Adaptive evaluation method and device for intelligent grading of communication network, and storage medium

Abstract

The invention discloses a self-adaptive evaluation method and device for intelligent grading of a communication network and a storage medium, and relates to the technical field of communication. According to the specific implementation scheme, a hierarchical structure model of a target communication network is established, the weight of at least one object related to a decision target contained in each hierarchy in the hierarchical structure model is determined, and the hierarchical structure model comprises multiple hierarchies; constructing a fuzzy evaluation matrix based on evaluation of at least one target object contained in a target hierarchy in the hierarchical structure model by multiple experts, and determining a fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix; and determining a system efficiency evaluation result of the target communication network based on the weight of each target object about the decision target and the fuzzy evaluation value corresponding to each target object. Therefore, quantitative analysis is carried out aiming at the qualitative problem of the network intelligent capability, and the evaluation of the network intelligent capability grading can be quickly and efficiently completed while the uncertainty information is processed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and particularly relates to a self-adaptive evaluation method and device for intelligent classification of communication network and a storage medium. BACKGROUND

[0002] In recent years, the ICT (Information Communications Technology) industry is actively developing network intelligence research, but the intelligent classification and level verification work has little effect. In the related art, in the process of evaluating the intelligent classification of a communication network, artificial intervention must be supported in the decision-making and execution process of all levels, and the artificial auditing conclusion and execution instruction has the highest authority, which means that the artificial qualitative judgment is completely relied on, and has obvious limitations. SUMMARY

[0003] The present application provides a self-adaptive evaluation method and device for intelligent classification of communication network and a storage medium.

[0004] According to a first aspect of the present application, a self-adaptive evaluation method for intelligent classification of communication network is provided, which comprises:

[0005] establishing a hierarchical structure model of a target communication network and determining the weight of at least one object contained in each level of the hierarchical structure model with respect to a decision target, wherein the hierarchical structure model comprises a plurality of levels;

[0006] based on the evaluation of a plurality of experts on at least one target object contained in a target level of the hierarchical structure model, constructing a fuzzy evaluation matrix to determine the fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix;

[0007] based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object, determining the system performance evaluation result of the target communication network.

[0008] As a possible implementation manner, the method further comprises:

[0009] determining the classification result of the target communication network based on the weight of each target object with respect to the decision target.

[0010] As a possible implementation manner, the determining the classification result of the target communication network based on the weight of each target object with respect to the decision target comprises:

[0011] sorting each target object according to the weight of each target object with respect to the decision target, and determining the classification result of the target communication network based on the sorting result.

[0012] As a possible implementation manner, the determining the system performance evaluation result of the target communication network based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object comprises:

[0013] determining a performance contribution value of each target object to the target communication network based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object;

[0014] determining the system performance evaluation result of the target communication network based on the performance contribution value of each target object to the target communication network.

[0015] As a possible implementation manner, the determining the performance contribution value of each target object to the target communication network based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object comprises:

[0016] multiplying the weight of the target object with respect to the decision target and the fuzzy evaluation value corresponding to the target object to obtain a performance contribution fuzzy value of the target object to the target communication network;

[0017] determining the performance contribution value of the target object to the target communication network based on the performance contribution fuzzy value of the target object to the target communication network.

[0018] As a possible implementation manner, the fuzzy evaluation value corresponding to the target object is a triangular fuzzy evaluation value, the triangular fuzzy evaluation value is composed of three first parameters, the three first parameters comprise a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value, and correspondingly, the performance contribution fuzzy value of the target object to the target communication network is a performance contribution triangular fuzzy value, the performance contribution triangular fuzzy value is composed of three second parameters, the three second parameters comprise a first performance contribution triangular fuzzy value, a second performance contribution triangular fuzzy value and a third performance contribution triangular fuzzy value;

[0019] The multiplying the weight of the target object with respect to the decision target and the fuzzy evaluation value corresponding to the target object to obtain a performance contribution fuzzy value of the target object to the target communication network comprises:

[0020] multiplying the weight of the target object with respect to the decision target and the first fuzzy evaluation value, the second fuzzy evaluation value and the third fuzzy evaluation value corresponding to the target object respectively to obtain a first performance contribution triangular fuzzy value, a second performance contribution triangular fuzzy value and a third performance contribution triangular fuzzy value of the target object to the target communication network.

[0021] As a possible implementation manner, the determining the performance contribution value of the target object to the target communication network based on the performance contribution fuzzy value of the target object to the target communication network comprises:

[0022] determining a sum of the first performance contribution triangular fuzzy value, the second performance contribution triangular fuzzy value multiplied by the set multiple and the third performance contribution triangular fuzzy value as a performance contribution intermediate value;

[0023] determining a ratio between the performance contribution intermediate value and the first set numerical value as the performance contribution value of the target object to the target communication network.

[0024] As a possible implementation manner, the determining the system performance evaluation result of the target communication network based on the performance contribution values of the target objects to the target communication network comprises:

[0025] determining a sum of the performance contribution values of the target objects to the target communication network as the system performance evaluation result of the target communication network.

[0026] As a possible implementation manner, the constructing the fuzzy evaluation matrix based on the evaluations of the experts on at least one target object contained in a target level in the hierarchical model, and determining the fuzzy evaluation values corresponding to the target objects based on the fuzzy evaluation matrix comprises:

[0027] converting the evaluations of the experts on at least one target object contained in a target level in the hierarchical model into corresponding fuzzy decision numbers based on a preset corresponding relationship between evaluations and fuzzy decision numbers;

[0028] constructing the fuzzy evaluation matrix based on the fuzzy decision numbers, wherein any row or column in the fuzzy evaluation matrix is composed of fuzzy decision numbers corresponding to the evaluations of the experts on any target object;

[0029] determining the fuzzy evaluation values corresponding to the target objects based on any row or column in the fuzzy evaluation matrix.

[0030] As a possible implementation manner, the determining the fuzzy evaluation values corresponding to the target objects based on any row or column in the fuzzy evaluation matrix comprises:

[0031] determining a ratio between a sum of the fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the fuzzy evaluation value corresponding to the target object.

[0032] As a possible implementation manner, the fuzzy decision number is a triangular fuzzy decision number, the triangular fuzzy decision number is composed of three third parameters, the three third parameters include a first fuzzy decision number, a second fuzzy decision number and a third fuzzy decision number, and correspondingly, the fuzzy evaluation value is a triangular fuzzy evaluation value, the triangular fuzzy evaluation value is composed of three first parameters, the three first parameters include a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value.

[0033] The ratio between the sum of the fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts is determined as the fuzzy evaluation value corresponding to the corresponding target object.

[0034] The ratio between the sum of the first fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts is determined as the first fuzzy evaluation value corresponding to the corresponding target object.

[0035] The ratio between the sum of the second fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts is determined as the second fuzzy evaluation value corresponding to the corresponding target object.

[0036] The ratio between the sum of the third fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts is determined as the third fuzzy evaluation value corresponding to the corresponding target object.

[0037] As a possible implementation manner, the establishing a hierarchical structure model of the target communication network and determining the weight of at least one object contained in each level of the hierarchical structure model with respect to the decision target comprises:

[0038] The hierarchical structure model of the target communication network is established and the weight of at least one object contained in each level of the hierarchical structure model with respect to the decision target is determined by using the analytic hierarchy process.

[0039] As a possible implementation manner, the weight of the object contained in the highest level of the hierarchical structure model with respect to the decision target is a second set value.

[0040] The hierarchical structure model of the target communication network is established and the weight of at least one object contained in each level of the hierarchical structure model with respect to the decision target is determined by using the analytic hierarchy process.

[0041] The hierarchical structure model of the target communication network is established based on the mutual relationship among the decision target, the decision criterion and the decision scheme.

[0042] constructing at least one judgment matrix corresponding to each of the levels based on the relative importance of any two objects in each of the levels other than the highest level to any object in the upper level;

[0043] performing consistency check on each of the judgment matrices, and determining the weight of at least one object included in each of the levels other than the highest level with respect to the decision target based on each of the judgment matrices if the consistency check on each of the judgment matrices is passed.

[0044] As a possible implementation, the method further comprises:

[0045] reconstructing the judgment matrix if the consistency check on any of the judgment matrices is not passed.

[0046] As a possible implementation, the constructing at least one judgment matrix corresponding to each of the levels based on the relative importance of any two objects in each of the levels other than the highest level to any object in the upper level comprises:

[0047] converting the relative importance of any two objects in each of the levels other than the highest level to any object in the upper level into corresponding scale values based on a preset scale mode of elements of the judgment matrix;

[0048] constructing at least one judgment matrix corresponding to each of the levels based on the scale values, wherein any row or column in any of the judgment matrices is composed of the relative importance of any object in the corresponding level to any object in the upper level compared with all objects in the level.

[0049] As a possible implementation, the performing consistency check on each of the judgment matrices, and determining the weight of at least one object included in each of the levels other than the highest level with respect to the decision target based on each of the judgment matrices if the consistency check on each of the judgment matrices is passed comprises:

[0050] determining a consistency index corresponding to any of the judgment matrices based on the largest eigenvalue corresponding to the judgment matrix and the order of the judgment matrix;

[0051] determining an average consistency index corresponding to the judgment matrix based on the order of the judgment matrix according to a preset correspondence between the order and the average consistency index;

[0052] determining a consistency check coefficient corresponding to the judgment matrix based on the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix, so as to determine that the consistency check of the judgment matrix is passed in a case where the consistency check coefficient is less than a third set value;

[0053] in a case where the consistency check of each of the judgment matrices is passed, determining a weight matrix corresponding to a corresponding level based on a feature vector corresponding to a target judgment matrix, wherein the target judgment matrix is at least one judgment matrix corresponding to any of the levels in the hierarchical structure model except the highest level;

[0054] determining the weight of at least one object included in each of the levels in the hierarchical structure model except the highest level with respect to the decision target based on the weight matrix corresponding to each of the levels.

[0055] As a possible implementation manner, the determining of the consistency index corresponding to the judgment matrix based on the maximum eigenvalue corresponding to the judgment matrix and the order of the judgment matrix comprises:

[0056] determining a first intermediate value as a difference between the maximum eigenvalue corresponding to the judgment matrix and the order of the judgment matrix;

[0057] determining a second intermediate value as a difference between the order of the judgment matrix and a fourth set value;

[0058] determining a ratio between the first intermediate value and the second intermediate value as the consistency index corresponding to the judgment matrix.

[0059] As a possible implementation manner, the determining of the consistency check coefficient corresponding to the judgment matrix based on the consistency index corresponding to the judgment matrix and the average consistency index comprises:

[0060] determining a ratio between the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix as the consistency check coefficient corresponding to the judgment matrix.

[0061] As a possible implementation manner, the determining of the weight of at least one object included in each of the levels in the hierarchical structure model except the highest level with respect to the decision target based on the weight matrix corresponding to each of the levels comprises:

[0062] For any of the levels, if there is at least one upper level of the non-highest level for the level, multiplying the weight matrix corresponding to the level with the weight matrix corresponding to each of the upper level of the non-highest level to obtain a target weight matrix corresponding to the level, or if there is no at least one upper level of the non-highest level for the level, determining the weight matrix corresponding to the level as the target weight matrix corresponding to the level, wherein the target weight matrix is composed of the weight of at least one object included in the corresponding level with respect to the decision target;

[0063] Based on the target weight matrix corresponding to each of the levels, the weight of at least one object included in each of the levels with respect to the decision target is determined.

[0064] According to a second aspect of the present application, an adaptive evaluation device for intelligent classification of a communication network is provided, comprising a memory, a transceiver, and a processor:

[0065] The memory is configured to store a computer program; the transceiver is configured to transceive data under the control of the processor; and the processor is configured to read the computer program in the memory and perform the following operations:

[0066] establishing a hierarchical model of a target communication network and determining the weight of at least one object included in each level of the hierarchical model with respect to a decision target, wherein the hierarchical model comprises a plurality of levels;

[0067] Based on the evaluation of a plurality of experts on at least one target object included in a target level of the hierarchical model, a fuzzy evaluation matrix is constructed to determine the fuzzy evaluation value corresponding to each of the target objects based on the fuzzy evaluation matrix;

[0068] Based on the weight of each of the target objects with respect to the decision target and the fuzzy evaluation value corresponding to each of the target objects, a system performance evaluation result of the target communication network is determined.

[0069] As a possible implementation manner, the processor is further configured to perform the following operation:

[0070] Based on the weight of each of the target objects with respect to the decision target, a classification result of the target communication network is determined.

[0071] As a possible implementation manner, the processor is further configured to perform the following operation:

[0072] Each of the target objects is sorted according to the weight of each of the target objects with respect to the decision target, and based on the sorting result, a classification result of the target communication network is determined.

[0073] As a possible implementation manner, the processor is further configured to perform the following operation:

[0074] Based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object, a contribution value of each target object to the performance of the target communication network is determined.

[0075] Based on the contribution value of each target object to the performance of the target communication network, a system performance evaluation result of the target communication network is determined.

[0076] As a possible implementation manner, the processor is further configured to perform the following operation:

[0077] For any target object, the weight of the target object with respect to the decision target is multiplied by the fuzzy evaluation value corresponding to the target object to obtain a contribution fuzzy value of the target object to the performance of the target communication network.

[0078] Based on the contribution fuzzy value of the target object to the performance of the target communication network, a contribution value of the target object to the performance of the target communication network is determined.

[0079] As a possible implementation manner, the fuzzy evaluation value corresponding to the target object is a triangular fuzzy evaluation value composed of three first parameters, the three first parameters including a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value, and correspondingly, the contribution fuzzy value of the target object to the performance of the target communication network is a contribution triangular fuzzy value composed of three second parameters, the three second parameters including a first contribution triangular fuzzy value, a second contribution triangular fuzzy value and a third contribution triangular fuzzy value.

[0080] The processor is further configured to perform the following operation:

[0081] The weight of the target object with respect to the decision target is multiplied by the first fuzzy evaluation value, the second fuzzy evaluation value and the third fuzzy evaluation value corresponding to the target object respectively to obtain a first contribution triangular fuzzy value, a second contribution triangular fuzzy value and a third contribution triangular fuzzy value of the target object to the performance of the target communication network.

