per user model value = Total interface traffic / Number of Internet users.

[0046] Further, the determination unit includes:

[0047] The first determination unit, connected to the synthesis unit, is configured to determine whether there is a hidden network fault according to the error difference between the target model values of network nodes at the same time and the same level;

[0048] The second determination unit, connected to the synthesis unit, is configured to determine whether there is a hidden network fault according to the standard deviation difference between the target model values of network nodes at the same time and the same level;

[0049] The third determination unit, connected to the synthesis unit, is configured to determine whether there is a hidden network fault according to the variance difference between the target model values of network nodes at the same time and the same level;

[0050] The first determination unit includes:

[0051] The first calculation module is configured to calculate the standard deviation between the target model values;

[0052] The first calculation module stores the calculation formula for the standard deviation:

[0053]

[0054] Wherein, Y is the standard deviation; μ is the average value of the target model value; N is the number of target model values, and N is a natural number greater than 1; Xi is the target model value of the i-th target model, where i ∈ N;

[0055] A second calculation module, connected to the first calculation module, is configured to calculate a deviation coefficient according to the standard deviation difference;

[0056] The second calculation module stores a deviation coefficient C v The calculation formula is as follows:

[0057] C v = (Y / μ) * 100%;

[0058] where Y is the standard deviation; μ is the average value of the target model values;

[0059] A determination module, connected to the second calculation module, is configured to determine whether the deviation coefficient exceeds a preset deviation threshold:

[0060] If the deviation coefficient exceeds the preset deviation threshold, it is determined that there is a latent fault in the corresponding network node.

[0061] In a third aspect, the present invention provides an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to implement the method for locating latent faults in a mobile communication network as described in the first aspect.

[0062] Based on the consistency principle service model, the present invention can quickly and accurately identify latent faults in a mobile communication network, thereby ensuring the stability and reliability of the network.

[0063] Specific beneficial effects are as follows:

[0064] 1. Fast fault location: Based on the service model of the consistency principle, the present invention can quickly discover and locate latent faults by comprehensively analyzing the data of multiple network nodes. This method can immediately identify data inconsistencies between different network nodes, providing a strong basis for timely problem-solving.

[0065] 2. Accurate data analysis: The present invention makes full use of the correlation between different network nodes and conducts comprehensive data analysis using the consistency principle. This method can effectively capture potential latent network problems, significantly improve the accuracy of fault location, enable network operation and maintenance personnel to obtain accurate fault diagnosis information in real time, shorten the fault handling time, and thus provide a more stable network service.

[0066] 3. Improve user experience: Since the present invention can quickly and accurately discover and locate network faults, it effectively reduces service interruptions and user complaints caused by faults, thereby improving user satisfaction and loyalty.

[0067] 4. Reduce operation and maintenance costs: Through the automated fault detection and location process, the present invention reduces the need for manual intervention, alleviates the workload of operation and maintenance personnel, thereby saving labor costs and time costs.

[0068] 5. Enhance network security: The present invention can quickly locate faults, thereby reducing potential security risks and enhancing the security of the entire network.

[0069] 6. Support decision-making: Through accurate fault analysis and location, the present invention provides support for network operation and maintenance decisions, helps optimize network resource allocation, and achieves more efficient network management. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a schematic diagram of the method for locating hidden faults in a mobile communication network in an embodiment of the present invention;

[0071] Figure 2 It is a schematic diagram of the service bearing of a multi-level communication network of an operator in an embodiment of the present invention;

[0072] Figure 3 It is a schematic diagram of the topology of the service bearing of a multi-level communication network for 4G data services of a provincial operator in an embodiment of the present invention;

[0073] Figure 4 It is a schematic diagram of the abnormal location of the topology of the service bearing of a multi-level communication network for 4G data services of a provincial operator in an embodiment of the present invention;

[0074] Figure 5 It is a schematic diagram of the device for locating hidden faults in a mobile communication network in an embodiment of the present invention.

