An Equipment Evaluation Index System Based on Intelligent Learning, Its Construction Method and Application

Abstract

The present invention discloses an equipment evaluation index system based on intelligent learning, its construction method and application, belonging to the technical field of information processing. The construction method includes the following steps: Step 1. Establish an equipment index feature extraction model according to the equipment capability description materials; Step 2. Establish a task evaluation index model based on the tree-like analysis strategy; Step 3. Establish a consistency test and confirmation model for the evaluation index system; Step 4. Establish an adjustment and optimization model for the evaluation index system. This method learns from the description materials of the evaluation object, establishes a specification for describing the quality of the index, extracts index features based on semantic association analysis, and obtains the index system of the evaluation object. There is no need for the artificial intervention of domain experts in the middle, which can ensure that the constructed index system objectively reflects the problems of the evaluation object and can be used for the ability evaluation of equipment. It has the advantages of high automation degree, high efficiency in constructing the index system, and economic applicability.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and particularly relates to an equipment evaluation index system based on intelligent learning, a construction method thereof, and an application thereof. Background Art

[0002] With the continuous development of technology, modern equipment has become increasingly sophisticated and complex. These equipments include, but are not limited to, the mechanical systems, electronic systems composed of themselves, and software systems for realizing the functions of the equipment. Sometimes, they may also be composed of only some of them. For example, a large software system is only composed of software. These equipments have complex structures, diverse functions, and high manufacturing costs. Before being put into service, a special evaluation system generally needs to be constructed to effectively evaluate the equipment to test its operating performance.

[0003] In the current construction process of the evaluation index system, generally, methods such as brainstorming, group decision-making, and Delphi method are first adopted to list all possible evaluation index sets, then the indexes are screened to find out important indexes, and finally the index weights are set by methods such as the analytic hierarchy process. The method process for constructing the index system includes three steps: initial construction of indexes, screening of indexes, and determination of weights. In the existing methods for constructing the index system, there are disadvantages of strong subjectivity and low construction efficiency. Strong subjectivity. Domain experts put forward evaluation indexes of the evaluation object based on their own knowledge and experience, which is highly subjective. Or when modifying the previous indexes, there is also a situation that is not completely consistent with the objective evaluation object; low construction efficiency. Traditional brainstorming or group decision-making methods are all based on the work of domain expert groups. Specific evaluation objects need to be analyzed specifically, and multiple rounds of work such as initial construction, screening, and weight assignment are required, resulting in low construction efficiency of the index system. At the same time, the traditional construction of the equipment evaluation index system for equipment capabilities mainly determines the influencing factors of the evaluation object and constructs the equipment evaluation index system through methods such as brainstorming and expert consultation, based on the domain knowledge and experience of experts in the equipment field. This traditional method is often affected by the subjective factors and knowledge backgrounds of experts themselves, and the obtained equipment evaluation index system is not objective enough, and it is inevitable that there will be situations inconsistent with the actual situation.

[0004] In view of the above problems, it is urgent to design an equipment evaluation index system based on intelligent learning to solve the problems existing in the above-mentioned prior art. Summary of the Invention

[0005] In view of the above existing problems, the present invention aims to provide an equipment evaluation index system based on intelligent learning, a construction method thereof, and an application thereof. This method learns from the description materials of the evaluation object, establishes a specification for describing the quality of indexes, extracts index features based on semantic association analysis, and obtains the index system of the evaluation object. There is no need for artificial intervention by domain experts in the middle, which can ensure that the constructed index system objectively reflects the problems of the evaluation object.

[0006] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] A method for constructing an equipment evaluation index system based on intelligent learning, comprising

[0008] Step 1. Establish an equipment index feature extraction model according to the equipment ability description materials;

[0009] Step 2. Establish a task evaluation index model based on a tree-like analysis strategy;

[0010] Step 3. Establish a consistency test and confirmation model for the evaluation index system;

[0011] Step 4. Establish an adjustment and optimization model for the evaluation index system.