[0082] As a possible implementation manner, the processor is further configured to perform the following operation:

[0083] A sum of the first contribution triangular fuzzy value, a set multiple of the second contribution triangular fuzzy value and the third contribution triangular fuzzy value is determined as a contribution intermediate value.

[0084] A ratio between the performance contribution intermediate value and a first set value is determined as the performance contribution value of the target object to the target communication network.

[0085] As a possible implementation, the processor is further configured to perform the following operation:

[0086] A sum of the performance contribution values of the target objects to the target communication network is determined as a system performance evaluation result of the target communication network.

[0087] As a possible implementation, the processor is further configured to perform the following operation:

[0088] Based on a preset correspondence between evaluation and fuzzy decision numbers, the evaluation of each expert on at least one target object contained in a target level in the hierarchical structure model is converted into a corresponding fuzzy decision number;

[0089] Based on the fuzzy decision numbers, a fuzzy evaluation matrix is constructed, wherein any row or column in the fuzzy evaluation matrix is composed of the fuzzy decision numbers corresponding to the evaluation of any target object by each expert;

[0090] Based on any row or column in the fuzzy evaluation matrix, a fuzzy evaluation value corresponding to a target object is determined.

[0091] As a possible implementation, the processor is further configured to perform the following operation:

[0092] A ratio between a sum of the fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts is determined as the fuzzy evaluation value corresponding to the target object.

[0093] As a possible implementation, the fuzzy decision number is a triangular fuzzy decision number composed of three third parameters, including a first fuzzy decision number, a second fuzzy decision number and a third fuzzy decision number, and correspondingly, the fuzzy evaluation value is a triangular fuzzy evaluation value composed of three first parameters, including a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value.

[0094] The processor is further configured to perform the following operation:

[0095] A ratio between a sum of the first fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts is determined as a first fuzzy evaluation value corresponding to the target object;

[0096] A ratio between a sum of the second fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts is determined as a second fuzzy evaluation value corresponding to the target object.

[0097] A ratio between the sum of the third fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts is determined as a third fuzzy evaluation value corresponding to the target object.

[0098] As a possible implementation manner, the processor is further configured to perform the following operation:

[0099] An analytic hierarchy process is adopted to establish a hierarchical structure model of the target communication network and determine a weight of at least one object contained in each hierarchy in the hierarchical structure model with respect to a decision target.

[0100] As a possible implementation manner, the weight of the object contained in the highest hierarchy in the hierarchical structure model with respect to the decision target is a second set value;

[0101] The processor is further configured to perform the following operation:

[0102] Based on the interrelations among the decision target, the decision criteria and the decision scheme, a hierarchical structure model of the target communication network is established;

[0103] Based on the relative importance of any two objects in each hierarchy in the hierarchical structure model except the highest hierarchy with respect to any object in the previous hierarchy, at least one judgment matrix corresponding to each hierarchy is constructed;

[0104] Consistency check is performed on each judgment matrix, so that in a case where the consistency check of each judgment matrix is passed, weights of at least one object contained in each hierarchy in the hierarchical structure model except the highest hierarchy with respect to the decision target are determined based on each judgment matrix.

[0105] As a possible implementation manner, the processor is further configured to perform the following operation:

[0106] In a case where the consistency check of any judgment matrix is not passed, the judgment matrix is reconstructed.

[0107] As a possible implementation manner, the processor is further configured to perform the following operation:

[0108] Based on a preset element scale mode of the judgment matrix, the relative importance of any two objects in each hierarchy in the hierarchical structure model except the highest hierarchy with respect to any object in the previous hierarchy is converted into a corresponding scale value;

[0109] Based on each scale value, at least one judgment matrix corresponding to each hierarchy is constructed, wherein any row or column in any judgment matrix is composed of the relative importance of any object in the corresponding hierarchy with respect to any object in the previous hierarchy compared with all objects in the current hierarchy.

[0110] As a possible implementation manner, the processor is further configured to perform the following operation:

[0111] For any judgment matrix, a consistency index corresponding to the judgment matrix is determined based on a maximum eigenvalue corresponding to the judgment matrix and an order of the judgment matrix;

[0112] According to a preset correspondence between orders and average consistency indexes, an average consistency index corresponding to the judgment matrix is determined based on the order of the judgment matrix;

[0113] A consistency check coefficient corresponding to the judgment matrix is determined based on the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix, so that the judgment matrix passes the consistency check in a case where the consistency check coefficient is less than a third preset value;

[0114] In a case where the consistency check of each judgment matrix passes, a weight matrix corresponding to a corresponding level is determined based on an eigenvector corresponding to a target judgment matrix, wherein the target judgment matrix is at least one judgment matrix corresponding to any level in the hierarchical structure model except a highest level;

[0115] Based on the weight matrix corresponding to each level, a weight of at least one object included in each level in the hierarchical structure model except the highest level with respect to a decision target is determined.

[0116] As a possible implementation manner, the processor is further configured to perform the following operation:

[0117] A difference between the maximum eigenvalue corresponding to the judgment matrix and the order of the judgment matrix is determined as a first intermediate value;

[0118] A difference between the order of the judgment matrix and a fourth preset value is determined as a second intermediate value;

[0119] A ratio between the first intermediate value and the second intermediate value is determined as the consistency index corresponding to the judgment matrix.

[0120] As a possible implementation manner, the processor is further configured to perform the following operation:

[0121] A ratio between the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix is determined as the consistency check coefficient corresponding to the judgment matrix.

[0122] As a possible implementation manner, the processor is further configured to perform the following operation:

[0123] For any of the levels, if there is at least one upper level of the non-highest level for the level, multiplying the weight matrix corresponding to the level with the weight matrix corresponding to each of the upper level of the non-highest level to obtain a target weight matrix corresponding to the level, or if there is no at least one upper level of the non-highest level for the level, determining the weight matrix corresponding to the level as the target weight matrix corresponding to the level, wherein the target weight matrix is composed of the weight of at least one object included in the corresponding level with respect to the decision target;

[0124] Based on the target weight matrix corresponding to each of the levels, the weight of at least one object included in each of the levels with respect to the decision target is determined.

[0125] According to a third aspect of the present application, an adaptive evaluation device for intelligent hierarchical communication network is provided, which comprises:

[0126] A first processing unit is configured to establish a hierarchical structure model of a target communication network and determine the weight of at least one object included in each level of the hierarchical structure model with respect to a decision target, wherein the hierarchical structure model comprises a plurality of levels;

[0127] A second processing unit is configured to construct a fuzzy evaluation matrix based on the evaluation of a plurality of experts on at least one target object included in a target level of the hierarchical structure model, and determine a fuzzy evaluation value corresponding to each of the target objects based on the fuzzy evaluation matrix;

[0128] A first determining unit is configured to determine the system performance evaluation result of the target communication network based on the weight of each of the target objects with respect to the decision target and the fuzzy evaluation value corresponding to each of the target objects.

[0129] As a possible implementation manner, the device further comprises:

[0130] A second determining unit is configured to determine the hierarchical result of the target communication network based on the weight of each of the target objects with respect to the decision target.

[0131] As a possible implementation manner, the second determining unit is further configured to:

[0132] Sort each of the target objects according to the weight of each of the target objects with respect to the decision target, and determine the hierarchical result of the target communication network based on the sorting result.

[0133] As a possible implementation manner, the first determining unit further comprises:

[0134] The first determining module is configured to determine, based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object, a contribution value of each target object to the performance of the target communication network.

[0135] The second determining module is configured to determine, based on the contribution value of each target object to the performance of the target communication network, a system performance evaluation result of the target communication network.

[0136] As a possible implementation, the first determining module is further configured to:

[0137] For any target object, the weight of the target object with respect to the decision target is multiplied by the fuzzy evaluation value corresponding to the target object to obtain a contribution fuzzy value of the target object to the performance of the target communication network.

[0138] Based on the contribution fuzzy value of the target object to the performance of the target communication network, a contribution value of the target object to the performance of the target communication network is determined.

[0139] As a possible implementation, the fuzzy evaluation value corresponding to the target object is a triangular fuzzy evaluation value composed of three first parameters, including a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value, and correspondingly, the contribution fuzzy value of the target object to the performance of the target communication network is a contribution triangular fuzzy value composed of three second parameters, including a first contribution triangular fuzzy value, a second contribution triangular fuzzy value and a third contribution triangular fuzzy value.

[0140] The first determining module is further configured to:

[0141] The weight of the target object with respect to the decision target is multiplied by the first fuzzy evaluation value, the second fuzzy evaluation value and the third fuzzy evaluation value corresponding to the target object respectively to obtain a first contribution triangular fuzzy value, a second contribution triangular fuzzy value and a third contribution triangular fuzzy value of the target object to the performance of the target communication network.

[0142] As a possible implementation, the first determining module is further configured to:

[0143] The sum of the first contribution triangular fuzzy value, the second contribution triangular fuzzy value multiplied by a set multiple and the third contribution triangular fuzzy value is determined as a contribution intermediate value.

[0144] The ratio between the contribution intermediate value and a first set value is determined as the contribution value of the target object to the performance of the target communication network.

[0145] As a possible implementation manner, the second determining module is further configured to:

[0146] determine a sum of the performance contribution values of the target objects to the target communication network as a system performance evaluation result of the target communication network.

[0147] As a possible implementation manner, the second processing unit further comprises:

[0148] a converting module configured to convert the evaluation of each of the experts on at least one target object contained in a target level in the hierarchical structure model into a corresponding fuzzy decision number based on a preset corresponding relationship between the evaluation and the fuzzy decision number;

[0149] a first constructing module configured to construct a fuzzy evaluation matrix based on the fuzzy decision numbers, wherein any row or column in the fuzzy evaluation matrix is composed of the fuzzy decision numbers corresponding to the evaluation of any target object by each of the experts;

[0150] a third determining module configured to determine a fuzzy evaluation value corresponding to a corresponding target object based on any row or column in the fuzzy evaluation matrix.

[0151] As a possible implementation manner, the third determining module is further configured to:

[0152] determine a ratio between a sum of the fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the fuzzy evaluation value corresponding to the corresponding target object.

[0153] As a possible implementation manner, the fuzzy decision number is a triangular fuzzy decision number composed of three third parameters, the three third parameters comprising a first fuzzy decision number, a second fuzzy decision number and a third fuzzy decision number, and correspondingly, the fuzzy evaluation value is a triangular fuzzy evaluation value composed of three first parameters, the three first parameters comprising a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value.

[0154] The third determining module is further configured to:

[0155] determine a ratio between a sum of the first fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the first fuzzy evaluation value corresponding to the corresponding target object;

[0156] determine a ratio between a sum of the second fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the second fuzzy evaluation value corresponding to the corresponding target object.

[0157] A ratio between the sum of the third fuzzy decision numbers in any row or column of the fuzzy evaluation matrix and the number of experts is determined as a third fuzzy evaluation value corresponding to the target object.

[0158] As a possible implementation, the first processing unit is further configured to:

[0159] An analytic hierarchy process is adopted to establish a hierarchical structure model of the target communication network and determine a weight of at least one object included in each hierarchy of the hierarchical structure model with respect to the decision target.

[0160] As a possible implementation, the weight of the object included in the highest hierarchy of the hierarchical structure model with respect to the decision target is a second set value.

[0161] The first processing unit further includes:

[0162] The establishing module is configured to establish a hierarchical structure model of the target communication network based on the mutual relationship among the decision target, the decision criteria and the decision scheme.

[0163] The second constructing module is configured to construct at least one judgment matrix corresponding to each hierarchy based on the relative importance of any two objects in each hierarchy of the hierarchical structure model except the highest hierarchy with respect to any object in the previous hierarchy.

[0164] The processing module is configured to perform consistency check on each judgment matrix, and determine the weight of at least one object included in each hierarchy of the hierarchical structure model except the highest hierarchy with respect to the decision target based on each judgment matrix, in a case where the consistency check on each judgment matrix is passed.

[0165] As a possible implementation, the apparatus further includes:

[0166] The reconstructing unit is configured to reconstruct the judgment matrix in a case where the consistency check on any judgment matrix is not passed.

[0167] As a possible implementation, the second constructing module is further configured to:

[0168] The relative importance of any two objects in each hierarchy of the hierarchical structure model except the highest hierarchy with respect to any object in the previous hierarchy is converted into a corresponding scale value based on a preset element scale mode of the judgment matrix.

[0169] At least one judgment matrix corresponding to each hierarchy is constructed based on each scale value, wherein any row or column in any judgment matrix is composed of the relative importance of any object in the corresponding hierarchy with respect to any object in the previous hierarchy compared with all objects in the current hierarchy.

[0170] As a possible implementation manner, the processing module is further configured to:

[0171] For any judgment matrix, determine a consistency index corresponding to the judgment matrix based on a maximum eigenvalue corresponding to the judgment matrix and an order of the judgment matrix;

[0172] According to a preset correspondence between orders and average consistency indexes, determine an average consistency index corresponding to the judgment matrix based on the order of the judgment matrix;

[0173] Determine a consistency check coefficient corresponding to the judgment matrix based on the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix, so as to determine that the judgment matrix passes the consistency check in a case where the consistency check coefficient is less than a third preset value;

[0174] In a case where the consistency checks of all the judgment matrices pass, determine a weight matrix corresponding to a corresponding level based on an eigenvector corresponding to a target judgment matrix, wherein the target judgment matrix is at least one judgment matrix corresponding to any level in the hierarchical structure model except a highest level;

[0175] Determine a weight of at least one object included in each of the levels with respect to a decision target based on the weight matrix corresponding to each of the levels.

[0176] As a possible implementation manner, the processing module is further configured to:

[0177] Determine a difference between the maximum eigenvalue corresponding to the judgment matrix and the order of the judgment matrix as a first intermediate value;

[0178] Determine a difference between the order of the judgment matrix and a fourth preset value as a second intermediate value;

[0179] Determine a ratio between the first intermediate value and the second intermediate value as the consistency index corresponding to the judgment matrix.