[0075] Reference numerals: 10, acquisition unit; 20, synthesis unit; 30, determination unit. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0076] To enable those skilled in the art to better understand the technical solutions of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0077] It can be understood that the specific embodiments and accompanying drawings described herein are only for explaining the present invention, rather than limiting the present invention.

[0078] It can be understood that, without conflict, the various embodiments and features in the embodiments of the present invention can be combined with each other.

[0079] It can be understood that for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings of the present invention, and the parts not related to the present invention are not shown in the drawings.

[0080] It is understandable that each unit and module involved in the embodiments of the present invention may correspond to only one entity structure, or may be composed of multiple entity structures. Alternatively, multiple units and modules may also be integrated into one entity structure.

[0081] It is understandable that, without conflict, the functions and steps marked in the flowcharts and block diagrams of the present invention may occur in an order different from that marked in the drawings.

[0082] It is understandable that in the flowcharts and block diagrams of the present invention, the possible system architectures, functions, and operations of the systems, devices, equipment, and methods according to the embodiments of the present invention are shown. Among them, each block in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified function. Moreover, each block or combination of blocks in the block diagram and flowchart can be implemented by a hardware-based system for implementing the specified function, or by a combination of hardware and computer instructions.

[0083] It is understandable that the units and modules involved in the embodiments of the present invention can be implemented in software or in hardware. For example, the units and modules can be located in the processor.

[0084] Embodiment 1:

[0085] This embodiment provides a method for locating hidden faults in a mobile communication network. The method of this embodiment is mainly used for network operation and maintenance management. By relying on real-time monitoring and data analysis, it can quickly identify potential hidden faults, thereby improving the efficiency of fault troubleshooting and ensuring the stability of communication services. When dealing with user complaints, this method can quickly locate the root cause of the problem and improve the user experience. At the same time, it provides support for network optimization, enabling operation and maintenance personnel to foresee and solve network performance bottlenecks. In addition, this method also has the function of risk assessment to ensure the reliability of the network architecture, thereby overall improving the quality and security of the mobile communication network.

[0086] The technical solution of this embodiment is based on the principle of consistency of the user service model. By collecting data related to the specified service model on different network nodes at each network layer, and using a pre-set system to perform operations on these data, it analyzes whether there are obvious differences in the service model values of a certain network node and other network nodes at the same level (expressed, for example, by apparent error, standard deviation, or variance). If a large difference is found, it can be determined that there is a hidden fault in this network node.

[0087] For the complex multi - level communication networks of operators, in order to ensure service security and sufficient network carrying capacity, specific services are usually randomly distributed to multiple network node devices at the same level for joint hosting. The "service model consistency principle" in this embodiment refers to that when the network schedules services, based on factors such as the capacity of the lower - level network, the operator randomly distributes a large number of services of the same type to network elements at the next network level with specific weights. Due to the randomness of service distribution, theoretically, at the same time point (within a period of time), the total service model values (such as total call duration, total Internet traffic, etc.) carried by different node network elements in the lower - level network will show obvious differences due to different distribution weights at the upper level. However, some average - value - type service model values (such as average call duration per user, average Internet traffic per user, etc.) will not show obvious deviations at different network levels and nodes.

[0088] In the operator's network, usually in the absence of network anomalies (such as individual network node failures, etc.), some average - value - type service model values will not change abnormally due to the location of the data collection source (different network levels or network nodes). Therefore, when calculating the average - value - type service models at different network levels or network element nodes at the same time, their calculation results often show very similar characteristics.

[0089] As Figure 2 shown, this embodiment is based on a multi - level distribution network structure, including network nodes at different levels. Specifically, it includes a multi - level control and distribution network:

[0090] First - level control and distribution network:

[0091] This is the highest level of the entire network, responsible for overall control and management. Its main task is to coordinate the operations of lower - level nodes and data distribution.

[0092] Second - level distribution network nodes:

[0093] These nodes are located below the first - level control network and are mainly responsible for receiving data or instructions from the first - level network and distributing them to lower - level nodes.

[0094] Third - level distribution network nodes:

[0095] These nodes are located below the second - level nodes and are responsible for further distributing data or instructions. N - level distribution network nodes:

[0096] N - level distribution network nodes:

[0097] These nodes represent the lower - level distribution nodes in the network, usually more levels after the third - level nodes.

