A semi-automatic network planning auxiliary optimization method for mobile communication network and its application

By performing factor load matrix and correlation analysis on the historical data of the mobile communication system, weight coefficients are generated, which solves the problem of low timeliness of the performance evaluation of the mobile communication network, and realizes efficient and accurate network planning auxiliary evaluation.

CN114462810BActive Publication Date: 2024-11-05NAT UNIV OF DEFENSE TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210023005.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-10
Publication Date
2024-11-05
Estimated Expiration
2042-01-10

AI Technical Summary

Technical Problem

The performance evaluation method of the existing mobile communication network is low in timeliness and fails to effectively utilize historical data, resulting in high unilaterality of the evaluation results.

Method used

By obtaining the historical operation data of the mobile communication system, calculating the factor load matrix of the evaluation index data, determining the key factors and related evaluation indexes, conducting importance and correlation analysis, and generating weight coefficients to evaluate the effectiveness of the network planning scheme.

Benefits of technology

有效利用历史数据,简化评估指标,减少数据采集和计算量,提高评估的时效性和准确性,降低评估时间,提供高效的网络规划辅助参考。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114462810B_ABST
    Figure CN114462810B_ABST
Patent Text Reader

Abstract

The present application discloses a semi-automatic network planning auxiliary optimization method for a mobile communication network and its application, the method comprising: calculating a number of evaluation indicators corresponding to a mobile communication system network according to historical operation data; obtaining the importance coefficient of each evaluation indicator to all factors according to the factor load matrix corresponding to the evaluation indicator, and then calculating the first weight coefficient of the corresponding evaluation indicator data; determining a number of key factors, respectively calculating the correlation coefficients between the evaluation indicator data associated with the key factors, and selecting the evaluation indicators with correlation coefficients greater than a first specified threshold as key evaluation indicators; normalizing the weight coefficient of each key evaluation indicator data to obtain an updated second weight coefficient; obtaining simulated operation data of a network planning scheme, and generating an evaluation result of each network planning scheme according to the second weight coefficient and the simulated data; the present invention greatly reduces the amount of data collection and calculation, has high timeliness, and has high evaluation accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of communication network technology, and more specifically, to a semi-automatic network planning auxiliary optimization method and application for a mobile communication network. Background Art

[0002] The application mode of mobile communication network is closely related to the specific needs and application environment. Different needs and application environments will lead to different network structures and different service priorities. The network structure will also change according to different mission requirements, the number of participating units, terrain restrictions, the number of equipment and other conditions. Different network structures will also lead to different network planning parameters, such as network routing, access methods, subnet frequency distribution, encryption mechanism, key distribution method, etc. For example, in Figure 1 In the example, independent network 1 selects the broadcast protocol, independent network 2 selects the point-to-point protocol to form a chain network, and independent network n selects the Carrier Sense Multiple Access (CSMA) protocol to form a fully connected network. It can be seen that it would be very complicated to design and plan the network entirely relying on human efforts, and there is an urgent need for methods that can assist in completing the design of mobile communication networks based on user needs.

[0003] There are currently semi-automatic systems to support network solution design and plan different network structures for mobile communication networks. For this automatically planned network solution, network performance evaluation is also required. In the past, researchers have proposed a variety of methods for evaluating the effectiveness of mobile communication systems, most of which are based on simulation methods.

[0004] The Chinese patent "CN103178995 A systematic multi-scale communication network performance evaluation method" aims to solve the problem that communication network performance evaluation is difficult to be systematic, detailed and comprehensive. It proposes a comprehensive and systematic communication network performance evaluation indicator data system, covering communication transmission capability, access capability, information processing capability, security and confidentiality capability and other aspects. It can realize multi-scale performance evaluation of various organizations such as large and complex communication networks, single network systems, and equipment. However, this evaluation method starts more from the network structure and the capabilities it possesses, fails to effectively use historical data, and does not analyze the importance of different evaluation indicator data.

