A wireless network health assessment method suitable for industry field networks

Abstract

The present invention discloses a wireless network health assessment method suitable for industry field networks, including: extracting industry terminal-level indicator data, scoring the associated items of each dimension in the indicator data according to priority; grading problems according to the scoring situation, distinguishing the points that need to be checked on site; extracting the serial numbers of various industry terminals in the network management for matching; calculating the comprehensive scores of each dimension, and dividing the hidden danger fault levels of industry terminals according to the comprehensive scores; executing the corresponding fault handling plan according to the divided hidden danger fault levels of industry terminals; and continuously iterating and improving the indicator mapping model through on-site verification. The present invention utilizes the collected big data resources to analyze the correlation between background indicator phenomena and on-site problems, realizes the mapping of indicators and problems, and then through on-site analysis and verification, realizes the iteration of algorithms, optimization and calibration of models, batch output of existing field network problems and promotes their resolution, and realizes effective monitoring of new field network problems.

Description

Technical Field

[0001] The present invention belongs to the field of wireless communication technology, and relates to wireless network health assessment and intelligent operation and maintenance of industry field networks in scenarios such as smart energy, smart manufacturing, and smart medical care, and specifically to a wireless network health assessment method suitable for industry field networks. Background Art

[0002] In recent years, the scale of industry field network users has been increasing day by day, and the types of industry terminal equipment and network construction needs have become increasingly diverse. Industry field networks have borne more and more business pressure. The maintenance and quality control of industry field networks have also gradually become the focus of attention. Traditional field network system maintenance and quality control methods mainly rely on inspections and responses to alarms, which are solved on-site by maintenance personnel. However, with the rapid development of information and communication technology, the current traditional operation and maintenance model that is mainly manual has a gap with the advancement of the network itself, and the difficulties and challenges in operation and maintenance have become increasingly prominent. Fault analysis and location and root cause tracing are difficult, and the existing passive response operation and maintenance model is inefficient and has a poor customer experience. This method has the following defects:

[0003] 1. High cost and low efficiency

[0004] With the continuous rise in labor costs in recent years and the expansion of the scale of field network system construction, the cost of inspecting a large number of field network systems has gradually increased; at the same time, alarms generally cannot directly reveal the corresponding hardware or software failures, and must be investigated and located on-site by experienced technical experts. It is often necessary to debug the main equipment, investigate the backbone and leveling, and check a series of parts such as edge gateways and branch and line distribution devices. This is inefficient. When multiple failures occur simultaneously in a certain area, the number of technical personnel is often stretched to the limit, and the problems cannot be solved in a timely and efficient manner.

[0005] 2. Outdated means and lack of system

[0006] Due to the long-term lack of support for systematic indicator monitoring, the actual maintenance work of the field network system lacks effective planning guidance. When encountering a field network system failure, maintenance personnel often use simple means such as "restarting equipment, replacing new components", without analyzing the cause of the problem, and without any preventive measures for potential hidden dangers that may emerge later. This often results in the inability to improve the maintenance level, and more seriously, it is difficult to form a mechanism to solve and prevent hidden dangers.

[0007] 3. Impact on users and waste of resources

[0008] Due to the above-mentioned inefficiency, when performing field network system maintenance in power operation sites, monitoring and dispatching centers, medical facilities, production bases and other scenarios, it is sometimes necessary to enter the site during working hours to check different parts, affecting industry operations and production activities; at the same time, due to the lack of a mechanism for predicting hidden dangers, some sites will repeatedly fail, interfering with the daily work of industry users and causing a lot of waste of manpower and financial resources. In addition, the lack of necessary analysis and utilization of massive field network maintenance data is a waste of big data resources.

[0009] It can be seen that these problems with traditional means have affected the maintenance quality, economic and technical benefits of the field network system, and made it unable to cope with the challenges of diversified 5G+ vertical industry applications in the next few years. Summary of the invention

[0010] Purpose of the invention: In order to overcome the deficiencies in the prior art, a wireless network health assessment method suitable for industry field networks is provided, which utilizes collected big data resources to analyze the correlation between background indicator phenomena and field problems, and realizes the mapping of indicators and problems under an effective health assessment system. Furthermore, through field analysis and verification, the algorithm is iterated, the model is optimized and calibrated, and the existing field network problems are batch-output and promoted for resolution, thereby realizing effective monitoring of new field network problems.