[0098] This multi-level distribution network structure is usually applied to large-scale data distribution systems, such as content delivery networks (CDNs) or distributed computing systems. Nodes at each level are responsible for distributing data or tasks to nodes closer to the end-users to improve data transmission efficiency and response speed. Through this hierarchical architecture, the system can effectively manage and distribute large amounts of data while ensuring network stability and reliability.

[0099] As Figure 1 shown, this embodiment provides a method for locating hidden faults in a mobile communication network, which specifically includes the following steps:

[0100] Step S1: Obtain the composition element data of all network nodes; the composition element data is obtained by decomposing a target model; the target model is a service model that is pre-constructed according to the operator network topology and the service types carried by network nodes at each level and conforms to the consistency principle.

[0101] Specifically, the composition element data specifically includes: basic element data and signaling element data; the basic element data is obtained from a professional network management system or an integrated network system; the signaling element data is obtained from a service provider through a capabilities open API interface. The composition element data can be divided into basic element data and signaling element data, and these two parts of data jointly provide important information for network management and fault location. The basic element data is the core information required for the network to maintain its normal operation, including device status, performance indicators, device traffic, user access conditions, etc. These data can help the operator monitor the health status of the network in real time and provide a necessary basis for network optimization. The acquisition of basic element data mainly depends on professional network management systems (network management systems) and integrated network systems. These systems have strong data collection and analysis capabilities, can monitor various devices and nodes in the network in real time, and record their operating status and performance. Through effective data collection, the operator can timely discover potential problems and take corresponding measures to ensure network stability and reliability. The signaling element data focuses on the communication and signal exchange between devices in the network, mainly involving control signaling and user requests. These data are usually obtained from a service provider through a capabilities open API interface. This open interface allows seamless data exchange between different systems, enabling the operator to obtain signaling information about call connection, data transmission status, and other network functions in real time. By analyzing the signaling element data, the operator can gain a deeper understanding of user behavior, respond to customer needs in a timely manner, and thus improve the user experience. The target model includes various models such as the average call duration per user model and the average Internet access rate per user model.

[0102] Step S2: Synthesize the composition element data of the network nodes to obtain the target model value of the network nodes.

[0103] Specifically, when the target model is the per-user Internet traffic model, the component data of the network node includes the total interface traffic and the number of Internet users. Synthesizing the component data of the network node is to synthesize the total interface traffic and the number of Internet users to obtain the per-user Internet traffic model value of the network node. The synthesis formula is as follows:

[0104] Per-user Internet traffic model value = Total interface traffic / Number of Internet users.

[0105] Synthesizing the component data of the network node is to generate the target model value of the network node to help the operator evaluate the network performance and user experience. In this process, the target model value is obtained by combining different data. Specifically, when the target model is the per-user Internet traffic model, it depends on the two key component data of the total interface traffic and the number of Internet users. This synthesis can provide the operator with a more intuitive network usage situation, thus facilitating better management and optimization. Specifically, the total interface traffic in the component data represents the sum of all user traffic passing through the network node within a specific time. This data is collected in real time through the monitoring function of network devices to ensure an accurate reflection of the overall network consumption. On the other hand, the number of Internet users represents the total number of users who are simultaneously using the interface to access the Internet, which can indicate the user activity and load of the network. By combining these two data, the operator can more clearly understand the current network load and efficiency. Calculate the per-user Internet traffic model value through the synthesis formula, specifically expressed as "Per-user Internet traffic model value = Total interface traffic / Number of Internet users". The significance of this formula is that it divides the total traffic by the actual number of users to obtain the average traffic consumed by each user. This indicator can not only help the operator identify traffic anomalies in the network but also provide a basis for analyzing user behavior during peak and off-peak periods, thereby providing a scientific basis for network optimization and resource allocation.