[0180] As a possible implementation manner, the processing module is further configured to:

[0181] Determine a ratio between the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix as the consistency check coefficient corresponding to the judgment matrix.

[0182] As a possible implementation manner, the processing module is further configured to:

[0183] for any of the levels, if there is at least one upper level of the non-highest level for the level, multiplying the weight matrix corresponding to the level with the weight matrix corresponding to each of the upper level of the non-highest level to obtain a target weight matrix corresponding to the level, or if there is no at least one upper level of the non-highest level for the level, determining the weight matrix corresponding to the level as the target weight matrix corresponding to the level, wherein the target weight matrix is composed of the weight of at least one object included in the corresponding level with respect to the decision target;

[0184] Based on the target weight matrix corresponding to each of the levels, the weight of at least one object included in each of the levels with respect to the decision target is determined.

[0185] According to a fourth aspect of the present application, a processor-readable storage medium is provided, which stores a computer program for causing the processor to execute any of the methods according to the first aspect of the present application.

[0186] According to a fifth aspect of the present application, a computer program product is provided, which comprises a computer program for implementing any of the methods according to the first aspect of the present application when executed by a processor.

[0187] According to the communication network intelligent hierarchical adaptive evaluation method, device and storage medium provided by the present application, the hierarchical structure model of the target communication network is established, and the weight of at least one object included in each level of the hierarchical structure model with respect to the decision target is determined, wherein the hierarchical structure model comprises a plurality of levels, so as to construct a fuzzy evaluation matrix based on the evaluation of the plurality of experts on at least one target object included in the target level of the hierarchical structure model, determine the fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix, and then determine the system performance evaluation result of the target communication network based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object. Thus, by implementing quantitative analysis on the network intelligent capability qualitative problem, the evaluation of the network intelligent capability hierarchy can be quickly and efficiently completed while dealing with uncertain information.

[0188] It should be understood that the contents described in this part are not intended to identify the key or important features of the embodiments of the present application, nor are they used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0189] The accompanying drawings are used to better understand the present application, and do not limit the present application. Among them:

[0190] Figure 1 is a schematic diagram of a communication network intelligent capability hierarchical evaluation method in the related art;

[0191] Figure 2 is a flowchart of a method for adaptive evaluation of intelligent classification of a communication network according to a first embodiment of the present application;

[0192] Figure 3 is a schematic diagram of a hierarchical structure model of a target communication network according to a second embodiment of the present application;

[0193] Figure 4 is a flowchart of a method for adaptive evaluation of intelligent classification of a communication network according to a third embodiment of the present application;

[0194] Figure 5 is a flowchart of a method for determining a system performance evaluation result according to a fourth embodiment of the present application;

[0195] Figure 6 is a flowchart of a method for determining a fuzzy evaluation value according to a fifth embodiment of the present application;

[0196] Figure 7 is a flowchart of a method for establishing a hierarchical structure model and determining a weight according to a sixth embodiment of the present application;

[0197] Figure 8 is a flowchart of a method for adaptive evaluation of intelligent classification of a communication network according to a seventh embodiment of the present application;

[0198] Figure 9 is a structural diagram of an adaptive evaluation device for intelligent classification of a communication network according to an eighth embodiment of the present application;

[0199] Figure 10 is a structural diagram of an adaptive evaluation device for intelligent classification of a communication network according to a ninth embodiment of the present application. DETAILED DESCRIPTION

[0200] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after it.

[0201] In the embodiments of the present application, the term "a plurality of" means two or more, and other quantifiers are similar.

[0202] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work are within the protection scope of the present application.

[0203] Although artificial intelligence technology has achieved single-point breakthrough and application in local scenarios and local fields in communication networks, there is a lack of unified description language and system evolution ideas. Researching and formulating a communication network intelligent capability grading method commonly recognized by the industry can provide evaluation basis for the industry to measure the intelligent capability level of communication networks (and their components), and promote the formation of a unified understanding and understanding of intelligent networks and related concepts in the industry.

[0204] In order to provide evaluation standards for measuring the intelligent level of wireless communication networks for the industry, and guide relevant enterprises to clarify the development stage and target of network intelligence, a wireless communication network intelligence grading standard is proposed. The wireless communication network intelligence grading standard is based on network implementation process and scene capability, and divides the network into six levels L0-L5 as shown in Figure 1 from five grading evaluation dimensions of execution, perception, analysis, decision-making, and demand mapping. At the L0 level, the specific demand mapping, data collection and analysis, judgment and decision execution of the network completely rely on manual operation; from the L1 level to the L4 level, the network intelligence capability gradually improves, and can realize the intelligence of part of the scene and dimension; at the L5 level, the intelligent closed loop of the complete process is realized. However, the decision and execution process of all the above levels must support manual intervention, and manual review of the conclusion and execution instruction has the highest authority, which means that completely relying on manual qualitative judgment has obvious limitations.

[0205] Therefore, the present application proposes a self-adaptive evaluation method, device and storage medium for communication network intelligence grading, to provide a qualitative and quantitative combined decision evaluation analysis method, which can quickly and efficiently complete the evaluation of network intelligence capability grading while processing uncertain information by implementing quantitative analysis on the qualitative problems of network intelligence capability.

[0206] Among them, the method and the device are based on the same application concept. Since the principles of the method and the device for solving problems are similar, the implementation of the device and the method can be mutually referred to, and the repeated parts will not be described again.

[0207] The technical solutions provided by the embodiments of the present application can be applied to various systems, especially future communication systems, such as a 5G system. For example, the applicable systems can be a GSM (Global System for Mobile Communications) system, a CDMA (Code Division Multiple Access) system, a WCDMA (Wide-band Code Division Multiple Access) system, a GPRS (Ggeneral Packet Radio Service) system, an LTE (Long Term Evolution) system, an LTE FDD (Frequency Division Duplex) system, an LTE TDD (Time Division Duplex) system, an LTE-A (Long Term Evolution Advanced) system, a UMTS (Universal Mobile Telecommunication System) system, a WiMAX (Worldwide Interoperability for Microwave Access) system, a 5G system, and the like. The various systems all include terminal devices and network devices. The system can also include a core network part, such as an EPS (Evolved Packet System), a 5GC (5G core network), and the like.

[0208] The terminal device to which the embodiments of the present application relate can refer to a device providing voice and / or data connectivity to a user, a handheld device having a wireless connection function, or other processing devices connected to a wireless modem, etc. In different systems, the name of the terminal device can also be different, for example, in the 5G system, the terminal device can be called UE. The wireless terminal device can communicate with one or more CNs through the RAN, and the wireless terminal device can be a mobile terminal device, such as a mobile phone (or called "cellular" phone) and a computer with a mobile terminal device, for example, it can be a portable, pocket, handheld, computer built-in or vehicle-mounted mobile device, which exchanges language and / or data with the wireless access network. For example, PCS (Personal Communication Service) phone, cordless phone, SIP (Session Initiated Protocol) phone, WLL (Wireless Local Loop) station, PDA (Personal Digital Assistant) and other devices. The wireless terminal device can also be called system, subscriber unit, subscriber station, mobile station, mobile, remote station, access point, remote terminal, access terminal, user terminal, user agent, user device, which is not limited in the embodiments of the present application.

[0209] The network device according to the embodiments of the present applicationapplicationbe a base station, whichapplicationinclude a plurality of cells serving terminals. According to different application scenarios, the base stationapplicationalso be referred to as an access point, orapplicationbe a device in an access network that communicates with wireless terminal devices through one or more sectors over an air interface, or other names. The network deviceapplicationbe used to exchange received air frames and IP (Internet Protocol) packets as a router between wireless terminal devices and the rest of the access network, wherein the rest of the access networkapplicationinclude an IP communication network. The network deviceapplicationalso coordinate the management of properties of the air interface. For example, the network device according to the embodiments of the present applicationapplicationbe a BTS (Base Transceiver Station) in GSM or CDMA, or a NodeB (network device) in WCDMA, or an eNB or e-NodeB (evolutional NodeB) in an LTE system, or a 5G base station (gNB) in a 5G network architecture (next generation system), or a HeNB (Home evolved Node B), a relay node, a femto, a pico, etc., which are not limited in the embodiments of the present application. In some network structures, the network deviceapplicationinclude a CU (Centralized Unit) node and a DU (Distributed Unit) node, and the CU and the DUapplicationalso be arranged geographically apart.

[0210] The network device and the terminal deviceapplicationeach use one or more antennas for MIMO (Multi Input Multi Output) transmission, whichapplicationbe SU-MIMO (Single User MIMO) or MU-MIMO (Multiple User MIMO). According to the shape and number of antenna combinations, the MIMO transmissionapplicationbe 2D-MIMO, 3D-MIMO, FD-MIMO or massive-MIMO, or diversity transmission, or precoding transmission, or beamforming transmission, etc.

[0211] The communication network intelligentization hierarchical adaptive evaluation method, device and storage medium according to the embodiments of the present application are described below with reference to the accompanying drawings.

[0212] Figure 2 is a flowchart of a communication network intelligentization hierarchical adaptive evaluation method according to the first embodiment of the present application.

[0213] As Figure 2 shown, the adaptive evaluation method of intelligent classification of the communication network can include the following steps:

[0214] Step 201, establishing a hierarchical model of the target communication network and determining the weight of at least one object contained in each level of the hierarchical model with respect to the decision target.

[0215] The hierarchical model includes a plurality of levels.

[0216] In some embodiments, according to the evaluation dimensions and key features in the wireless communication network intelligent classification standard proposed by the relevant organization, the target, the considered factors (the criteria of the decision) and the decision scheme can be divided into the highest layer, the intermediate layer and the lowest layer according to their mutual relationship, and the hierarchical model of the target communication network as shown in Figure 3 is established. Figure 3 In the "alternative scheme" level, at least one object: "L0", "L1", "L2", "L3", "L4", "L5" are Figure 1 six levels in

[0217] The decision refers to the need to select a certain scheme according to certain standards when facing multiple schemes. For example, in the selection of a field to report a scientific research project in basic research, applied research and mathematics education, the contribution of the results (practical value, scientific significance), feasibility (difficulty, period and funds) and talent training should be considered. For example, in selecting a tourist spot from A, B and C, the scenery of the scenic spot, the living environment, the characteristics of food, the convenience of transportation and the cost of tourism should be considered.

[0218] The highest layer is the purpose of the decision or the problem to be solved, the intermediate layer is the considered factor or the criteria of the decision, and the bottom layer is the alternative scheme when making a decision. For two adjacent layers, the higher layer is called the target layer, and the lower layer is called the factor layer.

[0219] On the basis of in-depth analysis of actual problems, the factors contained in the problem are decomposed into several levels from top to bottom: the factors in the same layer belong to or have an impact on the factors in the upper layer, and at the same time, they dominate or are affected by the factors in the lower layer. Alternatively, when constructing the hierarchical model, various factors to be considered can be placed in appropriate levels to clearly express the relationship between these factors using the hierarchical model.

[0220] It should be noted that the highest layer is the target layer (the purpose of solving the problem), and generally only contains one object. The number of middle layers can be one or more, which are the criteria (also known as strategy layer, constraint layer, criterion layer, etc.) that must be followed by various measures and schemes taken to achieve the decision target. When there are too many criteria (for example, more than 9, so generally not more than 9), a sub-criterion layer should be further decomposed. The bottom layer is usually a scheme or object layer (various measures, schemes, etc. for solving the problem).

[0221] In some embodiments, after establishing the hierarchical model of the target communication network, a target weight determination method can be used to determine the weight of at least one object contained in each level of the hierarchical model with respect to the decision target. The target weight determination method includes, but is not limited to, the analytic hierarchy process, the entropy method, the factor analysis method, the principal component analysis method, etc.

[0222] As an example, after establishing the hierarchical model of the target communication network as shown in Figure 3 , the weight of at least one object contained in each level of the hierarchical model with respect to the decision target is shown in the following table:

[0223] Table 1: Example of weight of at least one object contained in each level of the hierarchical model with respect to the decision target

[0224] Overall indicator Primary indicator Weight Secondary indicator Weight Tertiary indicator Weight U A 1 B1 0.5549 C1 0.0371 B2 0.0967 C2 0.7263 B3 0.0967 C3 0.2263 B4 0.0967 C4 0.0651 B5 0.0967 C5 0.0353 C6 0.0353

[0225] In Table 1, the overall index is the "decision target" in the present application; the first-level index corresponds to the "target" level in the hierarchical model of the target communication network as shown in Figure 3 , i.e., the first-level index is "application intelligent level"; the second-level index corresponds to the "criterion" level in the hierarchical model of the target communication network as shown in Figure 3 , i.e., the second-level indexes B1-B5 are "demand mapping", "data collection", "analysis", "decision", and "execution", respectively; and the third-level index corresponds to the "alternative scheme" level in the hierarchical model of the target communication network as shown in Figure 3 , i.e., the third-level indexes C1-C6 are "L0", "L1", "L2", "L3", "L4", and "L5", respectively.

[0226] Optionally, one possible implementation of the above step 201 is to use the analytic hierarchy process to establish the hierarchical model of the target communication network and determine the weight of at least one object contained in each level of the hierarchical model with respect to the decision target.

[0227] At step 202, a fuzzy evaluation matrix is constructed based on the evaluations of the plurality of experts on at least one target object contained in the target level in the hierarchical model, so as to determine a fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix.

[0228] The target level can be the lowest level in the hierarchical model, such as the "alternative" level in the hierarchical model. Figure 3 The target level can be the lowest level in the hierarchical model, such as the "alternative" level in the hierarchical model.

[0229] In some embodiments, the experts can be organized to evaluate at least one target object contained in the target level in the hierarchical model in language, and the fuzzy evaluation matrix X = [x ij ] m×n wherein x ij represents a numerical value corresponding to the evaluation of the ith expert on the jth target object in the target level, m represents the number of experts, and n represents the number of target objects. Thus, the fuzzy evaluation value corresponding to each target object is determined based on the constructed fuzzy evaluation matrix, wherein the fuzzy evaluation value corresponding to any target object is determined based on the numerical values corresponding to the evaluations of the experts on the target object in the constructed fuzzy evaluation matrix.