[0011] Technical solution: To achieve the above purpose, the present invention provides a wireless network health assessment method suitable for industry field networks, comprising the following steps:

[0012] S1: Extract industry terminal-level indicator data;

[0013] S2: Score the related items of each dimension in the indicator data according to the priority according to the indicator scoring table; the degree of correlation of the related items should be formulated and regularly updated by the experienced operation and maintenance experts of the operator in accordance with the "Working Procedures" of the communication operator in the region;

[0014] S3: In the network management, the serial numbers of the terminals in each industry are extracted for matching so as to locate the fault and determine whether the faulty industry terminals are connected to the same base station, sector or cell;

[0015] S4: Calculate the comprehensive scores of each dimension, and classify the hidden dangers and fault levels of industry terminals according to the comprehensive scores through the indicator mapping model;

[0016] S5: Execute the corresponding fault handling plan according to the classified industry terminal hidden danger fault level;

[0017] S6: Continuously iterate and improve the indicator mapping model through on-site verification.

[0018] Furthermore, the dimensions of the industry terminal-level indicator data in step S1 include traffic, coverage, connection indicator anomalies and antenna feeder anomalies.

[0019] Furthermore, the associated items of the traffic include high traffic on the gateway and no traffic on the industry terminal, high traffic on the gateway and low traffic on the industry terminal, and unbalanced traffic on the industry terminal. The associated items of the coverage include unbalanced coverage, good overall coverage of the scene and local weak coverage. The associated items of the abnormal connection indicators include low RRC establishment success rate, low e-rab establishment success rate, and high e-rab drop rate. The associated items of the antenna feed abnormality include antenna channel interference, unbalanced multi-channel antenna interference, and abnormal standing wave ratio.

[0020] Furthermore, in step S1, the priorities are divided into high, medium and low.

[0021] Furthermore, the priority of the associated items of each dimension in step S1 is determined by: determining the priority according to the indicator threshold of each dimension. The indicator threshold is specifically formulated by experienced operation and maintenance experts of the operating enterprise and is updated regularly.

[0022] Furthermore, the comprehensive score of each dimension in step S4 is the sum of the scores of the associated items of each dimension; the industry terminal hidden danger fault levels include level I, level II, and level III.

[0023] Furthermore, the fault handling solution in step S5 is specifically as follows:

[0024] Level I fault handling plan: dispatch maintenance orders, and maintenance personnel will verify and rectify the faults on site as soon as possible;

[0025] Level II fault handling plan: dispatch maintenance orders, and maintenance personnel conduct on-site inspections and rectify faults;

[0026] Level III fault handling plan: Include in the key observation list and track the extraction indicators.

[0027] Furthermore, the iterative and perfecting method of the indicator mapping model in step S6 is:

[0028] The iterative optimization of the indicator mapping model is abstracted as a convex optimization problem, and the stochastic gradient descent algorithm (SGD) is used to solve and calculate the convex optimization problem, as follows:

[0029] The input vector in the model is the background indicator phenomenon {X1, X2, X3, ...}, and the output vector is the actual problem verified on site {Y1, Y2, Y3, ...}. At the same time, let the prediction result of the model be the vector {A1, A2, A3, ...}. It can be seen that the purpose of the algorithm iteration is to make the prediction result A of the model close to the actual fault Y of the field network system;

[0030] Define the following root mean square error as the loss function (Cost Function):

[0031]

[0032] In the above formula, w and b are the sets of weights and biases respectively, ||·|| is the norm operation, and the purpose of iteration is to minimize C. Similar to other gradient descent examples, the direction with the fastest descent speed can be determined by the negative direction of the gradient of the convex function C, that is, the iteration direction that enables the established model to approach the true value as quickly as possible. Through iterative calculation, the update formula of weights and biases can be obtained:

[0033]

[0034] Combined with the results of on-site verification and investigation, a set of weights and biases can be found to minimize the root mean square error, which makes the model more accurate.

[0035] In order to maintain and optimize the field network system in a more targeted and timely manner, the present invention proposes to develop an accurate prediction model using multi-source data through big data analysis, and establish a wireless network health assessment method suitable for industry field networks. The key to developing an effective wireless network health assessment method is to use the collected big data resources to analyze the correlation between background indicator phenomena and field problems, and to achieve the mapping of indicators and problems under an effective health assessment system. Then, through on-site analysis and verification, the algorithm iteration, model optimization and calibration, batch output of existing field network problems and promotion of solutions can be achieved, and effective monitoring of new field network problems can be achieved.

[0036] Beneficial effects: Compared with the prior art, the present invention can adapt to the characteristics of complex industry field network networking, diverse terminals and demands, etc., which is conducive to reducing labor costs and experience requirements for staff, reducing interference with users' daily life and production, reducing the overall failure rate and failure duration, and effectively responding to the increasing pressure and challenges faced by operators and industry users in network operation and maintenance; the present invention provides important assistance for realizing the intelligent operation and maintenance of industry field networks, empowers operation and maintenance services, forms automated and intelligent operation and maintenance capabilities with customers and services as the core, improves operation and maintenance efficiency, improves customer network experience, and ultimately forms a high-value industry field network operation and management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the process of the present invention;

[0038] Figure 2 Iterative flow chart of stochastic gradient descent method. DETAILED DESCRIPTION

[0039] The present invention is further explained below in conjunction with the accompanying drawings and specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention. After reading the present invention, various equivalent forms of modifications to the present invention by those skilled in the art all fall within the scope defined by the claims attached to this application.