[0005] In the Chinese patent "CN111191918 A method and device for business routing planning of a smart grid communication network", a comprehensive risk assessment model is established by taking site load balancing, link load balancing and business average communication delay as indicators, and using the deep reinforcement learning method to find the optimal routing planning scheme with the comprehensive risk value as the reward value. Using deep reinforcement learning, the optimal routing planning scheme is found to minimize the comprehensive risk value of the system. This method focuses on converting the preset comprehensive risk assessment model into reward function information to obtain the optimal routing planning scheme, but the comprehensiveness of the selected indicators is questionable, and the comprehensiveness of the reward function is not deeply analyzed.

[0006] At present, there is no unified model for the performance evaluation of mobile communication networks. From the above patents, it can be seen that various evaluation methods consider the problem from different angles, but there is less in-depth analysis and research and use of historical data, which leads to a certain one-sidedness of the evaluation results. However, the collection and processing of historical data is the key link in using it for performance evaluation and requires in-depth research. In addition, the performance evaluation of mobile communication networks must not only consider accuracy, but also timeliness. On the premise of ensuring accuracy, minimizing the evaluation time has a strong practical significance for the flexible configuration of mobile communication networks. Summary of the invention

[0007] In response to at least one defect or improvement need in the prior art, the present invention provides a semi-automatic network planning auxiliary optimization method and application for a mobile communication network, aiming to solve the problem of low timeliness of the existing performance evaluation method of the mobile communication network.

[0008] To achieve the above object, according to a first aspect of the present invention, a method for semi-automatic network planning auxiliary optimization of a mobile communication network is provided, which comprises:

[0009] Acquire historical operation data of the mobile communication system network, and calculate a number of evaluation index data corresponding to the mobile communication system network according to the historical operation data and a preconfigured calculation model;

[0010] Calculate the factor load matrix corresponding to each evaluation index data, obtain the importance coefficient of each evaluation index data to all factors according to the factor load matrix, and calculate the first weight coefficient of the corresponding evaluation index data according to the importance coefficient;

[0011] Determine a number of key factors using factor analysis, calculate correlation coefficients between a number of evaluation indicator data associated with the key factors, and select evaluation indicator data with the correlation coefficient greater than a first specified threshold as key evaluation indicator data;

[0012] Normalizing the weight coefficient of each key evaluation indicator data according to the number of the key evaluation indicator data to obtain an updated second weight coefficient of each key evaluation indicator data;

[0013] Simulation data generated by simulating the network planning scheme to be evaluated is obtained, and an evaluation result of each network planning scheme is generated according to the second weight coefficient and the simulation data.

[0014] Preferably, in the above-mentioned semi-automatic network planning auxiliary optimization method for the mobile communication network, if the difference between the correlation coefficients of each evaluation index data is less than a preset value, the first weight coefficients of each evaluation index data are sorted, and the evaluation index data whose first weight coefficient is greater than the second specified threshold is selected as the key evaluation index data.

[0015] Preferably, the semi-automatic network planning auxiliary optimization method for the mobile communication network is characterized in that the importance coefficient of each evaluation index data to all factors is obtained according to the factor load matrix, which is:

[0016] The sum of the squares of the loadings of each evaluation index data on all factors is defined as the importance coefficient of the evaluation index data.

[0017] Preferably, the semi-automatic network planning auxiliary optimization method for the mobile communication network is characterized in that the weight coefficient of the corresponding evaluation index data is calculated according to the importance coefficient, which is:

[0018] The ratio of the importance coefficient of each evaluation index data to the sum of the importance coefficients of all evaluation index data is specified as the weight coefficient of the corresponding evaluation index data.

[0019] Preferably, the semi-automatic network planning auxiliary optimization method for a mobile communication network is characterized in that the evaluation result of each network planning scheme is generated according to the second weight coefficient and the simulation data, which is:

[0020] According to the second weight coefficient of each key evaluation indicator data and the simulation data, an evaluation score of each network planning solution is generated by weighted summation.