[0012] Preferably, the establishment process of the equipment index feature extraction model described in Step 1 includes

[0013] Defining the index of equipment quality as an ordered set of semantic elements describing the equipment quality index, and obtaining the index semantic specification of equipment quality as:

[0014] <Index> ::= <Equipment Name><Index Description><Index Quantification> (1)

[0015] According to the equipment index semantic specification, retrieve and analyze to form the index representation of the equipment, denoted as:

[0016] Q = {C, E, P} (2)

[0017] Where: C is the ability index representation, represented by the ability index semantic specification formula (3); E is the effectiveness index representation, represented by the effectiveness index semantic specification formula (4); P is the performance index representation, represented by the performance index semantic specification formula (5);

[0018] <Ability Index> ::= <Equipment Name><Ability Description><Ability Quantification> (3)

[0019] <Effectiveness Index> ::= <Equipment Name><Effectiveness Description><Effectiveness Quantification> (4)

[0020] <Performance Index> ::= <Equipment Name><Performance Description><Performance Quantification> (5).

[0021] Preferably, the establishment process of the task evaluation index model described in Step 2 includes Step 21. First, establish an evaluation index hierarchy structure and construct a framework for the evaluation index system:

[0022] IA(r) = {I t} (6)

[0023] where: r ∈ R; t = 1, 2, ..., r; r is the number of levels of the indicators; I t is the set of indicators at the t-th level,

[0024] I t = {IF i , m; IS ij , n i} (7)

[0025] where: i = 1, 2, …, m; j = 1, 2, …, n i ;

[0026] In the formula: IF i is the i-th parent indicator; m is the total number of indicators at the t-th level; IS ij is the j-th sub-indicator of the i-th parent indicator; n i is the total number of sub-indicators of the i-th parent indicator;

[0027] Step 22. According to the description of the equipment evaluation task materials, select the indicator requirements of the equipment and establish an evaluation indicator system for a specific evaluation task:

[0028] IA(3) = {I1, I2, I3} (8)

[0029] I1 = {IF i , m; IS ij , n i} (9)

[0030] where: IF i ∈ C, IS ij ∈ E, i = 1, 2, …, m, j = 1, 2, …, n i ; m is the number of equipment capability indicators; n i is the number of sub-indicators of the i-th equipment capability indicator;

[0031] I2 = {IF i , s; IS ij , t i} (10)

[0032] where: IF i ∈ E, IS ij ∈ P, i = 1, 2, …, s, j = 1, 2, …, t i ; s is the number of equipment effectiveness indicators; t i is the number of sub-indicators of the i-th equipment effectiveness indicator;

[0033]

[0034] where: IF i ∈ P, i = 1, 2, …, u, is an empty set; u is the total number of equipment performance indicators.

[0035] Preferably, the consistency test and confirmation model of the evaluation index system described in step 3 includes an independent consistency test model and an aggregation consistency test model.

[0036] Preferably, the establishment process of the independent consistency test model includes

[0037] (1) Establish an independent consistency check matrix:

[0038]

[0039] where d ij The value-taking rule is as follows:

[0040]

[0041] In the formula: When conducting an independent consistency test on the ability index set, indicators i and j belong to IFi in formula (9), i, j ∈ {IF1, IF2,..., IF m}; When conducting an independent consistency test on the effectiveness index set, indicators i and j belong to IFi in formula (10), i, j ∈ {IF1, IF2,..., IF s}; When conducting an independent consistency test on the performance index set, indicators i and j belong to IFi in formula (11), i, j ∈ {IF1, IF2,..., IF u};

[0042] (2) Define the independent consistency factor α, and the calculation formula is as follows

[0043]

[0044]

[0045] Preferably, the establishment process of the aggregation consistency test model includes

[0046] (1) Establish an aggregation consistency check matrix:

[0047]

[0048] When checking the aggregation consistency of effectiveness indicators and ability indicators, i takes the sub-indicator IS of formula (9) ij , and j takes the parent indicator IF of formula (9) i , such as

[0049]

[0050] When checking the aggregation consistency of performance indicators and effectiveness indicators, i takes the sub-indicator IS of formula (10) ij, the value of j takes the parent index IF of formula (10) i , such as

[0051]

[0052] where h ij The value-taking rule is as follows:

[0053]

[0054] (2) Define the aggregation consistency factor, and the calculation formula is as

[0055]

[0056]

[0057] Preferably, the establishment process of the evaluation index system adjustment and optimization model described in step 4 includes

[0058] Step 41. The correction amount of the independent consistency test is:

[0059] δ1 = α - α0 (22)

[0060] where α0 is the reference standard value of the independent consistency factor;

[0061] Step 42. The correction amount of the aggregation consistency test is:

[0062] δ2 = β - β0 (23)

[0063] where β0 is the reference standard value of the aggregation consistency factor.