[0230] At step 203, the system performance evaluation result of the target communication network is determined based on the weights of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object.

[0231] The system performance evaluation result is a quantitative analysis result, such as a system performance value.

[0232] Optionally, one possible implementation of the above step 203 is to determine the performance contribution value of each target object to the target communication network based on the weights of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object, and to determine the system performance evaluation result of the target communication network based on the performance contribution value of each target object to the target communication network.

[0233] Since the system performance evaluation result is a quantitative analysis result, in the present application, quantitative analysis can be implemented for the qualitative problem of network intelligent capability, thereby solving the technical problem that the related art completely relies on artificial qualitative judgment which has limitations, and making the analysis result more detailed and specific.

[0234] The communication network intelligent grading adaptive evaluation method provided by the embodiment of the application can establish a hierarchical structure model of a target communication network and determine the weight of at least one object included in each level of the hierarchical structure model with respect to a decision target, wherein the hierarchical structure model includes multiple levels, thereby constructing a fuzzy evaluation matrix based on the evaluation of the at least one target object included in a target level of the hierarchical structure model by multiple experts, determining the fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix, and determining the system performance evaluation result of the target communication network based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object. Thus, the quantitative analysis of the network intelligent capability qualitative problem can be implemented, and the evaluation of the network intelligent capability grading can be quickly and efficiently completed while the uncertain information is processed.

[0235] In the application, in addition to determining the system performance evaluation result of the target communication network, the grading result of the target communication network can also be determined. The process is described below in combination with Figure 4 .

[0236] Figure 4 FIG. 1 is a flowchart of the communication network intelligent grading adaptive evaluation method provided by the third embodiment of the application.

[0237] As shown in Figure 4 , the communication network intelligent grading adaptive evaluation method can include the following steps:

[0238] Step 401, a hierarchical structure model of a target communication network is established, and the weight of at least one object included in each level of the hierarchical structure model with respect to a decision target is determined.

[0239] Step 402, a fuzzy evaluation matrix is constructed based on the evaluation of the at least one target object included in a target level of the hierarchical structure model by multiple experts, and the fuzzy evaluation value corresponding to each target object is determined based on the fuzzy evaluation matrix.

[0240] Step 403, the system performance evaluation result of the target communication network is determined based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object.

[0241] It should be noted that the execution process of steps 401-403 can refer to the execution process of steps 201-203 in the above embodiment, and the principle is the same, which will not be described here again.

[0242] Step 404, the grading result of the target communication network is determined based on the weight of each target object with respect to the decision target.

[0243] Optionally, one possible implementation of the step 404 is to sort the target objects according to the weights of the target objects with respect to the decision target, to determine the hierarchical result of the target communication network based on the sorting result.

[0244] For example, after the hierarchical structure model of the target communication network is established as shown in the following table 1, the weights of the at least one object contained in each level of the hierarchical structure model with respect to the decision target are determined as shown in the following table 1, assuming that the target level is Figure 3 Figure 3 For example, after the hierarchical structure model of the target communication network is established as shown in the following table 1, the weights of the at least one object contained in each level of the hierarchical structure model with respect to the decision target are determined as shown in the following table 1, assuming that the target level is Figure 3 For example, after the hierarchical structure model of the target communication network is established as shown in the following table 1, the weights of the at least one object contained in each level of the hierarchical structure model with respect to the decision target are determined as shown in the following table 1, assuming that the target level is

[0245] In summary, in the present application, not only the hierarchical result of the target communication network is determined, but also the system performance evaluation result of the target communication network is determined, compared with the related art which only determines the hierarchical result, the fineness of the analysis result is effectively improved, which is beneficial to further determine the evaluation grade of the target communication network. For example, some network systems are between two adjacent grades, and it is more objective to give “hierarchical result + system performance evaluation result” than to directly and roughly give “hierarchical result”.

[0246] The communication network intelligent hierarchical self-adaptive evaluation method provided by the embodiment of the present application establishes a hierarchical structure model of a target communication network and determines the weight of at least one object contained in each level of the hierarchical structure model with respect to a decision target, wherein the hierarchical structure model includes multiple levels, thereby constructing a fuzzy evaluation matrix based on the evaluation of multiple experts on at least one target object contained in a target level of the hierarchical structure model, determining the fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix, determining the system performance evaluation result of the target communication network based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object, and determining the hierarchical result of the target communication network based on the weight of each target object with respect to the decision target. Thus, not only the hierarchical result of the target communication network is determined, but also the system performance evaluation result of the target communication network is determined, compared with the related art which only determines the hierarchical result, the fineness of the analysis result is effectively improved, which is beneficial to further determine the evaluation grade of the target communication network.

[0247] To clearly illustrate how the system performance evaluation result of the target communication network is determined based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object, the embodiment provides a possible implementation manner of determining the system performance evaluation result, Figure 5 is a flowchart of determining the system performance evaluation result according to the fourth embodiment of the present application.

[0248] As shown in Figure 5 , the specific process of determining the system performance evaluation result can include the following steps:

[0249] Step 501, for any target object, the weight of the target object with respect to the decision target is multiplied by the fuzzy evaluation value corresponding to the target object to obtain the fuzzy value of the performance contribution of the target object to the target communication network.

[0250] Optionally, a possible implementation manner of the above step 501 is that the fuzzy evaluation value corresponding to the target object is a triangular fuzzy evaluation value, the triangular fuzzy evaluation value is composed of three first parameters, the three first parameters include a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value, correspondingly, the fuzzy value of the performance contribution of the target object to the target communication network is a performance contribution triangular fuzzy value, the performance contribution triangular fuzzy value is composed of three second parameters, the three second parameters include a first performance contribution triangular fuzzy value, a second performance contribution triangular fuzzy value and a third performance contribution triangular fuzzy value, so that the weight of the target object with respect to the decision target can be multiplied by the first fuzzy evaluation value, the second fuzzy evaluation value and the third fuzzy evaluation value corresponding to the target object respectively to obtain the first performance contribution triangular fuzzy value, the second performance contribution triangular fuzzy value and the third performance contribution triangular fuzzy value of the target object to the target communication network.

[0251] As an example, it is assumed that the weight of the i th target object with respect to the decision target is w i , the fuzzy evaluation value corresponding to the i th target object is x i , where x i =(e i ,f i ,g i ), e i is the first fuzzy evaluation value corresponding to the i th target object, f i is the second fuzzy evaluation value corresponding to the i th target object, and g i is the third fuzzy evaluation value corresponding to the i th target object, then the fuzzy value of the performance contribution of the i th target object to the target communication network is d i =x i ×w i , i=1,2,…,n, n represents the number of target objects, where d i =(αi ,β i ,λ i ), α i =e i ×w i ,β i =f i ×w i , λ i =g i ×w i α i The triangular fuzzy value β contributes to the first performance of the target communication network for the i-th target object. i The triangular fuzzy value λ contributes to the second effectiveness of the target communication network for the i-th target object. i The triangular fuzzy value contributes to the third performance of the target communication network for the i-th target object.

[0252] Step 502: Determine the performance contribution value of the target object to the target communication network based on the fuzzy value of the performance contribution of the target object to the target communication network.

[0253] Optionally, one possible implementation of step 502 above is as follows: the sum of the first efficiency contribution triangle fuzzy value, the second efficiency contribution triangle fuzzy value of a set multiple, and the third efficiency contribution triangle fuzzy value is determined as the efficiency contribution median value; the ratio between the efficiency contribution median value and the first set value is determined as the efficiency contribution value of the target object to the target communication network.

[0254] As an example, suppose the fuzzy value of the performance contribution of the i-th target object to the target communication network is denoted by d. i It means that, where d i =(α i ,β i ,λ i ), α i The triangular fuzzy value β contributes to the first performance of the target communication network for the i-th target object. i The triangular fuzzy value λ contributes to the second effectiveness of the target communication network for the i-th target object. i Let the triangular fuzzy value be the third performance contribution of the i-th target object to the target communication network. If the multiplier is set to 2 and the first set value is 4, then the performance contribution value s of the i-th target object to the target communication network is... i =(α i +2β i +λ i ) / 4, i = 1, 2, ..., n, where n represents the number of target objects.

[0255] Step 503: The sum of the performance contributions of each target object to the target communication network is determined as the system performance evaluation result of the target communication network.

[0256] As an example, assuming that the performance contribution value of the ith target object to the target communication network is denoted by s i , then the system performance evaluation result of the target communication network is i = 1, 2, …, n, where n represents the number of target objects.

[0257] In summary, by multiplying the weight of a target object with respect to a decision target and the fuzzy evaluation value corresponding to the target object for any target object, the performance contribution fuzzy value of the target object to the target communication network is obtained, and then the performance contribution value of the target object to the target communication network is determined based on the performance contribution fuzzy value of the target object to the target communication network. The sum of the performance contribution values of the target objects to the target communication network is determined as the system performance evaluation result of the target communication network. Thus, quantitative analysis can be implemented for network intelligent capability qualitative problems.

[0258] In order to clearly illustrate how the fuzzy evaluation matrix is constructed based on the evaluation of the at least one target object contained in the target level of the hierarchical structure model by multiple experts, and how the fuzzy evaluation value corresponding to each target object is determined based on the fuzzy evaluation matrix, the present embodiment provides a possible implementation manner for determining the fuzzy evaluation value, Figure 6 which is a flowchart for determining the fuzzy evaluation value according to the fifth embodiment of the present application.

[0259] As shown in Figure 6 , the specific process of determining the fuzzy evaluation value can include the following steps:

[0260] In step 601, based on the preset correspondence between the evaluation and the fuzzy decision number, the evaluation of the at least one target object contained in the target level of the hierarchical structure model by each expert is converted into the corresponding fuzzy decision number.

[0261] In some embodiments, the experts can evaluate the at least one target object contained in the target level of the hierarchical structure model using language. Optionally, the experts can evaluate each target object using the following language: very poor, poor, medium-low, medium, medium-high, good, and very good. Thus, based on the preset correspondence between the evaluation and the fuzzy decision number, the evaluation of the at least one target object contained in the target level of the hierarchical structure model by each expert can be converted into the corresponding fuzzy decision number. Optionally, the fuzzy decision number is a triangular fuzzy decision number, which is composed of three third parameters, including a first fuzzy decision number, a second fuzzy decision number, and a third fuzzy decision number. The preset correspondence between the evaluation and the fuzzy decision number can be as shown in the following table:

[0262] Table 2: Example of correspondence between preset evaluation and fuzzy decision number

[0263]

[0264]

[0265] Step 602, constructing a fuzzy evaluation matrix based on the fuzzy decision numbers.

[0266] Any row or column in the fuzzy evaluation matrix is composed of the fuzzy decision numbers corresponding to the evaluations of any target object by each expert.

[0267] In some embodiments, after converting the evaluations of at least one target object contained in a target level in the hierarchical model by each expert into corresponding fuzzy decision numbers, a fuzzy evaluation matrix can be constructed based on the fuzzy decision numbers.

[0268] As an example, the constructed fuzzy evaluation matrix is X=[x ij ] m×n , where x ij represents the fuzzy decision number corresponding to the evaluation of the jth target object in the target level by the ith expert, m represents the number of experts, and n represents the number of target objects. Optionally, the fuzzy decision number is a triangular fuzzy decision number composed of three third parameters, including a first fuzzy decision number, a second fuzzy decision number, and a third fuzzy decision number, so that x ij can be represented by a triangular fuzzy number as x ij =(e ij ,f ij ,g ij ), where e ij represents the first fuzzy decision number corresponding to the evaluation of the jth target object in the target level by the ith expert, f ij represents the second fuzzy decision number corresponding to the evaluation of the jth target object in the target level by the ith expert, and g ij represents the third fuzzy decision number corresponding to the evaluation of the jth target object in the target level by the ith expert.

[0269] Step 603, determining the fuzzy evaluation value corresponding to the target object based on any row or column in the fuzzy evaluation matrix.

[0270] Optionally, one possible implementation of the above step 603 is to determine the ratio between the sum of the fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the fuzzy evaluation value corresponding to the target object.

[0271] Optionally, the fuzzy decision number is a triangular fuzzy decision number, which consists of three third parameters, including a first fuzzy decision number, a second fuzzy decision number, and a third fuzzy decision number. Correspondingly, the fuzzy evaluation value is a triangular fuzzy evaluation value, which consists of three first parameters, including a first fuzzy evaluation value, a second fuzzy evaluation value, and a third fuzzy evaluation value. Thus, the ratio between the sum of all first fuzzy decision numbers in any row or column of the fuzzy evaluation matrix and the number of experts can be determined as the first fuzzy evaluation value corresponding to the target object; the ratio between the sum of all second fuzzy decision numbers in any row or column of the fuzzy evaluation matrix and the number of experts can be determined as the second fuzzy evaluation value corresponding to the target object; and the ratio between the sum of all third fuzzy decision numbers in any row or column of the fuzzy evaluation matrix and the number of experts can be determined as the third fuzzy evaluation value corresponding to the target object.

[0272] As an example, the fuzzy evaluation matrix constructed above is X = [x ij ] m×n For example, the fuzzy evaluation matrix X = [x ij ] m×n Transform into an evaluation vector x = (x1, x2, ..., x j ), where x j = (1 / m) × (x) 1j +x 2j +…+x mj ), j = 1, 2, ..., n, x j That is, the fuzzy evaluation value corresponding to the j-th target object. Optionally, x ij This can be represented by the triangular fuzzy number x. ij =(e ij ,f ij ,g ij Accordingly, x j =(e j ,f j ,g j ),in, e j f represents the first fuzzy evaluation value corresponding to the j-th target object. j G represents the second fuzzy evaluation value corresponding to the j-th target object. j This represents the third fuzzy evaluation value corresponding to the j-th target object.

[0273] In summary, by converting the evaluation of each expert on at least one target object contained in a target level in the hierarchical structure model into a corresponding fuzzy decision number based on the correspondence between the preset evaluation and the fuzzy decision number, a fuzzy evaluation matrix is constructed based on the fuzzy decision numbers, wherein any row or column in the fuzzy evaluation matrix is composed of the fuzzy decision numbers corresponding to the evaluation of each expert on any target object, and then the fuzzy evaluation value corresponding to the target object is determined based on any row or column in the fuzzy evaluation matrix. Thus, the fuzzy evaluation matrix can be constructed by converting the evaluation of each expert on each target object into a corresponding fuzzy decision number, and the fuzzy evaluation value corresponding to each target object is determined based on the fuzzy evaluation matrix.