[0106] Step S3: Determine whether there is a hidden network fault based on the difference between the target model values of network nodes at the same time and the same level; specifically, if the difference between the target model value of a certain network node and the target model values of other network nodes at the same time and the same level exceeds a preset threshold (the threshold is preset in advance), it is determined that there is a hidden network fault in this network node, thus completing the location of the hidden network fault.

[0107] Specifically, in step S3, the differences between the target model values specifically include: error differences, standard deviation differences, or variance differences between the target model values;

[0108] The error difference refers to the gap between the target model value and the actual observed value, which reflects the accuracy of the model prediction. It can be measured by calculating the difference between each model value and the actual value (such as absolute error or relative error). A larger error difference usually indicates insufficient or unstable prediction ability of the model, while a smaller error indicates that the model can better reflect the actual situation. Therefore, the error difference is an important indicator for evaluating model performance and optimizing the model.

[0109] The variance difference refers to the degree of fluctuation among a set of target model values, which is measured by calculating the deviation degree between the model value and its mean. The larger the variance, the more obvious the differences and fluctuations among the model values, reflecting the instability and inconsistency of the model prediction; while the smaller the variance, the more concentrated the model values are and the more consistent the prediction results are. Analyzing the variance difference helps to evaluate the performance stability of the model under different conditions and optimize the model to improve its prediction reliability.

[0110] When the difference among the target model values is the standard deviation difference, step S3 specifically includes the following steps:

[0111] Step S31: Calculate the standard deviation among the target model values, and its calculation formula is as follows:

[0112]

[0113] where Y is the standard deviation; μ is the average value of the target model values; N is the number of target model values, and N is a natural number greater than 1; X i is the target model value of the i-th target model, i ∈ N;

[0114] Step S32: Calculate the deviation coefficient according to the standard deviation difference;

[0115] The deviation coefficient C r has the following calculation formula:

[0116] C v = (Y / μ) * 100%;

[0117] where Y is the standard deviation; μ is the average value of the target model values;

[0118] Step S33: Determine whether the deviation coefficient exceeds the preset deviation threshold:

[0119] If the deviation coefficient exceeds the preset deviation threshold, it is determined that there is a hidden fault in the corresponding network node.

[0120] Assume there are 5 network nodes (N = 5), and the total interface traffic and the number of Internet users of each node are as follows: The total interface traffic of node 1 is 1000 GB, and the number of Internet users is 100. Therefore, the average Internet traffic per user model value = total interface traffic / number of Internet users = 10 GB / user; The total interface traffic of node 2 is 1200 GB, and the number of Internet users is also 100. The average Internet traffic per user model value is 12 GB / user; The total interface traffic of node 3 is 1100 GB, and the number of Internet users is 100. The calculated average Internet traffic per user model value is 11 GB / user; The total interface traffic of node 4 is 1300 GB, and the number of Internet users is also 100. The average Internet traffic per user model value is 13 GB / user; While the total interface traffic of node 5 reaches 1400 GB, and the number of Internet users is 100. Therefore, its average Internet traffic per user model value is 14 GB / user. That is, the target model values of each node are obtained as follows: X 1 = 10, X 2 = 12, X 3 = 11, X 4 = 13, X 5 = 14.

[0121] Step S31: Calculate the standard deviation between the target model values:

[0122] First, calculate the average value μ of these target model values:

[0123] μ = (10 + 12 + 11 + 13 + 14) / 5 = 12;

[0124] Then, calculate the square of the difference between each value and the average value:

[0125] (10 - 12) 2 = 4, (12 - 12) 2 = 0, (11 - 12) 2 = 1,

[0126] (13 - 12) 2 = 1, (14 - 12) 2 = 4,

[0127] Next, calculate the average value of these squared differences:

[0128] (4 + 0 + 1 + 1 + 4) / 5 = 2;

[0129] Finally, calculate the standard deviation

[0130] Step S32: Calculate the deviation coefficient:

[0131] C v=(Y / μ)*100%=(1.414 / 12)*100%≈11.78%.

[0132] Step S33: Determine whether the deviation coefficient exceeds a preset deviation threshold:

[0133] Assume that the preset deviation threshold is 10%. Since the calculated deviation coefficient C v ≈11.78% is greater than 10%, it is determined that there is a latent fault in the corresponding network node.