[0021] Preferably, the above-mentioned semi-automatic network planning auxiliary optimization method for mobile communication network is characterized by further comprising:

[0022] The actual data after the network planning scheme is run is obtained, and the actual data is used as the historical operation data to update the key evaluation indicator data and the corresponding second weight coefficient in real time.

[0023] Preferably, the above-mentioned semi-automatic network planning auxiliary optimization method for mobile communication network is characterized in that before calculating the factor load matrix corresponding to each evaluation index data, it also includes:

[0024] Each evaluation index data is assimilated and dimensionless processed to form standardized data.

[0025] According to a second aspect of the present invention, there is also provided a semi-automatic network planning auxiliary optimization device for a mobile communication network, which includes a decomposer and an analyzer; wherein the decomposer includes:

[0026] A data processing module, used to obtain historical operation data of the mobile communication system network, and respectively calculate a number of evaluation index data corresponding to the mobile communication system network according to the historical operation data and a pre-configured calculation model;

[0027] An importance analysis module, used to calculate the factor load matrix corresponding to each evaluation index data, obtain the importance coefficient of each evaluation index data to all factors according to the factor load matrix, and calculate the first weight coefficient of the corresponding evaluation index data according to the importance coefficient;

[0028] A correlation analysis module, used to determine a number of key factors by factor analysis, respectively calculate correlation coefficients between a number of evaluation index data associated with the key factors, and select evaluation index data with the correlation coefficient greater than a first specified threshold as key evaluation index data;

[0029] An updating module, used for normalizing the weight coefficient of each key evaluation indicator data according to the number of the key evaluation indicator data, to obtain a second weight coefficient after each key evaluation indicator data is updated;

[0030] The analyzer is used to simulate the network planning scheme to be evaluated to generate simulation data; and generate the evaluation result of each network planning scheme according to the simulation data and the second weight coefficient.

[0031] According to the third aspect of the present invention, there is also provided an electronic device, which comprises at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit executes the steps of any one of the above-mentioned methods.

[0032] According to a fourth aspect of the present invention, there is also provided a computer-readable medium storing a computer program executable by an electronic device, wherein when the computer program runs on the electronic device, the electronic device executes the steps of any one of the above methods.

[0033] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0034] The present invention effectively utilizes historical data, simplifies original evaluation indicators into a small number of key evaluation indicators through indicator importance analysis and correlation analysis, and evaluates the effectiveness of network planning schemes based on key evaluation indicators. Compared with traditional factor analysis methods, the present invention greatly reduces the amount of data collection and calculation, reduces the evaluation time, has high timeliness, and has high evaluation accuracy. It improves the timeliness of evaluation while ensuring accuracy, and can provide assistance and reference for the planning and design of semi-automatic network schemes for mobile communication networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 is a schematic diagram of the mobile communication network structure;

[0037] Figure 2 It is a flow chart of a method for semi-automatic network planning and auxiliary optimization of a mobile communication network provided in this embodiment;

[0038] Figure 3 It is a structural diagram of a semi-automatic network planning auxiliary optimization device for a mobile communication network provided in this embodiment;

[0039] Figure 4 It is a logic block diagram of the decomposer provided in this embodiment. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0041] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0042] In addition, in order to avoid obscuring the understanding of the present invention by the skilled person, well-known or widely used techniques, elements, structures and processes may not be described or shown in detail. Although the drawings represent exemplary embodiments of the present invention, the drawings are not necessarily drawn to scale, and certain features may be enlarged or omitted to better illustrate and explain the present invention.