[0274] To clearly illustrate how the hierarchical structure model of the target communication network is established and the weight of at least one object contained in each level of the hierarchical structure model with respect to the decision target is determined in the present application, the present embodiment provides a possible implementation of establishing the hierarchical structure model and determining the weight, Figure 7 is a flowchart of establishing the hierarchical structure model and determining the weight according to the sixth embodiment of the present application.

[0275] It should be noted that, Figure 7 The process shown is the process of establishing the hierarchical structure model of the target communication network and determining the weight of at least one object contained in each level of the hierarchical structure model with respect to the decision target by using the analytic hierarchy process.

[0276] The analytic hierarchy process is a qualitative and quantitative combination decision analysis method for solving multi-objective complex problems. This method combines quantitative analysis and qualitative analysis, uses the experience of decision makers to judge the relative importance between the standards for measuring whether the target can be achieved, and reasonably gives the weight of each standard of each decision scheme, and uses the weight to obtain the order of advantages and disadvantages of each scheme.

[0277] As Figure 7 shown, the specific process of establishing the hierarchical structure model and determining the weight can include the following steps:

[0278] Step 701, based on the mutual relationship between the decision target, the decision criterion and the decision scheme, a hierarchical structure model of the target communication network is established.

[0279] The analytic hierarchy process divides the problem into different constituent factors according to the nature of the problem and the overall goal to be achieved, and according to the mutual influence and membership relationship between the factors, the factors are aggregated and combined according to different levels to form a multi-level analysis structure model, so that the problem is ultimately reduced to the determination of the relative importance weight of the lowest level (the scheme, measure, etc. for decision) relative to the highest level (the overall goal) or the arrangement of the relative order of advantages and disadvantages.

[0280] In some embodiments, the decision target, decision criteria and decision scheme can be divided into the highest layer, the middle layer and the lowest layer according to the interrelationship among them, and a hierarchical structure model of the target communication network as shown in Figure 3 is established. The highest layer is the purpose of decision or the problem to be solved, the middle layer is the factor to be considered or the criteria of decision, and the lowest layer is the alternative scheme of decision.

[0281] In step 702, at least one judgment matrix corresponding to each layer of the hierarchical structure model is constructed based on the relative importance of any two objects in each layer of the hierarchical structure model to any object in the upper layer, except the highest layer.

[0282] In some embodiments, starting from the second layer of the hierarchical structure model, a judgment matrix can be constructed for the factors in the same layer that belong to (or affect) each factor in the upper layer, until the lowest layer. The judgment matrix is a comparison of the relative importance of all factors in the layer to a certain factor in the upper layer.

[0283] It should be noted that the process of constructing the judgment matrix is not to compare the factors in the same layer together, but to compare them with each other, and the comparison process uses a relative scale to reduce the difficulty of comparing factors with different properties to each other as much as possible, so as to improve the accuracy.

[0284] It should be noted that each layer of the hierarchical structure model corresponds to at least one judgment matrix, and the number of judgment matrices corresponding to each layer is consistent with the number of objects contained in the upper layer of each layer. For example, Figure 3 The number of objects contained in the upper layer of the "criteria" layer of the hierarchical structure model as shown in Figure 3 The judgment matrix corresponding to the "criteria" layer of the hierarchical structure model also has only one.

[0285] In a possible implementation, when performing step 702 of constructing at least one judgment matrix corresponding to each layer of the hierarchical structure model based on the relative importance of any two objects in each layer of the hierarchical structure model to any object in the upper layer, except the highest layer, the following steps can be performed:

[0286] In step 7021, the relative importance of any two objects in each layer of the hierarchical structure model to any object in the upper layer, except the highest layer, is converted into a corresponding scale value based on a preset scale mode of elements of the judgment matrix.

[0287] Optionally, the preset scale mode of elements of the judgment matrix is shown in the following table:

[0288] Table 3: Example of preset scale mode of elements of judgment matrix

[0289] Criteria (dimension) i compared to criteria (dimension) j Scale value Equally important 1 Slightly important 3 More important 5 Strongly important 7 Extremely important 9 Intermediate value of the two adjacent judgments above 2、4、6、8

[0290] wherein the above two adjacent judging intermediate values of 2, 4, 6, 8 mean that when the criterion (dimension) i is between equally important and slightly important compared with the criterion (dimension) j, the corresponding scale value is 2; when the criterion (dimension) i is between slightly important and relatively important compared with the criterion (dimension) j, the corresponding scale value is 4; when the criterion (dimension) i is between relatively important and strongly important compared with the criterion (dimension) j, the corresponding scale value is 6; when the criterion (dimension) i is between strongly important and extremely important compared with the criterion (dimension) j, the corresponding scale value is 8.

[0291] It should be noted that the scale value corresponding to the relative importance of the criterion (dimension) i compared with the criterion (dimension) j is a ij , then the scale value corresponding to the relative importance of the criterion (dimension) j compared with the criterion (dimension) i is 1 / a ij .

[0292] Step 7022, based on each scale value, constructing at least one judgment matrix corresponding to each level.

[0293] Wherein, any row or column in any judgment matrix is composed of the relative importance of any object in the corresponding level compared with all objects in the current level for any object in the previous level.

[0294] Optionally, the judgment matrix A is as follows:

[0295]

[0296] Suppose the judgment matrix A is Figure 3 The judgment matrix corresponding to the "criterion" level in the hierarchical structure model shown in the table, then the first row respectively represents the relative importance of execution compared with itself, the relative importance of execution compared with data collection, the relative importance of execution compared with analysis, the relative importance of execution compared with decision, the relative importance of execution compared with demand mapping, the second row respectively represents the relative importance of data collection compared with execution, the relative importance of data collection compared with itself, the relative importance of data collection compared with analysis, the relative importance of data collection compared with decision, the relative importance of data collection compared with demand mapping, and the other rows are in turn. That is, the judgment matrix A can be obtained through the following table:

[0297] Table 4 Comparison example table of the relative importance of all objects in the "criterion" level for the "application intelligent level" object in the "target" level

[0298]

[0299] Similarly, the relative importance matrix corresponding to the "alternative" hierarchy can be obtained by Table 5-Table 9:

[0300] Table 5 Comparative example table of relative importance of all objects in the "alternative" hierarchy to the "execution" object in the "criterion" hierarchy

[0301]

[0302] Table 6 Comparative example table of relative importance of all objects in the "alternative" hierarchy to the "data collection" object in the "criterion" hierarchy

[0303]

[0304] Table 7 Comparative example table of relative importance of all objects in the "alternative" hierarchy to the "analysis" object in the "criterion" hierarchy

[0305]

[0306] Table 8 Comparative example table of relative importance of all objects in the "alternative" hierarchy to the "decision" object in the "criterion" hierarchy

[0307]

[0308]

[0309] Table 9 Comparative example table of relative importance of all objects in the "alternative" hierarchy to the "demand mapping" object in the "criterion" hierarchy

[0310]

[0311] In summary, the judgment matrix corresponding to the "alternative" hierarchy includes judgment matrix B, judgment matrix C, judgment matrix D, judgment matrix E and judgment matrix F.

[0312] It should be noted that in the present application, the constructed judgment matrix is an n-order consistency matrix.

[0313] In step 703, consistency check is performed on each judgment matrix, so that in the case that the consistency check of each judgment matrix is passed, the weight of at least one object included in each hierarchy in the hierarchical structure model except the highest hierarchy with respect to the decision target is determined based on each judgment matrix.

[0314] In a possible implementation, in the case that the consistency check of any judgment matrix is not passed, the judgment matrix is re-constructed.

[0315] In a possible implementation, in the step 703, the consistency check is performed on each judgment matrix, and when the consistency check of each judgment matrix is passed, the weight of at least one object included in each level of the hierarchical structure model except the highest level with respect to the decision target is determined based on each judgment matrix, which can be specifically performed according to the following steps:

[0316] In step 7031, for any judgment matrix, a consistency index corresponding to the judgment matrix is determined based on the maximum eigenvalue corresponding to the judgment matrix and the order of the judgment matrix.

[0317] Optionally, the difference between the maximum eigenvalue corresponding to the judgment matrix and the order of the judgment matrix is determined as a first intermediate value; the difference between the order of the judgment matrix and a fourth set value is determined as a second intermediate value; and the ratio between the first intermediate value and the second intermediate value is determined as the consistency index corresponding to the judgment matrix.

[0318] As an example, assuming that the fourth set value is 1, the maximum eigenvalue corresponding to the judgment matrix is denoted as λ max , and the order of the judgment matrix is n, the consistency index corresponding to the judgment matrix is

[0319] In step 7032, according to a preset correspondence between the order and the average consistency index, the average consistency index corresponding to the judgment matrix is determined based on the order of the judgment matrix.

[0320] Optionally, the preset correspondence between the order and the average consistency index can be as shown in the following table:

[0321] Table 10: Example table of preset correspondence between order and average consistency index

[0322] n (order) 1 2 3 4 5 6 7 8 9 RI (average consistency index) 0 0 0.58 0.90 1.12 1.24 1.32 1.41 1.45

[0323] As an example, assuming that the order of the judgment matrix is 5, the average consistency index corresponding to the judgment matrix can be determined based on the preset correspondence between the order and the average consistency index, and the average consistency index is 1.12.

[0324] In step 7033, a consistency check coefficient corresponding to the judgment matrix is determined based on the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix, and when the consistency check coefficient is less than a third set value, it is determined that the consistency check of the judgment matrix is passed.

[0325] Optionally, the ratio between the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix is determined as the consistency check coefficient corresponding to the judgment matrix.

[0326] Optionally, in a case where the consistency check coefficient is not less than the third set value, it can be determined that the consistency check of the judgment matrix fails. In a possible implementation of the present application, in a case where the consistency check of any judgment matrix fails, the judgment matrix can be reconstructed.

[0327] As an example, assuming that the consistency index corresponding to the judgment matrix is denoted by CI, the consistency index corresponding to the judgment matrix is denoted by RI, and the consistency check coefficient corresponding to the judgment matrix is denoted by CR, the consistency check coefficient corresponding to the judgment matrix can be calculated as follows: Assuming that the third set value is 0.1, when CR<0.1, it can be considered that the judgment matrix has satisfactory consistency, and it is determined that the consistency check of the judgment matrix passes; otherwise, the judgment matrix needs to be adjusted.

[0328] In a case where the consistency check of each judgment matrix passes, the weight matrix corresponding to the corresponding level can be determined based on the eigenvector corresponding to the target judgment matrix.

[0329] The target judgment matrix is at least one judgment matrix corresponding to any level in the hierarchical structure model except the highest level.

[0330] It should be noted that, since the highest level in the hierarchical structure model only contains one object, the weight of the object included in the highest level in the hierarchical structure model with respect to the decision target can be the second set value. The second set value is, for example, 1.

[0331] In some embodiments, in a case where the consistency check of each judgment matrix passes, the weight matrix corresponding to any level in the hierarchical structure model except the highest level can be determined based on the eigenvector corresponding to at least one judgment matrix corresponding to the level.

[0332] As an example, for the judgment matrix A corresponding to the “Criteria” level and the judgment matrices B, C, D, E, and F corresponding to the “Alternatives” level in the hierarchical structure model shown in FIG. 8, the eigenvector corresponding to each judgment matrix can be determined by using the following calculation process: Figure 3 As an example, for the judgment matrix A corresponding to the “Criteria” level and the judgment matrices B, C, D, E, and F corresponding to the “Alternatives” level in the hierarchical structure model shown in FIG. 8, the eigenvector corresponding to each judgment matrix can be determined by using the following calculation process:

[0333] Assuming that the judgment matrix is

[0334] (1) Normalize each column of the judgment matrix:

[0335]

[0336] (2) Add the normalized matrix of each column by row:

[0337]

[0338] (3) the vector M = (M1, M2, …, M n ) T Normalization:

[0339]

[0340] The sought W = (W1, W2, …, W n ) T is the eigenvector corresponding to the judgment matrix.

[0341] Thus, the eigenvector corresponding to the judgment matrix A can be expressed as W A = (W1, W2, …, W5) T , and the W A is converted into a matrix, and the converted matrix is merged to obtain the weight matrix W0 corresponding to the "criterion" level, wherein W0 is a 1-row 5-column matrix. The eigenvector corresponding to the judgment matrix B can be expressed as W B = (W1, W2, …, W6) T , the eigenvector corresponding to the judgment matrix C can be expressed as W C = (W1, W2, …, W6) T , the eigenvector corresponding to the judgment matrix D can be expressed as W D = (W1, W2, …, W6) T , the eigenvector corresponding to the judgment matrix E can be expressed as W E = (W1, W2, …, W6) T , and the eigenvector corresponding to the judgment matrix F can be expressed as W F = (W1, W2, …, W6) T , the W B , W C , W D , W E , and W F are converted into a matrix, and the converted matrix is merged to obtain the weight matrix W1 corresponding to the "alternative" level, wherein W1 is a 5-row 6-column matrix.

[0342] In step 7035, based on the weight matrix corresponding to each level, the weight of at least one object contained in each level of the hierarchical structure model except the highest level with respect to the decision target is determined.

[0343] Optionally, for any level, if there is at least one upper level of the non-highest level, the weight matrix corresponding to the level is multiplied by the weight matrix corresponding to the upper level of the non-highest level to obtain the target weight matrix corresponding to the level, or if there is no at least one upper level of the non-highest level, the weight matrix corresponding to the level is determined as the target weight matrix corresponding to the level, wherein the target weight matrix is composed of the weights of at least one object included in the corresponding level with respect to the decision target, so as to determine the weights of at least one object included in each level with respect to the decision target based on the target weight matrix corresponding to each level.