[0040] The present invention provides a wireless network health assessment method suitable for industry field networks, such as Figure 1 As shown, it includes the following steps:

[0041] S1: Extract industry terminal-level indicator data;

[0042] The dimensions of industry terminal-level indicator data include traffic, coverage, connection indicator anomalies, and antenna feeder anomalies;

[0043] S2: Score the related items of each dimension in the indicator data according to the priority according to the indicator scoring table;

[0044] The degree of correlation of the correlation items shall be determined in accordance with the "Working Procedures" of the telecommunications operator in the region and shall be specifically formulated and regularly updated by the operator's experienced operation and maintenance experts;

[0045] The associated items of traffic include high traffic on the gateway and no traffic on the industry terminal, high traffic on the gateway and low traffic on the industry terminal, and unbalanced traffic on the industry terminal. The associated items of coverage include unbalanced coverage, good overall coverage of the scene and weak local coverage. The associated items of abnormal connection indicators include low RRC establishment success rate, low e-rab establishment success rate, and high e-rab drop rate. The associated items of antenna feed abnormalities include antenna channel interference, unbalanced multi-channel antenna interference, and abnormal standing wave ratio.

[0046] Priority is divided into high, medium and low;

[0047] The priority of the associated items of each dimension is determined by: determining the priority according to the threshold of each dimension indicator;

[0048] The scoring method is as follows: the correlation items of each dimension and degree decrease as the priority level decreases;

[0049] The specific scoring situation in this embodiment is shown in Table 1 below:

[0050] Table 1

[0051]

[0052] S3: In the network management, the serial numbers of the terminals in each industry are extracted for matching so as to locate the fault and determine whether the faulty industry terminals are connected to the same base station, sector or cell;

[0053] S4: Calculate the comprehensive scores of each dimension, and classify the hidden dangers and fault levels of industry terminals according to the comprehensive scores through the indicator mapping model;

[0054] The comprehensive score of each dimension is the sum of the scores of the related items of each dimension. The higher the score, the greater the possibility of failure. The hidden danger failure levels of industry terminals include level I, level II, and level III.

[0055] When the fault level is level I or II, a maintenance order will be dispatched to check on-site whether the main equipment is abnormal, whether the indoor distribution system is damaged, whether the passive components are normal, whether there are any missing antenna points, etc.;

[0056] When the fault level is Level III, Level III will be included in the key observation list and the indicators will be tracked and extracted.

[0057] S5: Execute the corresponding fault handling plan according to the classified industry terminal hidden danger fault level;

[0058] In this embodiment, when the comprehensive scoring item is 1 point or more: the hidden danger fault level is level I, and maintenance personnel are required to verify and rectify on site as soon as possible to avoid affecting customer perception or on-site production. When the comprehensive scoring item is 0.7-1 point: the hidden danger fault level is level II, and maintenance personnel are required to conduct on-site inspection and rectification. When the comprehensive scoring item is 0.1-0.6 points: the hidden danger fault level is level III, and it needs to be included in the list to be observed for further observation.

[0059] S6: Through on-site verification, continuously iterate and improve the wireless network health assessment system and indicator mapping model;

[0060] Reference Figure 2 , the iteration and improvement method of the indicator mapping model is:

[0061] The iterative optimization of the indicator mapping model is abstracted as a convex optimization problem, and the stochastic gradient descent algorithm (SGD) is used to solve and calculate the convex optimization problem, as follows:

[0062] The input vector in the model is the background indicator phenomenon {X1, X2, X3, ...}, and the output vector is the actual problem verified on site {Y1, Y2, Y3, ...}. At the same time, let the prediction result of the model be the vector {A1, A2, A3, ...}. It can be seen that the purpose of the algorithm iteration is to make the prediction result A of the model close to the actual fault Y of the field network system;

[0063] Define the following root mean square error as the loss function (Cost Function):

[0064]

[0065] In the above formula, w and b are the sets of weights and biases respectively, ||·|| is the norm operation, and the purpose of iteration is to minimize C. Similar to other gradient descent examples, the direction with the fastest descent speed can be determined by the negative direction of the gradient of the convex function C. Through iterative calculation, the update formula of weights and biases can be obtained:

[0066]

[0067] Combined with the results of on-site verification and investigation, a set of weights and biases can be found to minimize the root mean square error, which makes the model more accurate.