[0043] Figure 2 FIG. 1 is a flow chart of a method for semi-automatic network planning and auxiliary optimization of a mobile communication network provided in this embodiment. Figure 2 As shown, the method mainly includes the following steps:

[0044] S1 obtains historical operation data of the mobile communication system network, and calculates several evaluation index data corresponding to the mobile communication system network according to the historical operation data and a preconfigured calculation model;

[0045] exist Figure 1 In the mobile communication system network shown, the network management device can be accessed at any node in the network. This architecture is similar to the MIML-IDPS system and can form a 3-layer or 2-layer management structure. The three-layer network management architecture includes a first-level network management center, multiple second-level network management centers, and third-level node devices. The first-level network management center is responsible for controlling all nodes in the network and dividing the network into different administrative areas, which are managed by the second-level network management center. The last layer of equipment is the backbone network node and the separation network access node. These nodes act as network management agents, which can control the network management device's instructions to specific devices and report the status of the equipment to the network management device. Network management nodes / devices at all levels collect various data generated in the actual operation of the network and store them in the historical database.

[0046] After collecting a large amount of historical operation data from the historical database, several evaluation index data corresponding to the mobile communication system network are calculated respectively according to the historical operation data and the pre-configured calculation model; in this embodiment, 8 representative indicators are selected to evaluate the system operation efficiency. The specific evaluation index data and definitions are shown in Table 1 below.

[0047] Table 1 Index name and definition

[0048]

[0049]

[0050] According to the evaluation index data of the mobile communication system, the calculation model of each index is defined respectively; and then the value of each evaluation index data is calculated according to the calculation model and the historical operation data.

[0051] In general evaluation methods, the larger the value of some evaluation index data, the better the effect. However, the larger the value of some evaluation index data, the worse the effectiveness. The closer some indicators are to the median, the better the effect, and the higher or lower than the median, the worse the effect. Therefore, before subsequent processing, the eight indicators need to be assimilated and dimensionless processed to form standardized data. Assimilation processing is also called forward processing. In this embodiment, each evaluation index data is first processed into an assimilation matrix, and then the Z-score method is used to perform dimensionless processing on the assimilation matrix data.

[0052] S2 calculates the factor load matrix corresponding to each evaluation index data, obtains the importance coefficient of each evaluation index data to all factors according to the factor load matrix, and calculates the first weight coefficient of the corresponding evaluation index data according to the importance coefficient;

[0053] In this embodiment, the factor analysis method is used to calculate the factor load matrix corresponding to each evaluation index data; first, by calculating the eigenvalue of the correlation coefficient matrix and the variance contribution rate of the factor, usually when the variance contribution rate of several factors is above 85%, the several factor components can be used as the main factors for factor analysis. According to the eigenvector corresponding to the selected factor, a non-rotated factor loading matrix is ​​generated. Factor loading is one of the important indicators of factor analysis and is the data source for factor naming. If a factor has a large load on most indicators, it means that the factor is an important comprehensive factor; but if some indicators have a large load on several factors, the factor cannot be directly explained. It is necessary to rotate the factor loading matrix so that the indicator can only show a large load on one factor and a small load on other factors. The maximum variance orthogonal rotation method can be used to rotate the data. After the rotated factor loading matrix, the specific indicators reflected by a factor can be analyzed to determine the specific meanings and characteristics represented by different factors. After that, the Bartlett factor score method is used to calculate the rotated factor score to generate the factor loading matrix.

[0054] After obtaining the factor load matrix, performing importance analysis on each evaluation index data according to the factor load matrix, specifically obtaining the importance coefficient of each evaluation index data to all factors according to the factor load matrix, and calculating the first weight coefficient of the corresponding evaluation index data according to the importance coefficient;

[0055] In an optional embodiment, the square sum of the loads of each evaluation index data on all factors is defined as the importance coefficient of the evaluation index data. The weight coefficient of the corresponding evaluation index data is calculated according to the importance coefficient: the ratio of the importance coefficient of each evaluation index data to the sum of the importance coefficients of all evaluation index data is defined as the weight coefficient of the corresponding evaluation index data.

[0056] The sum of squares of the loads of the i-th evaluation index data on all factors is defined as the commonality of the evaluation index, which reflects the impact of the evaluation index on all factors, that is, the importance of each original index. The expression is as follows:

[0057]

[0058] Among them, a ij Represents the load of the i-th evaluation indicator on the j-th factor, which comes from the factor loading matrix; m is the number of factors, and p is the number of evaluation indicators.