[0134] For the operator's multi-level and multi-node network architecture, based on the consistency principle of the user service model, this embodiment collects the user service-related data of each network node at each network level. After the pre-set system performs operations and analyzes these collected data, if it is found that there are obvious differences in the service model data between a certain network node or its associated upper and lower level network nodes and other network nodes at the same level, it can be determined that the network node with the difference may have a latent fault. This method effectively helps the operator quickly identify and locate potential problems in a complex network environment, improving the stability and reliability of the network. In this embodiment, by collecting the user service-related data of each network node at each network level and using the pre-set system to perform operations and analyze these data, obvious differences in the service model data can be found, for example, expressed by apparent error, standard deviation or variance, etc. By applying the consistency principle of the user service model, the inconsistency between a certain network node or its associated upper and lower level network nodes and other network nodes at the same level can be discovered and accurately located, thus effectively identifying potential network faults.

[0135] Step S4: Feed back the network latent fault to the terminal APP so that professionals can handle the network latent fault. The feedback of the network latent fault to the terminal APP can be achieved in various ways to ensure that users can timely understand the network status. First, the operator can directly push the real-time fault information to the user's terminal APP through the network protocol, which ensures the immediacy and accuracy of the information. Second, when a latent fault occurs in the network, the operator can also use SMS notifications to send the fault situation and relevant handling progress to the user's mobile phone, which is especially suitable for users who may not be able to connect to the network in a short time. In addition, the push notification function in the terminal APP can also be used to inform users of the latest dynamics about the fault, and users can view the historical notifications and fault handling status at any time. To enhance the user interaction experience, the APP can also set up a problem feedback channel to encourage users to actively report problems during use, and the operator can then analyze and handle the faults based on the feedback information. At the same time, sending fault notifications using the user's reserved email or social media accounts is also an effective communication method. Through these comprehensive means, it is ensured that users can smoothly obtain the relevant information about the network latent fault and improve user satisfaction. When the deviation coefficient Cv of the service model value calculated by the preset system device is greater than the set value T, the system will determine that there is a latent fault in the corresponding network node. For example, if the deviation coefficient Cv calculated by the system exceeds the set value T of 3%, it means that a network node with differences is found to have a latent fault. Once the system identifies that there is a latent fault in the network node, it will automatically notify the professional in the form of an alarm. The professional who receives the notification will further accurately locate the specific network node element where the fault occurs through manual assistance based on the number of network node elements of the network node that triggers the alarm, combined with the network topology and service characteristics.

[0136] Taking the discovery and location process of a Gi-FW latent fault of a certain telecom operator as an example for detailed elaboration. In this scenario, the bearing topology diagram of the 4G data service multi-level communication network of this telecom operator is as Figure 3 shown.

[0137] After the Spring Festival in a certain year, this telecom operator received a large number of user complaints about the lag of 4G Internet access services in many cities across the province, but the specific locations of the users were uncertain. After preliminary investigation, the operator excluded the faults in the wireless network, and no fault alarms were issued by the network nodes at all levels such as the bearing network and the core network, and the daily performance indicators were also normal. To further investigate, the maintenance team conducted a large number of dial tests on the 4G Internet access problems reported by users and deeply tracked the signaling, but no abnormal situations were found. Before the method of the present invention was developed, after two months of investigation and analysis, the problem still could not be clearly defined, and the maintenance team was once in trouble.

[0138] After a series of analyses and in-depth considerations, the R & D team where the inventor belongs found that the 4G Internet access service is based on the carrying capacity of each level of the network and is randomly distributed to different network nodes for carrying in proportion. Under normal circumstances, the value of the "average Internet traffic model per user" of each network node should be consistent, that is, at the same moment, the service model values of different network nodes should not show significant differences due to different network levels and nodes. However, if a certain network node at a certain level has an abnormality, it usually affects the consistency of the "average Internet traffic model per user during peak hours" value.