[0068] This embodiment also provides a wireless network health assessment system suitable for an industry field network, the system comprising a network interface, a memory and a processor; wherein the network interface is used to receive and send signals during the process of sending and receiving information with other external network elements; the memory is used to store computer program instructions that can be run on the processor; the processor is used to execute the steps of the above-mentioned consensus method when running the computer program instructions.

[0069] The present embodiment also provides a computer storage medium, which stores a computer program, and the method described above can be implemented when the processor executes the computer program. The computer readable medium can be considered to be tangible and non-temporary. Non-limiting examples of non-temporary tangible computer-readable media include non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits or mask read-only memory circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital tapes or hard drives) and optical storage media (such as CDs, DVDs or Blu-ray discs), etc. The computer program includes processor executable instructions stored on at least one non-temporary tangible computer-readable medium. The computer program may also include or rely on stored data. The computer program may include a basic input / output system (BIOS) that interacts with the hardware of a special-purpose computer, a device driver that interacts with a specific device of a special-purpose computer, one or more operating systems, user applications, background services, background applications, etc.

[0070] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0071] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0072] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0073] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

Claims

1. A wireless network health assessment method suitable for an industry field network, characterized in that: The steps include: S1: Extract industry terminal-level indicator data; S2: Score the related items of each dimension in the indicator data according to the priority according to the indicator scoring table; S3: Matching is performed by extracting the terminal serial numbers of various industries in the network management; S4: Calculate the comprehensive scores of each dimension, and classify the hidden dangers and fault levels of industry terminals according to the comprehensive scores through the indicator mapping model; S5: Execute the corresponding fault handling plan according to the classified industry terminal hidden danger fault level; S6: Continuously iterate and improve the indicator mapping model through field verification; The iteration and improvement method of the indicator mapping model in step S6 is: The iterative optimization of the indicator mapping model is abstracted as a convex optimization problem, and the stochastic gradient descent algorithm is used to solve and calculate the convex optimization problem, as follows: The input vector in the model is the background indicator phenomenon {X1, X2, X3, ...}, and the output vector is the actual problem verified on site {Y1, Y2, Y3, ...}. At the same time, let the prediction result of the model be the vector {A1, A2, A3, ...}. It can be seen that the purpose of the algorithm iteration is to make the prediction result A of the model close to the actual fault Y of the field network system; Define the following root mean square error as the loss function: In the above formula, w and b are the sets of weights and biases respectively, ||·|| is the norm operation, and the purpose of iteration is to minimize C. The direction with the fastest descent speed is determined by the negative direction of the gradient of the convex function C, that is, the iteration direction that enables the established model to approach the true value as quickly as possible. Through iterative calculation, the update formula of weights and biases is obtained: Combined with the results of on-site verification and investigation, a set of weights and biases is found to minimize the root mean square error, that is, to make the model more accurate.

2. According to claim 1, a wireless network health assessment method suitable for an industry field network is characterized in that: The dimensions of the industry terminal-level indicator data in step S1 include traffic, coverage, connection indicator anomalies, and antenna feeder anomalies.

3. A wireless network health assessment method applicable to an industry field network according to claim 2, characterized in that: The associated items of the traffic include high traffic on the gateway and no traffic on the industry terminal, high traffic on the gateway and low traffic on the industry terminal, and unbalanced traffic on the industry terminal. The associated items of the coverage include unbalanced coverage, good overall coverage of the scene & local weak coverage. The associated items of the abnormal connection indicators include low RRC establishment success rate, low e-rab establishment success rate, and high e-rab drop rate. The associated items of the antenna feed abnormality include antenna channel interference, unbalanced multi-channel antenna interference, and abnormal standing wave ratio.

4. A wireless network health assessment method applicable to an industry field network according to claim 1, characterized in that: In step S1, the priorities are divided into high, medium and low.

5. A wireless network health assessment method applicable to an industry field network according to claim 1, characterized in that: The method for determining the priority of the associated items of each dimension in the step S1 is: performing priority determination according to the indicator threshold of each dimension.

6. A wireless network health assessment method applicable to an industry field network according to claim 1, characterized in that: The comprehensive score of each dimension in step S4 is the sum of the scores of the associated items of each dimension; the industry terminal hidden danger fault levels include level I, level II, and level III.

7. A wireless network health assessment method applicable to an industry field network according to claim 6, characterized in that: The specific fault handling solution in step S5 is: Level I fault handling plan: dispatch maintenance orders, and maintenance personnel will verify and rectify the faults on site as soon as possible; Level II fault handling plan: dispatch maintenance orders, and maintenance personnel conduct on-site inspections and rectify faults; Level III fault handling plan: Include in the key observation list and track the extraction indicators.

Images