[0344] As an example, for the above Figure 3 The weight matrix W0 corresponding to the "criterion" level in the hierarchical structure model shown in the figure is determined as the target weight matrix corresponding to the "criterion" level, because the upper level of the "criterion" level is the highest level, i.e. there is no at least one upper level of the non-highest level for the "criterion" level. The target weight matrix W corresponding to the "alternative" level is determined as W = W0W1, because the "alternative" level has one upper level of the non-highest level ("criterion" level).

[0345] In summary, by establishing the hierarchical structure model of the target communication network based on the mutual relationship among the decision target, the decision criterion and the decision scheme, at least one judgment matrix corresponding to each level is constructed based on the relative importance of any two objects in each level other than the highest level with respect to any object in the upper level, and then the consistency of each judgment matrix is checked, so that if the consistency check of each judgment matrix is passed, the weights of at least one object included in each level other than the highest level with respect to the decision target are determined based on the judgment matrix. Thus, the hierarchical structure model of the target communication network can be established by using the analytic hierarchy process, and the weights of at least one object included in each level of the hierarchical structure model with respect to the decision target can be determined.

[0346] In order to clearly illustrate the above embodiments, examples are given as follows.

[0347] Figure 8 is a flowchart of the adaptive evaluation method for intelligent classification of communication networks according to the seventh embodiment of the present application.

[0348] As Figure 8 shown, the adaptive evaluation method for intelligent classification of communication networks can include the following steps:

[0349] Step 1: Establish a hierarchical structure model, input data and construct a judgment matrix.

[0350] According to the evaluation dimensions and key features in the intelligent classification standard of wireless communication network proposed by relevant organizations, the hierarchy model is divided into the highest layer, the middle layer and the lowest layer according to the mutual relationship among the decision target, the considered factors (decision criteria) and the decision objects, as shown in Figure 3

[0351] All factors are compared with each other. At this time, the relative scale is used to reduce the difficulty of comparing factors with different properties with each other as much as possible, so as to improve the accuracy. The judgment matrix is a comparison of the relative importance of all factors in the layer to a certain factor in the upper layer. The elements of the judgment matrix are given by the scale method shown in Table 3.

[0352] It should be noted that each level in the hierarchy model corresponds to at least one judgment matrix, and the number of judgment matrices corresponding to each level is consistent with the number of objects contained in the upper level of each level. For example, Figure 3 The number of objects contained in the upper level of the "criteria" level in the hierarchy model shown in Figure 3 The judgment matrix corresponding to the "criteria" level in the hierarchy model shown in

[0353] For example, the judgment matrix A is as follows:

[0354]

[0355] Suppose the judgment matrix A is Figure 3 The judgment matrix corresponding to the "criteria" level in the hierarchy model shown in

[0356] The first row respectively represents the relative importance of execution compared with itself, the relative importance of execution compared with data collection, the relative importance of execution compared with analysis, the relative importance of execution compared with decision, and the relative importance of execution compared with demand mapping. The second row respectively represents the relative importance of data collection compared with execution, the relative importance of data collection compared with itself, the relative importance of data collection compared with analysis, the relative importance of data collection compared with decision, and the relative importance of data collection compared with demand mapping. The other rows are in turn.

[0357] Step 2: Weight and consistency check calculation

[0358] The consistency check is checked by calculating the consistency index and the check coefficient.

[0359] Consistency index:​

[0360] Consistency check coefficient:

[0361] In the formula, λ max CR is the largest eigenvalue corresponding to the judgment matrix, n is the order of the judgment matrix, and RI is the average consistency index, which can be found in Table 10. Generally speaking, when CR < 0.1, the judgment matrix can be considered to have satisfactory consistency; otherwise, the judgment matrix needs to be readjusted.

[0362] Step 3: Hierarchical weighting, confirming the current communication network hierarchy.

[0363] Figure 3 The weight W of at least one object in the "Alternative Solution" level of the hierarchical model shown can be calculated with respect to the decision objective using the following formula:

[0364] W = W0W1

[0365] Figure 3 The weights of at least one object in each level of the hierarchical model shown in Table 1 are as follows, with respect to the decision objective.

[0366] The objects in the "alternative solutions" level are arranged in order of their weights relative to the overall goal, and the object with the highest weight is the optimal solution.

[0367] At this point, we can determine the current intelligent classification result of the communication network. Next, we will determine the current system performance evaluation result of the communication network.

[0368] Step 4: Constructing the fuzzy evaluation matrix

[0369] Experts were organized to evaluate and score the weight indicators C1 to Cn in the analytic hierarchy process using language. The evaluation matrix X = [x ij ] m×n , where x ij This refers to the evaluation of the Cj indicator by the i-th expert, x. ij This can be represented by the triangular fuzzy number x. ij =(e ij ,f ij ,g ij The correspondence between expert evaluations and fuzzy decision numbers is shown in Table 2.

[0370] Please have m communication experts provide evaluation criteria for the current network system's performance indicators, as shown in the table below:

[0371] Table 11 Expert Evaluation of Network Intelligent System Performance Indicators

[0372] Expert C1 C2 C3 C4 C5 C6 1 Good Upper middle Good Middle Middle Lower middle 2 Middle Middle Lower middle Good Middle Upper middle 3 Middle Good Middle Lower middle Bad Indicator m … … … … … …

[0373] Step 5: Evaluation Vector Calculation

[0374] The evaluation matrix X = [x ij ] m×n Transform into an evaluation vector x = (x1, x2, ..., x j ), where x j = (1 / m) × (x) 1j +x 2j +…+x mj ), j = 1, 2, ..., n,

[0375] Where, x ij =(e ij ,f ij ,g ij ), m represents the number of experts, and n represents the number of indicators.

[0376] The triangular fuzzy evaluation values ​​of each indicator can be calculated from the above formula, as shown in the table below.

[0377] Table 12 Triangular fuzzy evaluation values ​​for each indicator

[0378] Triangular fuzzy evaluation value Indicator Triangular fuzzy evaluation value Indicator C1 (0.12，0.160，2) C4 (0.1，0.15，0.18) C2 (0.08，0.13，0.18) C5 (0.1，0.15，0.18) C3 (0.03，0.07，0.12) C6 (0.1，0.15，0.18)

[0379] Step 6: Calculate the contribution of each layer's indicators to the current communication network's system performance, and obtain the communication network evaluation.

[0380] The performance index weights calculated using the analytic hierarchy process (AHP) mentioned earlier are W = (W1, W2, ..., W6). T Among them, W i The weights for the i-th indicator are shown in Table 1.

[0381] The triangular fuzzy value d, representing the contribution of each indicator to the current communication network's effectiveness, can be calculated using the following formula. i :

[0382] d i =x i ×w i i = 1, 2, ..., n

[0383] Where, d i =(α i ,β i ,λ i ), α i =e i ×w i ,β i =f i ×w i , λ i =g i ×wi .

[0384] The contribution value s of each index to the system performance of the current communication network is calculated as follows i

[0385] s i = (a i + 2b i + l i ) / 4, i = 1, 2, …, n

[0386] The example is shown in the following table:

[0387] Table 13: The contribution value s of each index to the system performance of the current communication network

[0388] Corresponding system effectiveness contribution value Indicator Corresponding system effectiveness contribution value Figure 9 C1 <S1> C4 [S4] C2 [S2] C5 [S5] C3 [S3] C6 [S6]

[0389] The system performance evaluation result (system performance value E) of the current communication network is calculated as follows:

[0390] The system performance value E is calculated by the following formula:

[0391]

[0392] According to the foregoing table 13, the system performance evaluation result of the current communication network can be obtained.

[0393] In summary, according to the relationship between the evaluation dimensions and key features in the intelligent classification standard of wireless communication network proposed by the relevant organization, the application proposes an adaptive evaluation method for the intelligent classification of communication network. By fusing the analytic hierarchy process and the fuzzy decision method, the advantages in processing uncertain information are realized, and the grade evaluation of network intelligent capability can be quickly and efficiently completed.

[0394] In order to realize the above-mentioned embodiments, the application further provides an adaptive evaluation device for the intelligent classification of communication network.

[0395] Figure 9 It is a structure schematic diagram of the adaptive evaluation device for the intelligent classification of communication network provided by the eighth embodiment of the application.

[0396] As Figure 9 shown, the adaptive evaluation device for the intelligent classification of communication network can include a memory 910, a transceiver 920 and a processor 930.

[0397] The memory 910 is configured to store a computer program; the transceiver 920 is configured to transceive data under the control of the processor; and the processor 930 is configured to read the computer program in the memory and perform the following operations:

[0398] ​Establish a hierarchical structure model of the target communication network and determine the weight of at least one object in each level of the hierarchical structure model with respect to the decision objective, wherein the hierarchical structure model includes multiple levels;

[0399] Based on the evaluations of multiple experts on at least one target object contained in the target level of the hierarchical model, a fuzzy evaluation matrix is ​​constructed to determine the fuzzy evaluation value corresponding to each target object.

[0400] Based on the weights of each target object with respect to the decision objective and the corresponding fuzzy evaluation values ​​of each target object, the system performance evaluation results of the target communication network are determined.

[0401] Transceiver 920 is used to receive and send data under the control of processor 930.

[0402] Among them, Figure 10 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors, represented by processor 930, and memory, represented by memory 910. The bus architecture can also link various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 920 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over transmission media, including wireless channels, wired channels, optical fibers, etc. Processor 930 is responsible for managing the bus architecture and general processing, and memory 910 can store data used by processor 930 during operation.

[0403] The processor 930 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor can also adopt a multi-core architecture.

[0404] As one possible implementation of this application embodiment, the processor 930 is also configured to perform the following operations:

[0405] The hierarchical results of the target communication network are determined based on the weights of each target object with respect to the decision objective.

[0406] As one possible implementation of this application embodiment, the processor 930 is also configured to perform the following operations:

[0407] rank the target objects according to the weights of the target objects with respect to the decision target, to determine a hierarchical result of the target communication network based on a ranking result.

[0408] As a possible implementation manner of the embodiment of the present application, the processor 830 is further configured to perform the following operation:

[0409] determine the performance contribution value of each target object to the target communication network based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object;

[0410] determine the system performance evaluation result of the target communication network based on the performance contribution value of each target object to the target communication network.

[0411] As a possible implementation manner of the embodiment of the present application, the processor 930 is further configured to perform the following operation:

[0412] for any target object, multiply the weight of the target object with respect to the decision target by the fuzzy evaluation value corresponding to the target object to obtain a performance contribution fuzzy value of the target object to the target communication network;

[0413] determine the performance contribution value of the target object to the target communication network based on the performance contribution fuzzy value of the target object to the target communication network.

[0414] As a possible implementation manner of the embodiment of the present application, the fuzzy evaluation value corresponding to the target object is a triangular fuzzy evaluation value, the triangular fuzzy evaluation value is composed of three first parameters, the three first parameters include a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value, and correspondingly, the performance contribution fuzzy value of the target object to the target communication network is a performance contribution triangular fuzzy value, the performance contribution triangular fuzzy value is composed of three second parameters, the three second parameters include a first performance contribution triangular fuzzy value, a second performance contribution triangular fuzzy value and a third performance contribution triangular fuzzy value;

[0415] The processor 930 is further configured to perform the following operation:

[0416] multiply the weight of the target object with respect to the decision target by the first fuzzy evaluation value, the second fuzzy evaluation value and the third fuzzy evaluation value corresponding to the target object respectively to obtain the first performance contribution triangular fuzzy value, the second performance contribution triangular fuzzy value and the third performance contribution triangular fuzzy value of the target object to the target communication network.

[0417] As a possible implementation manner of the embodiment of the present application, the processor 930 is further configured to perform the following operation:

[0418] determine the performance contribution intermediate value as the sum of the first performance contribution triangular fuzzy value, the second performance contribution triangular fuzzy value multiplied by the set multiple and the third performance contribution triangular fuzzy value.

[0419] determine a ratio between the performance contribution intermediate value and the first set value as the performance contribution value of the target object to the target communication network.

[0420] As a possible implementation manner of the embodiment of the present application, the processor 930 is further configured to perform the following operation:

[0421] determine a sum of the performance contribution values of the target objects to the target communication network as the system performance evaluation result of the target communication network.

[0422] As a possible implementation manner of the embodiment of the present application, the processor 930 is further configured to perform the following operation:

[0423] convert the evaluation of each expert on at least one target object contained in the target level in the hierarchical structure model into a corresponding fuzzy decision number based on a preset corresponding relationship between the evaluation and the fuzzy decision number;

[0424] construct a fuzzy evaluation matrix based on the fuzzy decision numbers, wherein any row or column in the fuzzy evaluation matrix is composed of the fuzzy decision numbers corresponding to the evaluation of any target object by each expert;

[0425] determine the fuzzy evaluation value corresponding to the corresponding target object based on any row or column in the fuzzy evaluation matrix.

[0426] As a possible implementation manner of the embodiment of the present application, the processor 930 is further configured to perform the following operation:

[0427] determine a ratio between the sum of the fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the fuzzy evaluation value corresponding to the corresponding target object.

[0428] As a possible implementation manner of the embodiment of the present application, the fuzzy decision number is a triangular fuzzy decision number, the triangular fuzzy decision number is composed of three third parameters, the three third parameters include a first fuzzy decision number, a second fuzzy decision number and a third fuzzy decision number, and correspondingly, the fuzzy evaluation value is a triangular fuzzy evaluation value, the triangular fuzzy evaluation value is composed of three first parameters, the three first parameters include a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value;

[0429] The processor 930 is further configured to perform the following operation:

[0430] determine a ratio between the sum of the first fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the first fuzzy evaluation value corresponding to the corresponding target object;

[0431] Determine the ratio between the sum of each second fuzzy decision number in any row or column in the fuzzy evaluation matrix and the number of experts as the second fuzzy evaluation value corresponding to the corresponding target object;

[0432] Determine the ratio between the sum of each third fuzzy decision number in any row or column in the fuzzy evaluation matrix and the number of experts as the third fuzzy evaluation value corresponding to the corresponding target object.

[0433] As a possible implementation manner of the embodiment of the application, the processor 930 is further configured to perform the following operation:

[0434] An analytic hierarchy process is adopted to establish a hierarchical structure model of the target communication network and determine the weight of at least one object included in each level of the hierarchical structure model with respect to the decision target.