[0059] By comparing the commonalities of the evaluation indicators, we can see which indicator has a greater effect. Therefore, the commonalities of all evaluation indicators can be normalized into the weight of the evaluation indicator:

[0060]

[0061] Where W i represents the first weight coefficient of the i-th evaluation index, H i It represents the commonality of the i-th evaluation indicator, and p is the number of evaluation indicators. Through the above formula and factor loading matrix, the weight of each evaluation indicator can be calculated, and then the influence of the indicators with higher weight evaluation in different factors can be analyzed.

[0062] S3: using factor analysis to determine a number of key factors, respectively calculating correlation coefficients between a number of evaluation indicator data associated with the key factors, and selecting evaluation indicator data whose correlation coefficients are greater than a first specified threshold as key evaluation indicator data;

[0063] In order to ensure that there is no information overlap between the selected evaluation indicators, it is necessary to further screen the main indicators of each factor. In this embodiment, each evaluation indicator is subjected to correlation analysis. After several key factors are determined by the traditional factor analysis evaluation method, the evaluation indicators that determine the key factors are listed, and the correlation coefficients between the corresponding evaluation indicators of each factor are calculated for each factor. If the correlation between a certain evaluation indicator and other evaluation indicators is greater than the specified threshold, a correlation analysis is performed on these evaluation indicators. The overall idea is that if a certain evaluation indicator has a large correlation with other evaluation indicators and has a large impact on different key factors, the evaluation indicator is retained, otherwise the evaluation indicator is discarded; the retained evaluation indicator is the key evaluation indicator.

[0064] In an optional implementation, if the difference between the correlation coefficients of the evaluation index data is less than a preset value, the first weight coefficients of the evaluation index data are sorted, and the evaluation index data whose first weight coefficient is greater than the second specified threshold is selected as the key evaluation index data.

[0065] In actual operation, multiple indicators may have similar correlations and their impacts on factors tend to be the same, and the differences between them cannot be effectively distinguished. In this case, the evaluation indicators to be retained are determined by the analysis results of the above indicator importance. In this case, the evaluation indicators with large weights are retained, and those with small weights are discarded.

[0066] S4 normalizes the weight coefficient of each key evaluation indicator data according to the number of the key evaluation indicator data to obtain an updated second weight coefficient of each key evaluation indicator data;

[0067] Through the importance analysis of step S2 and the correlation analysis of step S3, the original evaluation index can be simplified into several key evaluation indexes, and the first weight coefficients of the retained key evaluation indexes are normalized to obtain the updated second weight coefficients; the formula is shown below.

[0068]

[0069] is the normalized second weight coefficient of the key evaluation index i, W i is the first weight coefficient of key evaluation indicator i, and k is the number of key evaluation indicators.

[0070] S5 obtains simulation data generated by simulating the network planning scheme to be evaluated, and generates an evaluation result of each network planning scheme according to the second weight coefficient and the simulation data.

[0071] In this embodiment, several network planning schemes generated by the network planning device are simulated to obtain simulated operation data. According to the method of step S1, the evaluation index data corresponding to the mobile communication system network are respectively calculated according to the simulated operation data and the preconfigured calculation model, and the evaluation index data are assimilated and dimensionless processed to obtain the evaluation index data in the standard data format; then, the evaluation result of each network planning scheme is generated according to the second weight coefficient obtained in step S4 and the evaluation index data corresponding to the simulated operation data; specifically, the evaluation score of each network planning scheme is generated by weighted summation according to the second weight coefficient of each key evaluation index data and the simulation data; the calculation formula is as follows:

[0072]

[0073] In the formula, The evaluation score for each network planning solution, Z ij is the normalized data (evaluation index data) of each network planning scheme, and n is the number of network planning schemes.

[0074] By calculating the evaluation scores of various network planning schemes and ranking them, the final ranking results of different network planning schemes can be obtained.