[0139] Based on this principle, the inventor developed the method in this embodiment. According to the method in this embodiment, the maintenance team collected, calculated, and analyzed the data of the "average Internet traffic model per user during peak hours" for the network nodes at the SAEGW level. After analysis, the team quickly found that the apparent error of the average Internet traffic per user during peak hours of the four network nodes SAEGW13, SAEGW14, SAEGW15, and SAEGW16 was nearly 4 percentage points lower than that of the other 15 peer network nodes, and the deviation of the other nodes was within 1%. Through this difference, the method gave a hint that there might be a hidden fault.

[0140] Through further analysis, it was judged that there might be problems or potential hazards in the upper or lower network nodes of this network node. Combining the service characteristics of the upper and lower network elements at the SAEGW level and through comprehensive judgment, the network node affecting user complaints was accurately located to the Gi-FW device in the lower network node computer room 5 at the SAEGW level (as Figure 4 shown).

[0141] After in-depth analysis of the Gi-FW device in computer room 5, the root cause of the complaint problem was quickly found: an abnormality occurred in the internal forwarding port of a certain service board of the device. After calculation, it was found that although this hidden fault only affected 0.875% of the 4G users in the province for Internet access, due to its small impact range, it was difficult to clearly determine the specific cause of the 4G Internet access problem complained by users through conventional dial tests and signaling tracking.

[0142] The above process fully demonstrates the effective application of the technical solution of the present invention in complex network fault location.

[0143] The method of this embodiment is based on a service model of the consistency principle, which can quickly locate hidden faults in a mobile communication network, thus ensuring the stability and reliability of the network. Through comprehensive analysis of data from multiple network nodes, this embodiment can quickly discover and locate hidden faults, timely identify data inconsistencies between different nodes, and provide strong evidence for problem-solving. In addition, this method makes full use of the correlation between nodes to achieve comprehensive data analysis, improves the accuracy of fault location, enables operation and maintenance personnel to obtain accurate fault diagnosis information in real time, greatly shortens the fault handling time, and further improves the stability of network services. Thanks to this fast and accurate fault location ability, this embodiment effectively reduces service interruptions and user complaints, thereby enhancing user satisfaction and loyalty. At the same time, this automated fault detection and location process reduces the need for manual intervention, lightens the workload of operation and maintenance personnel, and saves manpower and time costs. In addition, this embodiment can quickly locate faults, reduce potential security risks, and enhance network security. At the same time, it provides support for network operation and maintenance decisions, helps optimize resource allocation, and achieves more efficient network management.

[0144] Embodiment 2:

[0145] As Figure 5 shown, this embodiment provides a device for locating hidden faults in a mobile communication network, and the device includes:

[0146] An acquisition unit 10, configured to acquire composition element data of all network nodes;

[0147] Wherein, the composition element data are basic elements or signaling elements obtained by decomposing a target model; the target model is a service model that conforms to the consistency principle and is pre-constructed according to the operator network topology and the service types carried by network nodes at each level;

[0148] A synthesis unit 20, connected to the acquisition unit 10, configured to synthesize the composition element data of network nodes to obtain a target model value of the network nodes;

[0149] A determination unit 30, connected to the synthesis unit 20, configured to determine whether there is a network hidden fault according to the difference between the target model values of network nodes at the same time and the same level;

[0150] Wherein, if the difference between the target model value of a certain network node and the target model values of other network nodes at the same time and the same level exceeds a preset threshold, the determination unit determines that there is a network hidden fault in this network node, thereby completing the location of the network hidden fault.

[0151] As a specific implementation manner, the acquisition unit 10 includes:

[0152] The first acquisition unit, connected to the synthesis unit, is configured to acquire the basic element data of all network nodes from a professional network management system or an integrated network system, so that the synthesis unit synthesizes the basic element data of the network nodes to obtain the target model value of the network nodes;

[0153] The second acquisition unit, connected to the synthesis unit, is configured to acquire the signaling element data of all network nodes from a service provider through an open API interface for capabilities, so that the synthesis unit synthesizes the signaling element data of the network nodes to obtain the target model value of the network nodes.