[0435] As a possible implementation manner of the embodiment of the application, the weight of the object included in the highest level of the hierarchical structure model with respect to the decision target is a second set value;

[0436] The processor 930 is further configured to perform the following operation:

[0437] Based on the mutual relationship among the decision target, the decision criterion and the decision scheme, a hierarchical structure model of the target communication network is established;

[0438] Based on the relative importance of any two objects in each level of the hierarchical structure model to any object in the previous level, at least one judgment matrix corresponding to each level is constructed;

[0439] The consistency of each judgment matrix is checked, and in the case that the consistency check of each judgment matrix is passed, the weight of at least one object included in each level of the hierarchical structure model except the highest level with respect to the decision target is determined based on each judgment matrix.

[0440] As a possible implementation manner of the embodiment of the application, the processor 930 is further configured to perform the following operation:

[0441] In the case that the consistency check of any judgment matrix is not passed, the judgment matrix is reconstructed.

[0442] As a possible implementation manner of the embodiment of the application, the processor 930 is further configured to perform the following operation:

[0443] Based on the preset element scale mode of the judgment matrix, the relative importance of any two objects in each level of the hierarchical structure model except the highest level to any object in the previous level is converted into a corresponding scale value;

[0444] Based on the scale values, at least one judgment matrix corresponding to each level is constructed, wherein any row or column in any judgment matrix is composed of the relative importance of any object in the corresponding level to all objects in the current level with respect to any object in the previous level.

[0445] As a possible implementation manner of the embodiment of the present application, the processor 930 is further configured to perform the following operation:

[0446] For any judgment matrix, based on the maximum eigenvalue corresponding to the judgment matrix and the order of the judgment matrix, a consistency index corresponding to the judgment matrix is determined;

[0447] According to a preset correspondence between the order and the average consistency index, based on the order of the judgment matrix, an average consistency index corresponding to the judgment matrix is determined;

[0448] Based on the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix, a consistency check coefficient corresponding to the judgment matrix is determined, so that the judgment matrix passes the consistency check in the case that the consistency check coefficient is less than a third set value;

[0449] In the case that the consistency checks of all the judgment matrices pass, based on the eigenvector corresponding to the target judgment matrix, a weight matrix corresponding to the corresponding level is determined, wherein the target judgment matrix is at least one judgment matrix corresponding to any level in the hierarchical structure model except the highest level;

[0450] Based on the weight matrix corresponding to each level, the weight of at least one object included in each level in the hierarchical structure model except the highest level with respect to the decision target is determined.

[0451] As a possible implementation manner of the embodiment of the present application, the processor 930 is further configured to perform the following operation:

[0452] The difference between the maximum eigenvalue corresponding to the judgment matrix and the order of the judgment matrix is determined as a first intermediate value;

[0453] The difference between the order of the judgment matrix and a fourth set value is determined as a second intermediate value;

[0454] The ratio between the first intermediate value and the second intermediate value is determined as the consistency index corresponding to the judgment matrix.

[0455] As a possible implementation manner of the embodiment of the present application, the processor 930 is further configured to perform the following operation:

[0456] The ratio between the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix is determined as the consistency check coefficient corresponding to the judgment matrix.

[0457] As one possible implementation of this application embodiment, the processor 930 is also configured to perform the following operations:

[0458] For any level, if there is at least one non-highest level above the level, the weight matrix corresponding to the level is multiplied by the weight matrices corresponding to each non-highest level above the level to obtain the target weight matrix corresponding to the level. Alternatively, if there is no non-highest level above the level, the weight matrix corresponding to the level is determined as the target weight matrix corresponding to the level. The target weight matrix is ​​composed of the weights of at least one object contained in the corresponding level with respect to the decision objective.

[0459] Based on the target weight matrix corresponding to each level, determine the weight of at least one object in each level with respect to the decision objective.

[0460] It should be noted that the apparatus provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0461] To achieve the above embodiments, this application also provides an adaptive evaluation device for intelligent hierarchical classification of communication networks.

[0462] Figure 10 This is a schematic diagram of the adaptive evaluation device for intelligent hierarchical classification of communication networks provided according to the ninth embodiment of this application.

[0463] like Figure 2 to Figure 8 As shown, the adaptive evaluation device for intelligent hierarchical classification of the communication network includes: a first processing unit 11, a second processing unit 12, and a first determination unit 13.

[0464] The first processing unit 11 is used to establish a hierarchical structure model of the target communication network and determine the weight of at least one object in each level of the hierarchical structure model with respect to the decision target. The hierarchical structure model includes multiple levels.

[0465] The second processing unit 12 is used to construct a fuzzy evaluation matrix based on the evaluations of multiple experts on at least one target object contained in the target level of the hierarchical structure model, so as to determine the fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix.

[0466] The first determining unit 13 is used to determine the system performance evaluation result of the target communication network based on the weight of each target object with respect to the decision objective and the fuzzy evaluation value corresponding to each target object.

[0467] Optionally, in one possible implementation of this application embodiment, the above-mentioned apparatus further includes:

[0468] The second determining unit is configured to determine the ranking result of the target communication network based on the weights of the target objects with respect to the decision target.

[0469] Optionally, in a possible implementation manner of the embodiment of the present application, the second determining unit is further configured to:

[0470] sort the target objects according to the weights of the target objects with respect to the decision target, and determine the ranking result of the target communication network based on the sorting result.

[0471] Optionally, in a possible implementation manner of the embodiment of the present application, the first determining unit 13 further includes:

[0472] The first determining module is configured to determine the performance contribution value of each target object to the target communication network based on the weight of each target object with respect to the decision target and the fuzzy evaluation value corresponding to each target object.

[0473] The second determining module is configured to determine the system performance evaluation result of the target communication network based on the performance contribution value of each target object to the target communication network.

[0474] Optionally, in a possible implementation manner of the embodiment of the present application, the first determining module is further configured to:

[0475] for any target object, multiply the weight of the target object with respect to the decision target by the fuzzy evaluation value corresponding to the target object to obtain a performance contribution fuzzy value of the target object to the target communication network;

[0476] determine the performance contribution value of the target object to the target communication network based on the performance contribution fuzzy value of the target object to the target communication network.

[0477] Optionally, in a possible implementation manner of the embodiment of the present application, the fuzzy evaluation value corresponding to the target object is a triangular fuzzy evaluation value, the triangular fuzzy evaluation value is composed of three first parameters, the three first parameters include a first fuzzy evaluation value, a second fuzzy evaluation value and a third fuzzy evaluation value, and correspondingly, the performance contribution fuzzy value of the target object to the target communication network is a performance contribution triangular fuzzy value, the performance contribution triangular fuzzy value is composed of three second parameters, the three second parameters include a first performance contribution triangular fuzzy value, a second performance contribution triangular fuzzy value and a third performance contribution triangular fuzzy value.

[0478] The first determining module is further configured to:

[0479] The weight of the target object with respect to the decision target is multiplied by the first fuzzy evaluation value, the second fuzzy evaluation value and the third fuzzy evaluation value corresponding to the target object respectively to obtain a first performance contribution triangular fuzzy value, a second performance contribution triangular fuzzy value and a third performance contribution triangular fuzzy value of the target object to the target communication network.

[0480] Optionally, in a possible implementation manner of the embodiment of the present application, the first determining module is further configured to:

[0481] The sum of the first performance contribution triangular fuzzy value, the second performance contribution triangular fuzzy value multiplied by the set multiple and the third performance contribution triangular fuzzy value is determined as the performance contribution intermediate value.

[0482] The ratio between the performance contribution intermediate value and the first set numerical value is determined as the performance contribution value of the target object to the target communication network.

[0483] Optionally, in a possible implementation manner of the embodiment of the present application, the second determining module is further configured to:

[0484] The sum of the performance contribution values of the target objects to the target communication network is determined as the system performance evaluation result of the target communication network.

[0485] Optionally, in a possible implementation manner of the embodiment of the present application, the second processing unit 12 further includes:

[0486] The conversion module is configured to convert the evaluation of each expert on at least one target object contained in the target level in the hierarchical structure model into a corresponding fuzzy decision number based on a preset corresponding relationship between the evaluation and the fuzzy decision number.

[0487] The first constructing module is configured to construct a fuzzy evaluation matrix based on the fuzzy decision numbers, wherein any row or column in the fuzzy evaluation matrix is composed of the fuzzy decision numbers corresponding to the evaluation of any target object by each expert.

[0488] The third determining module is configured to determine the fuzzy evaluation value corresponding to the corresponding target object based on any row or column in the fuzzy evaluation matrix.

[0489] Optionally, in a possible implementation manner of the embodiment of the present application, the third determining module is further configured to:

[0490] The ratio between the sum of the fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts is determined as the fuzzy evaluation value corresponding to the corresponding target object.

[0491] Optionally, in a possible implementation manner of the embodiment of the present application, the fuzzy decision number is a triangular fuzzy decision number, the triangular fuzzy decision number is composed of three third parameters, the three third parameters include the first fuzzy decision number, the second fuzzy decision number and the third fuzzy decision number, and correspondingly, the fuzzy evaluation value is a triangular fuzzy evaluation value, the triangular fuzzy evaluation value is composed of three first parameters, the three first parameters include the first fuzzy evaluation value, the second fuzzy evaluation value and the third fuzzy evaluation value.

[0492] The third determining module is further configured to:

[0493] determine a ratio between the sum of the first fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the first fuzzy evaluation value corresponding to the target object;

[0494] determine a ratio between the sum of the second fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the second fuzzy evaluation value corresponding to the target object;

[0495] determine a ratio between the sum of the third fuzzy decision numbers in any row or column in the fuzzy evaluation matrix and the number of experts as the third fuzzy evaluation value corresponding to the target object.

[0496] Optionally, in a possible implementation manner of the embodiment of the present application, the first processing unit 11 is further configured to:

[0497] establish a hierarchical structure model of the target communication network and determine the weight of at least one object included in each level of the hierarchical structure model with respect to the decision target by using the analytic hierarchy process.

[0498] Optionally, in a possible implementation manner of the embodiment of the present application, the weight of the object included in the highest level of the hierarchical structure model with respect to the decision target is a second set value.

[0499] The first processing unit 11 further includes:

[0500] The establishing module is configured to establish a hierarchical structure model of the target communication network based on the mutual relationship among the decision target, the decision criteria and the decision scheme.

[0501] The second constructing module is configured to construct at least one judgment matrix corresponding to each level based on the relative importance of any two objects in each level of the hierarchical structure model to any object in the previous level.

[0502] The processing module is configured to perform consistency check on each judgment matrix, so as to determine the weight of at least one object included in each level of the hierarchical structure model except the highest level with respect to the decision target based on each judgment matrix in the case that the consistency check on each judgment matrix is passed.

[0503] Optionally, in a possible implementation manner of the embodiment of the present application, the apparatus further includes:

[0504] The reconstruction unit is configured to reconstruct the judgment matrix in a case where the consistency check of any judgment matrix fails.

[0505] Optionally, in a possible implementation manner of the embodiment of the present application, the second construction module is further configured to:

[0506] convert, based on a preset element scale mode of the judgment matrix, the relative importance of any two objects in each level of the hierarchical structure model to any object in the previous level into a corresponding scale value;

[0507] construct at least one judgment matrix corresponding to each level based on the scale values, wherein any row or column in any judgment matrix is composed of the relative importance of any object in the corresponding level to any object in the previous level compared with all objects in the current level.

[0508] Optionally, in a possible implementation manner of the embodiment of the present application, the processing module is further configured to:

[0509] determine, for any judgment matrix, a consistency index corresponding to the judgment matrix based on a maximum eigenvalue corresponding to the judgment matrix and an order of the judgment matrix;

[0510] determine, based on the order of the judgment matrix, an average consistency index corresponding to the judgment matrix according to a preset correspondence between the order and the average consistency index;

[0511] determine, based on the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix, a consistency check coefficient corresponding to the judgment matrix, so as to determine that the consistency check of the judgment matrix passes in a case where the consistency check coefficient is less than a third preset value;

[0512] determine, based on an eigenvector corresponding to a target judgment matrix, a weight matrix corresponding to the corresponding level in a case where the consistency check of each judgment matrix passes, wherein the target judgment matrix is at least one judgment matrix corresponding to any level of the hierarchical structure model except the highest level;

[0513] determine the weight of at least one object included in each level of the hierarchical structure model except the highest level with respect to the decision target based on the weight matrix corresponding to each level.

[0514] Optionally, in a possible implementation manner of the embodiment of the present application, the processing module is further configured to:

[0515] determine a first intermediate value as a difference between the maximum eigenvalue corresponding to the judgment matrix and the order of the judgment matrix.

[0516] determining a difference between the order of the judgment matrix and the fourth set value as a second intermediate value;

[0517] determining a ratio between the first intermediate value and the second intermediate value as a consistency index corresponding to the judgment matrix.

[0518] Optionally, in a possible implementation manner of the embodiment of the present application, the processing module is further configured to:

[0519] determining a ratio between the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix as a consistency check coefficient corresponding to the judgment matrix.

[0520] Optionally, in a possible implementation manner of the embodiment of the present application, the processing module is further configured to:

[0521] for any level, multiplying the weight matrix corresponding to the level and the weight matrix corresponding to each upper level of the at least one non-highest level, to obtain a target weight matrix corresponding to the level, or, in the case that the level does not have at least one upper level of the non-highest level, determining the weight matrix corresponding to the level as the target weight matrix corresponding to the level, wherein the target weight matrix is composed of the weights of the at least one object included in the corresponding level with respect to the decision target;

[0522] determining the weights of the at least one object included in each level with respect to the decision target based on the target weight matrix corresponding to each level.

[0523] It should be noted that the division of units in the embodiments of the present application is illustrative, and is merely a logical function division. In actual implementation, another division manner can be used. In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0524] The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a processor-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0525] It should be noted that the above-mentioned device provided by the embodiments of the present application can realize all the method steps realized by the above-mentioned method embodiments and achieve the same technical effects. Therefore, the same parts and beneficial effects of the method embodiments will not be described in detail.