[0075] In the application of the example, it is shown that the simplified evaluation model provided by this embodiment and the traditional factor analysis evaluation model have basically the same ranking results in the performance evaluation of the network planning scheme, indicating that the evaluation conclusion of the simplified evaluation model provided by this embodiment is reliable.

[0076] Table 1 Evaluation results of simplified evaluation model and traditional factor analysis evaluation model

[0077]

[0078]

[0079] Table 1 shows the ranking results of 31 groups of network planning schemes evaluated by the traditional multi-index evaluation model and the simplified evaluation model provided in this embodiment. It can be found that among the 31 groups of network planning schemes, the rankings of 13 groups of network planning schemes have not changed, accounting for 41.9%; the rankings of 12 groups of network planning schemes have a difference of one rank, accounting for 38.7%; the rankings of 4 groups of network planning schemes have a difference of two rank, accounting for 12.9%; the rankings of 2 groups of network planning schemes have a difference of three rank, accounting for 0.06%, which shows that the simplified evaluation model provided in this embodiment is reliable.

[0080] In actual application, in the first stage, this scheme processes the original evaluation indicators based on historical operation data to generate a simplified evaluation model. In the second stage, the simplified evaluation model is used to evaluate the simulated operation data of the network planning scheme, which greatly reduces the workload of data recording, statistics and calculation, facilitates the implementation of the later evaluation, and has strong economic benefits.

[0081] This method can be applied to the semi-automatic network planning auxiliary optimization system of the mobile communication network. By using the historical data stored in the database, the latest simplified indicators and weights can be obtained. When the network planning is performed again, the network planning scheme generated by the network planning device is imported into the system, and the system simulates all network planning schemes. According to the simplified indicators, only a small amount of simulation data needs to be collected, and the effectiveness of each network planning scheme can be directly calculated according to the simplified evaluation model.

[0082] In a preferred embodiment, actual data after the network planning scheme is run is obtained, and the actual data is used as historical operation data to update the key evaluation index data and the corresponding second weight coefficient in real time. That is, after each network operation, the data is imported into the system through the network management device, and the key evaluation index and its corresponding weight are updated, so that the system is continuously updated, thereby obtaining faster and more accurate evaluation results.

[0083] In view of the shortcomings of traditional factor analysis, which requires a large amount of data to be collected and takes a long time to evaluate, the importance of different indicators is determined according to the characteristics of the network through the analysis of evaluation indicators, and the correlation analysis of the indicators involved in different factors in the factor analysis is carried out to lay the foundation for subsequent evaluation. This scheme effectively uses historical data. On the basis of traditional factor analysis, it simplifies the original evaluation indicators into a small number of key evaluation indicators through indicator importance analysis and correlation analysis, and evaluates the effectiveness of network planning schemes based on key evaluation indicators. Compared with traditional factor analysis, it greatly reduces the amount of data collection and calculation, reduces the evaluation time, and improves the timeliness of the evaluation while ensuring accuracy. It has strong practical significance for the flexible configuration of mobile communication networks.

[0084] It should be noted that although the operations of the methods of the embodiments of this specification are described in a specific order in the above-mentioned embodiments, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flowchart can change the order of execution. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.

[0085] This embodiment provides a device for semi-automatic network planning and auxiliary optimization of a mobile communication network. The device can be implemented in software and / or hardware and can be integrated on an electronic device. The device is connected to a network planning device and a network management device of a mobile communication system, such as Figure 3 As shown, multi-agent system technology is used to simulate and evaluate the network planning scheme generated by the network planning device, and finally a preferred sorting scheme of the network planning device is generated for users to flexibly choose according to their own usage needs.