[0154] As a specific implementation manner, the synthesis unit 20 includes:

[0155] The first synthesis unit, connected to the acquisition unit, is configured to synthesize the average call duration per user model;

[0156] The second synthesis unit, connected to the acquisition unit, is configured to synthesize the average Internet access rate per user model;

[0157] Wherein, the following formula is stored in the first synthesis unit:

[0158] Average Internet access traffic per user model value = total interface traffic / number of Internet users.

[0159] As a specific implementation manner, the determination unit 30 includes:

[0160] The first determination unit, connected to the synthesis unit, is configured to determine whether there is a hidden network fault according to the error difference between the target model values of network nodes at the same time and the same level;

[0161] The second determination unit, connected to the synthesis unit, is configured to determine whether there is a hidden network fault according to the standard deviation difference between the target model values of network nodes at the same time and the same level;

[0162] The third determination unit, connected to the synthesis unit, is configured to determine whether there is a hidden network fault according to the variance difference between the target model values of network nodes at the same time and the same level;

[0163] The first determination unit includes:

[0164] The first calculation module is configured to calculate the standard deviation between the target model values;

[0165] The first calculation module stores the calculation formula for the standard deviation:

[0166]

[0167] Wherein, Y is the standard deviation; μ is the average value of the target model values; N is the number of target model values, and N is a natural number greater than 1; X i is the target model value of the i-th target model, and i ∈ N;

[0168] The second calculation module is connected to the first calculation module and is configured to calculate a deviation coefficient according to the standard deviation difference;

[0169] The second calculation module stores the deviation coefficient C v The calculation formula is as follows:

[0170] C v = (Y / μ) * 100%;

[0171] Wherein, Y is the standard deviation; μ is the average value of the target model values;

[0172] The determination module is connected to the second calculation module and is configured to determine whether the deviation coefficient exceeds a preset deviation threshold:

[0173] If the deviation coefficient exceeds the preset deviation threshold, it is determined that there is a latent fault in the corresponding network node.

[0174] The device in this embodiment can execute the method in Embodiment 1.

[0175] Embodiment 3:

[0176] This embodiment provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to implement the method for locating latent faults in a mobile communication network as described in Embodiment 1.

[0177] It can be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principles of the present invention, and the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also regarded as the protection scope of the present invention.

Claims

1. A method for locating hidden faults in a mobile communication network, characterized in that: The method comprises the following steps: Step S1: Obtain component element data of all network nodes; The component element data is obtained by decomposing the target model; the target model is a business model that complies with the consistency principle and is constructed in advance according to the operator network topology and the business types carried by each layer of network nodes; Step S2: synthesizing the component element data of the network node to obtain the target model value of the network node; Step S3: judging whether there is a hidden network fault according to the difference between the target model values ​​of the network nodes at the same time and at the same level; If the target model value of a certain network node differs from the target model value of other network nodes at the same time and level by more than a preset threshold, it is determined that the network node has a hidden network fault, thereby completing the location of the hidden network fault.

2. The method for locating hidden faults in a mobile communication network according to claim 1, characterized in that: The component element data in step S1 specifically includes: basic element data and signaling element data; The basic element data is obtained from a professional network management or integrated network system; the signaling element data is obtained from a service provider through a capability exposure API interface.

3. The method for locating hidden faults in a mobile communication network according to claim 1, characterized in that: The target model is an average per-user call duration model and / or an average per-user Internet access rate model; When the target model is an average per-user online traffic model, the component element data of the network node includes the total interface traffic and the number of online users; The step S2 is specifically: The total interface traffic and the number of online users are synthesized to obtain an average online traffic model value per user of the network node, and the synthesis formula is as follows: Average Internet traffic model value per user = total interface traffic / number of Internet users.

4. The method for locating hidden faults in a mobile communication network according to claim 1, characterized in that: After step S3, the method further comprises step S4: Step S4: Feedback the network hidden fault to the terminal APP so that professionals can handle the network hidden fault.