[0526] In order to realize the above-mentioned embodiments, the present application further provides a processor-readable storage medium. The processor-readable storage medium stores a computer program, and the computer program is used to make the processor execute the method of the present application Figure 2 to Figure 8 The adaptive evaluation method of the intelligent classification of the communication network of any embodiment.

[0527] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to a magnetic memory (such as a floppy disk, a hard disk, a magnetic tape, a magneto-optical disk (MO), etc.), an optical memory (such as a CD, a DVD, a BD, a HVD, etc.), and a semiconductor memory (such as a ROM, an EPROM, an EEPROM, a non-volatile memory (NAND FLASH), a solid-state hard disk (SSD)), etc.

[0528] In order to realize the above-mentioned embodiments, the present application further provides a computer program product, including a computer program, which, when executed by a processor, realizes the method of the present application Figure 1 The adaptive evaluation method of the intelligent classification of the communication network of any embodiment.

[0529] Those skilled in the art will appreciate that embodiments of the present application can be readily used as software, hardware, or a combination of software and hardware. In one

[0530] The present application is described in reference to the flow diagrams and / or block diagrams of the methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer executable instructions. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 an apparatus to perform the functions specified in the flow diagram and / or block diagram block or blocks.

[0531] These processor-executable instructions can also be loaded onto a computer or other programmable data processing devices, so that a series of operations are performed on the computer or other programmable data devices to produce a computer-implemented process such that the instructions executed on the computer or other programmable devices provide steps for implementing the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 an apparatus to perform the functions specified in the flow diagram and / or block diagram block or blocks.

[0532] These processor-executable instructions can also be loaded onto a computer or other programmable data processing devices, so that a series of operations are performed on the computer or other programmable data devices to produce a computer-implemented process such that the instructions executed on the computer or other programmable devices provide steps for implementing the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. ​ an apparatus to perform the functions specified in the flow diagram and / or block diagram block or blocks.

[0533] Obviously, various modifications and changes can be made to the present application by those skilled in the art without departing from the spirit and scope of the present application. Accordingly, it is intended that the present application embrace all such modifications and changes that fall within the scope of the appended claims and their equivalents.

Claims

1. An adaptive evaluation method for intelligent hierarchical classification of communication networks, characterized in that, include: Establish a hierarchical structure model of the target communication network and determine the weight of at least one object in each level of the hierarchical structure model with respect to the decision objective, wherein the hierarchical structure model includes multiple levels; Based on the evaluations of at least one target object contained in the target level of the hierarchical model by multiple experts, a fuzzy evaluation matrix is ​​constructed to determine the fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix. Based on the weights of each target object with respect to the decision objective and the fuzzy evaluation values ​​corresponding to each target object, the system performance evaluation results of the target communication network are determined.

2. The method according to claim 1, characterized in that, The method further includes: The classification result of the target communication network is determined based on the weight of each target object with respect to the decision objective.

3. The method according to claim 2, characterized in that, The step of determining the hierarchical result of the target communication network based on the weights of each target object with respect to the decision objective includes: The target objects are sorted according to their weight relative to the decision objective, and the hierarchical result of the target communication network is determined based on the sorting result.

4. The method according to claim 1, characterized in that, The determination of the system performance evaluation result of the target communication network based on the weights of each target object with respect to the decision objective and the fuzzy evaluation values ​​corresponding to each target object includes: Based on the weights of each target object with respect to the decision objective and the fuzzy evaluation values ​​corresponding to each target object, the performance contribution value of each target object to the target communication network is determined. Based on the performance contribution of each target object to the target communication network, the system performance evaluation result of the target communication network is determined.

5. The method according to claim 4, characterized in that, The step of determining the performance contribution value of each target object to the target communication network based on the weight of each target object with respect to the decision objective and the fuzzy evaluation value corresponding to each target object includes: For any of the target objects, the weight of the target object with respect to the decision objective is multiplied by the fuzzy evaluation value corresponding to the target object to obtain the fuzzy value of the target object's performance contribution to the target communication network. Based on the fuzzy value of the target object's performance contribution to the target communication network, the performance contribution value of the target object to the target communication network is determined.

6. The method according to claim 5, characterized in that, The fuzzy evaluation value corresponding to the target object is a triangular fuzzy evaluation value, which is composed of three first parameters, namely a first fuzzy evaluation value, a second fuzzy evaluation value, and a third fuzzy evaluation value. Correspondingly, the fuzzy value of the target object's performance contribution to the target communication network is a performance contribution triangular fuzzy value, which is composed of three second parameters, namely a first performance contribution triangular fuzzy value, a second performance contribution triangular fuzzy value, and a third performance contribution triangular fuzzy value. The step of multiplying the weight of the target object with respect to the decision objective by the fuzzy evaluation value corresponding to the target object to obtain the fuzzy value of the target object's performance contribution to the target communication network includes: The weight of the target object with respect to the decision objective is multiplied by the first fuzzy evaluation value, the second fuzzy evaluation value, and the third fuzzy evaluation value corresponding to the target object, respectively, to obtain the first efficiency contribution triangle fuzzy value, the second efficiency contribution triangle fuzzy value, and the third efficiency contribution triangle fuzzy value of the target object to the target communication network.

7. The method according to claim 6, characterized in that, The step of determining the performance contribution value of the target object to the target communication network based on the fuzzy value of the performance contribution of the target object to the target communication network includes: The sum of the first performance contribution triangle fuzzy value, the second performance contribution triangle fuzzy value (at a set multiple), and the third performance contribution triangle fuzzy value is determined as the performance contribution median value. The ratio between the median value of the performance contribution and the first set value is determined as the performance contribution value of the target object to the target communication network.

8. The method according to claim 4, characterized in that, The determination of the system performance evaluation result of the target communication network based on the performance contribution value of each target object to the target communication network includes: The sum of the performance contributions of each of the target objects to the target communication network is determined as the system performance evaluation result of the target communication network.

9. The method according to claim 1, characterized in that, The step of constructing a fuzzy evaluation matrix based on the evaluations of at least one target object contained in the target level of the hierarchical model by multiple experts, and determining the fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix, includes: Based on the pre-defined correspondence between evaluations and fuzzy decision numbers, the evaluations of each expert on at least one target object contained in the target level of the hierarchical model are converted into corresponding fuzzy decision numbers. Based on the fuzzy decision numbers, a fuzzy evaluation matrix is ​​constructed, wherein any row or column of the fuzzy evaluation matrix is ​​composed of the fuzzy decision numbers corresponding to the evaluations of each expert on any target object; Based on any row or column in the fuzzy evaluation matrix, determine the fuzzy evaluation value corresponding to the target object.

10. The method according to claim 9, characterized in that, Determining the fuzzy evaluation value corresponding to the target object based on any row or column of the fuzzy evaluation matrix includes: The ratio between the sum of the fuzzy decision numbers in any row or column of the fuzzy evaluation matrix and the number of experts is determined as the fuzzy evaluation value corresponding to the target object.

11. The method according to claim 10, characterized in that, The fuzzy decision number is a triangular fuzzy decision number, which is composed of three third parameters, namely a first fuzzy decision number, a second fuzzy decision number, and a third fuzzy decision number. Correspondingly, the fuzzy evaluation value is a triangular fuzzy evaluation value, which is composed of three first parameters, namely a first fuzzy evaluation value, a second fuzzy evaluation value, and a third fuzzy evaluation value. The step of determining the ratio between the sum of the fuzzy decision numbers in any row or column of the fuzzy evaluation matrix and the number of experts as the fuzzy evaluation value corresponding to the target object includes: The ratio between the sum of the first fuzzy decision numbers in any row or column of the fuzzy evaluation matrix and the number of experts is determined as the first fuzzy evaluation value corresponding to the target object. The ratio between the sum of the second fuzzy decision numbers in any row or column of the fuzzy evaluation matrix and the number of experts is determined as the second fuzzy evaluation value corresponding to the target object; The ratio between the sum of the third fuzzy decision numbers in any row or column of the fuzzy evaluation matrix and the number of experts is determined as the third fuzzy evaluation value corresponding to the target object.

12. The method according to claim 1, characterized in that, The establishment of the hierarchical structure model of the target communication network and the determination of the weights of at least one object in each level of the hierarchical structure model with respect to the decision objective include: Using the analytic hierarchy process (AHP), a hierarchical structure model of the target communication network is established, and the weight of at least one object in each level of the hierarchical structure model with respect to the decision objective is determined.

13. The method according to claim 12, characterized in that, The weight of the objects contained in the highest level of the hierarchical model with respect to the decision objective is a second predetermined value; The step of employing the analytic hierarchy process (AHP) to establish a hierarchical structure model of the target communication network and determining the weights of at least one object in each level of the hierarchical structure model with respect to the decision objective includes: Based on the interrelationships between the decision objectives, decision criteria, and decision schemes, a hierarchical structure model of the target communication network is established. Based on the relative importance of any two objects in each of the hierarchical structure models (excluding the highest level) to any object in the previous level, at least one judgment matrix is ​​constructed for each level. A consistency check is performed on each of the judgment matrices. If the consistency check of each judgment matrix passes, the weight of at least one object in each of the hierarchical structure models, excluding the highest level, is determined with respect to the decision objective based on each judgment matrix.

14. The method according to claim 13, characterized in that, The method further includes: If any of the aforementioned judgment matrices fails the consistency check, the judgment matrix shall be reconstructed.

15. The method according to claim 13, characterized in that, The step of constructing at least one judgment matrix corresponding to each of the hierarchical levels (excluding the highest level) based on the relative importance of any two objects in each level with respect to any object in the next higher level includes: Based on the element scaling method of the preset judgment matrix, the relative importance of any two objects in each level of the hierarchical structure model, except for the highest level, with respect to any object in the previous level, is converted into corresponding scale values. Based on each of the scale values, at least one judgment matrix is ​​constructed corresponding to each of the levels, wherein any row or column in any of the judgment matrices consists of the relative importance of any object in the corresponding level compared to all objects in the current level with respect to any object in the previous level.

16. The method according to claim 13, characterized in that, The step of performing consistency checks on each of the judgment matrices, so that if the consistency checks on each of the judgment matrices all pass, determines the weight of at least one object in each of the hierarchical structure models (excluding the highest level) with respect to the decision objective based on each of the judgment matrices, includes: For any of the judgment matrices, a consistency index is determined based on the largest eigenvalue corresponding to the judgment matrix and the order of the judgment matrix. Based on the preset correspondence between the order and the average consistency index, the average consistency index corresponding to the judgment matrix is ​​determined according to the order of the judgment matrix. Based on the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix, the consistency verification coefficient corresponding to the judgment matrix is ​​determined, so that if the consistency verification coefficient is less than a third set value, the consistency verification of the judgment matrix is ​​determined to be passed. If the consistency check of each judgment matrix passes, the weight matrix corresponding to the corresponding level is determined based on the feature vector corresponding to the target judgment matrix. The target judgment matrix is ​​at least one judgment matrix corresponding to any level in the hierarchical structure model except the highest level. Based on the weight matrix corresponding to each level, determine the weight of at least one object in each level of the hierarchical structure model, excluding the highest level, with respect to the decision objective.

17. The method according to claim 16, characterized in that, The step of determining the consistency index corresponding to the judgment matrix based on the largest eigenvalue corresponding to the judgment matrix and the order of the judgment matrix includes: The difference between the largest eigenvalue corresponding to the judgment matrix and the order of the judgment matrix is ​​determined as the first intermediate value; The difference between the order of the judgment matrix and the fourth set value is determined as the second intermediate value; The ratio between the first intermediate value and the second intermediate value is determined as the consistency index corresponding to the judgment matrix.

18. The method according to claim 16, characterized in that, The step of determining the consistency verification coefficient corresponding to the judgment matrix based on the consistency index and average consistency index corresponding to the judgment matrix includes: The ratio between the consistency index corresponding to the judgment matrix and the average consistency index corresponding to the judgment matrix is ​​determined as the consistency verification coefficient corresponding to the judgment matrix.

19. The method according to claim 16, characterized in that, The step of determining the weight of at least one object in each of the hierarchical structure models, excluding the highest level, with respect to the decision objective based on the weight matrix corresponding to each level includes: For any of the aforementioned levels, if the level has at least one non-highest level above it, the weight matrix corresponding to the level is multiplied by the weight matrix corresponding to each non-highest level above it to obtain the target weight matrix corresponding to the level. Alternatively, if the level does not have at least one non-highest level above it, the weight matrix corresponding to the level is determined as the target weight matrix corresponding to the level. The target weight matrix is ​​composed of the weights of at least one object contained in the corresponding level with respect to the decision objective. Based on the target weight matrix corresponding to each level, determine the weight of at least one object contained in each level with respect to the decision objective.

20. An adaptive evaluation device for intelligent hierarchical classification of communication networks, characterized in that, Includes memory, transceiver, and processor: A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: Establish a hierarchical structure model of the target communication network and determine the weight of at least one object in each level of the hierarchical structure model with respect to the decision objective, wherein the hierarchical structure model includes multiple levels; Based on the evaluations of at least one target object contained in the target level of the hierarchical model by multiple experts, a fuzzy evaluation matrix is ​​constructed to determine the fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix. Based on the weights of each target object with respect to the decision objective and the fuzzy evaluation values ​​corresponding to each target object, the system performance evaluation results of the target communication network are determined.

21. An adaptive evaluation device for intelligent hierarchical classification of communication networks, characterized in that, include: The first processing unit is used to establish a hierarchical structure model of the target communication network and determine the weight of at least one object in each level of the hierarchical structure model with respect to the decision target, wherein the hierarchical structure model includes multiple levels. The second processing unit is used to construct a fuzzy evaluation matrix based on the evaluations of at least one target object contained in the target level of the hierarchical model by multiple experts, so as to determine the fuzzy evaluation value corresponding to each target object based on the fuzzy evaluation matrix. The first determining unit is used to determine the system performance evaluation result of the target communication network based on the weight of each target object with respect to the decision objective and the fuzzy evaluation value corresponding to each target object.

22. A processor-readable storage medium, characterized in that, The processor-readable storage medium stores a computer program for causing the processor to perform the method of any one of claims 1 to 19.

Images