[0086] See also Figure 3 , the device includes a decomposer, an analyzer and an observer; Figure 4 is a logic block diagram of the decomposer provided in this embodiment, such as Figure 4 As shown, the decomposer includes a data processing module, an importance analysis module, a correlation analysis module and an update module;

[0087] The data processing module is mainly used to obtain historical operation data of the mobile communication system network from the historical database, and calculate several evaluation index data corresponding to the mobile communication system network according to the historical operation data and the pre-configured calculation model;

[0088] The importance analysis module is used to calculate the factor load matrix corresponding to each evaluation index data, obtain the importance coefficient of each evaluation index data to all factors according to the factor load matrix, and calculate the first weight coefficient of the corresponding evaluation index data according to the importance coefficient;

[0089] The correlation analysis module is used to determine a number of key factors by using a factor analysis method, respectively calculate the correlation coefficients between a number of evaluation indicator data associated with the key factors, and select the evaluation indicator data whose correlation coefficient is greater than a first specified threshold as the key evaluation indicator data;

[0090] The updating module is used to normalize the weight coefficient of each key evaluation indicator data according to the number of the key evaluation indicator data to obtain the updated second weight coefficient of each key evaluation indicator data; and send the updated second weight coefficient to the analyzer.

[0091] The analyzer is used to simulate the network planning scheme to be evaluated and generate simulation data; generate the evaluation result of each network planning scheme according to the simulation data and the key evaluation indicator data determined by the decomposer and the second weight coefficient, and sort the schemes according to the preference strategy.

[0092] The main function of the observer is to obtain the network planning scheme from the network planning device and export it to the analyzer; in addition, the observer also receives the actual operation data of the actual operation process of the network imported from the network management device, and exports the operation data to the decomposer after simple preprocessing. The decomposer can update the key evaluation indicators and the corresponding weight coefficients according to the actual operation data.

[0093] For the specific definition of the semi-automatic network planning auxiliary optimization device for a mobile communication network, please refer to the definition of the semi-automatic network planning auxiliary optimization method for a mobile communication network mentioned above, which will not be repeated here. The various components in the above-mentioned semi-automatic network planning auxiliary optimization device for a mobile communication network can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0094] This embodiment also provides an electronic device, which includes at least one processor and at least one memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned mobile communication network semi-automatic network planning auxiliary optimization method; in this embodiment, the types of processor and memory are not specifically limited, for example: the processor can be a microprocessor, a digital information processor, a programmable logic system on a chip, etc.; the memory can be a volatile memory, a non-volatile memory, or a combination thereof, etc.

[0095] The electronic device may also communicate with one or more external devices (such as a keyboard, a pointing terminal, a display, etc.), may also communicate with one or more terminals that enable a user to interact with the electronic device, and / or communicate with any terminal (such as a network card, a modem, etc.) that enables the electronic device to communicate with one or more other computing terminals. Such communication may be performed through an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through a network adapter.

[0096] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0097] The present invention proposes a solution for rapid performance evaluation, which can quickly evaluate and analyze the performance of the network planning scheme of the mobile communication network. Under the premise of maintaining the accuracy of the evaluation, the evaluation index is reduced by 50%. The priority strategy algorithm can first ensure the priority items, and then delete other items with low relevance to increase the feasibility of the optimization results. Generally speaking, the evaluation method is fast and efficient, and the evaluation results are true and reliable, and can be used for semi-automatic network planning auxiliary equipment for mobile communication networks. In addition, the present invention can also be applied to the field of network planning evaluation of mobile communication systems. Different industries need to be deployed on demand and quickly established. By querying the stored network planning schemes of historical data, users can quickly select appropriate schemes according to their actual needs to facilitate, which greatly improves the efficiency of network planning. A prototype system can also be developed based on the present invention, combined with multi-agent simulation technology, and further combined with artificial intelligence methods, and the network scheme evaluation is applied to the early generation stage of the network planning scheme, while achieving fast and accurate network planning, it also improves efficiency.