5. The method for locating hidden faults in a mobile communication network according to any one of claims 1 to 4, characterized in that: In step S3, the difference between the target model values ​​specifically includes: an error difference, a standard deviation difference or a variance difference between the target model values; When the difference between the target model values ​​is a standard deviation difference, step S3 specifically includes the following steps: Step S31: Calculate the standard deviation between the target model values, and the calculation formula is as follows: Where Y is the standard deviation; μ is the average value of the target model value; N is the number of target model values, and N is a natural number greater than 1; X i is the target model value of the i-th target model, i∈N; Step S32: Calculate the coefficient of deviation according to the standard deviation difference; The coefficient of variation C v The calculation formula is as follows: C v =(Y / μ)*100%; Where Y is the standard deviation; μ is the mean value of the target model value; Step S33: Determine whether the deviation coefficient exceeds a preset deviation threshold: If the deviation coefficient exceeds the preset deviation threshold, it is determined that the corresponding network node has a hidden fault.

6. A device for locating hidden faults in a mobile communication network, characterized in that: include: An acquisition unit, used to acquire component element data of all network nodes; The component element data is obtained by decomposing the target model; the target model is a business model that complies with the consistency principle and is constructed in advance according to the operator network topology and the business types carried by each layer of network nodes; A synthesis unit, connected to the acquisition unit, for synthesizing the constituent element data of the network node to obtain a target model value of the network node; A determination unit connected to the synthesis unit, and configured to determine whether there is a hidden network fault according to the difference between the target model values ​​of the network nodes at the same time and at the same level; If the target model value of a certain network node differs from the target model value of other network nodes at the same time and level by more than a preset threshold, the determination unit determines that the network node has a hidden network fault, thereby locating the hidden network fault.

7. The device for locating hidden faults in a mobile communication network according to claim 6, characterized in that: The acquisition unit comprises: A first acquisition unit, connected to the synthesis unit, is used to acquire basic element data of all network nodes from a professional network management or an integrated network system, so that the synthesis unit synthesizes the basic element data of the network nodes to obtain target model values ​​of the network nodes; The second acquisition unit is connected to the synthesis unit and is used to obtain the signaling element data of all network nodes from the service provider through the capability exposure API interface, so that the synthesis unit synthesizes the signaling element data of the network nodes to obtain the target model value of the network node.

8. The device for locating hidden faults in a mobile communication network according to claim 6, characterized in that: The synthesis unit comprises: A first synthesis unit, connected to the acquisition unit, for synthesizing an average per-user talk time model; A second synthesis unit, connected to the acquisition unit, for synthesizing an average Internet access rate model per user; The first synthesis unit stores the following formula: Average Internet traffic model value per user = total interface traffic / number of Internet users.

9. The device for locating hidden faults in a mobile communication network according to any one of claims 6 to 8, characterized in that: The determination unit comprises: A first determination unit, connected to the synthesis unit, is used to determine whether there is a network hidden fault according to the error difference between the target model values ​​of the network nodes at the same time and the same level; A second determination unit, connected to the synthesis unit, is used to determine whether there is a network hidden fault according to the standard deviation difference between the target model values ​​of the network nodes at the same time and the same level; A third determination unit, connected to the synthesis unit, is used to determine whether there is a network hidden fault according to the variance difference between the target model values ​​of the network nodes at the same time and the same level; The first determination unit comprises: A first calculation module, used to calculate the standard deviation between target model values; The first calculation module stores a calculation formula for the standard deviation: Where Y is the standard deviation; μ is the average value of the target model value; N is the number of target model values, and N is a natural number greater than 1; X i is the target model value of the i-th target model, i∈N; A second calculation module, connected to the first calculation module, for calculating a coefficient of deviation according to the standard deviation difference; The second calculation module stores a deviation coefficient C v The calculation formula is as follows: C v =(Y / μ)*100%; Where Y is the standard deviation; μ is the mean value of the target model value; A determination module, connected to the second calculation module, is used to determine whether the deviation coefficient exceeds a preset deviation threshold: If the deviation coefficient exceeds the preset deviation threshold, it is determined that the corresponding network node has a hidden fault.

10. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to implement the method for locating a hidden fault in a mobile communication network according to any one of claims 1 to 5.

Images