[0098] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0099] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A semi-automatic network planning auxiliary optimization method for a mobile communication network, characterized in that: include: Acquire historical operation data of the mobile communication system network, and calculate a number of evaluation index data corresponding to the mobile communication system network according to the historical operation data and a preconfigured calculation model; Calculate the factor load matrix corresponding to each evaluation index data, obtain the importance coefficient of each evaluation index data to all factors according to the factor load matrix, and calculate the first weight coefficient of the corresponding evaluation index data according to the importance coefficient; Determine a number of key factors using factor analysis, calculate correlation coefficients between a number of evaluation indicator data associated with the key factors, and select evaluation indicator data with the correlation coefficient greater than a first specified threshold as key evaluation indicator data; Normalizing the weight coefficient of each key evaluation indicator data according to the number of the key evaluation indicator data to obtain an updated second weight coefficient of each key evaluation indicator data; Simulation data generated by simulating the network planning scheme to be evaluated is obtained, and an evaluation result of each network planning scheme is generated according to the second weight coefficient and the simulation data.

2. The semi-automatic network planning auxiliary optimization method of the mobile communication network according to claim 1, characterized in that: If the difference between the correlation coefficients of the evaluation index data is less than a preset value, the first weight coefficients of the evaluation index data are sorted, and the evaluation index data whose first weight coefficient is greater than the second specified threshold are selected as the key evaluation index data.

3. The semi-automatic network planning auxiliary optimization method of the mobile communication network according to claim 1, characterized in that: The importance coefficient of each evaluation index data to all factors is obtained according to the factor load matrix: The sum of squares of the loadings of each evaluation index data on all factors is defined as the importance coefficient of the evaluation index data.

4. The semi-automatic network planning auxiliary optimization method of the mobile communication network according to claim 2, characterized in that: The first weight coefficient of the corresponding evaluation index data is calculated according to the importance coefficient, which is: The ratio of the importance coefficient of each evaluation index data to the sum of the importance coefficients of all evaluation index data is defined as the first weight coefficient of the corresponding evaluation index data.

5. The semi-automatic network planning auxiliary optimization method of a mobile communication network according to claim 1 or 3, characterized in that: The evaluation result of each network planning scheme generated according to the second weight coefficient and the simulation data is: According to the second weight coefficient of each key evaluation indicator data and the simulation data, an evaluation score of each network planning solution is generated by weighted summation.

6. The semi-automatic network planning auxiliary optimization method of a mobile communication network according to claim 1 or 3, characterized in that: Also includes: The actual data after the network planning scheme is run is obtained, and the actual data is used as the historical operation data to update the key evaluation indicator data and the corresponding second weight coefficient in real time.

7. The semi-automatic network planning auxiliary optimization method of a mobile communication network according to claim 1 or 3, characterized in that: Before calculating the factor load matrix corresponding to each evaluation index data, the following steps are also included: Each evaluation index data is assimilated and dimensionless processed to form standardized data.

8. A semi-automatic network planning auxiliary optimization device for a mobile communication network, characterized in that: The invention comprises a decomposer and an analyzer; wherein the decomposer comprises: A data processing module, used for acquiring historical operation data of the mobile communication system network, and respectively calculating a number of evaluation index data corresponding to the mobile communication system network according to the historical operation data and a pre-configured calculation model; An importance analysis module, used to calculate the factor load matrix corresponding to each evaluation index data, obtain the importance coefficient of each evaluation index data to all factors according to the factor load matrix, and calculate the first weight coefficient of the corresponding evaluation index data according to the importance coefficient; A correlation analysis module, used to determine a number of key factors by factor analysis, respectively calculate correlation coefficients between a number of evaluation index data associated with the key factors, and select evaluation index data with the correlation coefficient greater than a first specified threshold as key evaluation index data; An updating module, used for normalizing the weight coefficient of each key evaluation indicator data according to the number of the key evaluation indicator data, to obtain a second weight coefficient after each key evaluation indicator data is updated; The analyzer is used to simulate the network planning scheme to be evaluated to generate simulation data; and generate the evaluation result of each network planning scheme according to the simulation data and the second weight coefficient.

9. An electronic device, characterized in that: The method comprises at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit executes the steps of the method according to any one of claims 1 to 7.

10. A computer-readable medium, characterized in that It stores a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the method according to any one of claims 1 to 7.