[0064] An equipment evaluation index system based on intelligent learning includes

[0065] An equipment index feature extraction model, which is used to extract the equipment evaluation index features based on natural language preprocessing for the equipment product description materials through the processes of Chinese word segmentation, part-of-speech screening, and feature extraction;

[0066] A task evaluation index model, which is used to establish an evaluation index system for a specific evaluation task through the processes of index system framework, evaluation task identification, and task evaluation index system establishment for the evaluation task description materials;

[0067] A consistency test confirmation model, which is used to perform an independent consistency check on the parent indexes of the ability index set, effectiveness index set, and performance index set of the evaluation index system; perform an aggregation consistency check on the effectiveness index and ability index, and the performance index and effectiveness index respectively;

[0068] An evaluation index system adjustment and optimization model, which is used to based on the consistency test correction amount according to the results of the independent consistency and aggregation consistency checks of the evaluation indexes;

[0069] Among them, the equipment index feature extraction model, task evaluation index model, consistency verification and confirmation model, and evaluation index system adjustment and optimization model are established based on the construction method of the equipment evaluation index system of intelligent learning.

[0070] An application of an equipment evaluation index system based on intelligent learning, where the evaluation index system is used for the ability evaluation of equipment.

[0071] Preferably, the process of using the evaluation index system for the ability evaluation of equipment includes

[0072] Step S1. Input the equipment quality description file, retrieve the input file using semantic association technology, and obtain the index representation of the equipment.

[0073] Step S2. Input the equipment index representation, decompose the index requirements using tree analysis technology, and obtain the equipment index system.

[0074] Step S3. Input the equipment evaluation requirement file and the input equipment index system, and respectively output the index system framework, ability index set, effectiveness index set, and performance index set as the initial index system set.

[0075] Step S4. Input the ability index set, effectiveness index set, and performance index set, and respectively perform independent consistency verification to check whether the indicators at the same level meet the requirements of independence and completeness, and calculate the independent consistency factor.

[0076] Step S5. Input the ability index set and effectiveness index set, and respectively perform aggregation consistency verification to check whether the sub-indicators to the parent indicators meet the aggregation requirements, and calculate the aggregation consistency factor.

[0077] Step S6. Calculate the consistency verification correction amount, adjust and optimize the ability index set, effectiveness index set, and performance index set, and determine whether the consistency verification correction amount tends to zero. Otherwise, go back to Step S3 to perform reduction and optimization adjustment on the ability index set, effectiveness index set, and performance index set.

[0078] Step S7. Output the evaluation index system for a specific evaluation task to obtain the equipment ability evaluation index system IA(r).

[0079] The beneficial effects of the present invention are: The present invention discloses an equipment evaluation index system based on intelligent learning, its construction method and application. Compared with the prior art, the improvements of the present invention are as follows:

[0080] 1. The present invention proposes a method for constructing an equipment evaluation index system based on intelligent learning. This method learns from the description materials of the evaluation object, establishes a specification for describing the quality of indicators, extracts indicator features based on semantic association analysis, and obtains the indicator system of the evaluation object. There is no need for manual intervention by domain experts in the middle, which can effectively ensure that the constructed indicator system can objectively reflect the problems of the evaluation object. At the same time, based on the text learning of the domain knowledge of the evaluation object, this method intelligently establishes, tests, and optimizes indicators, and does not require the knowledge and experience of domain experts to establish and screen indicators.

[0081] 2. The present invention proposes an equipment evaluation index system, including an equipment indicator feature extraction model, a task evaluation index model, a consistency verification and confirmation model, and an evaluation index system adjustment and optimization model. When in use, the above modules can be used to process the input equipment quality description file, and automatically obtain the equipment ability evaluation index system, which has the advantages of high automation, high efficiency in constructing the index system, and being economical and applicable. Brief Description of the Drawings

[0082] Figure 1 It is a flow chart of the intelligent construction method of the evaluation index system of the present invention.

[0083] Figure 2 It is an application flow chart of the index system of the present invention. Detailed Embodiments

[0084] In order to enable ordinary technicians in the field to better understand the technical solutions of the present invention, the technical solutions of the present invention will be further described below in conjunction with the drawings and embodiments.

[0085] Example 1: Refer to the Figure 1 - Figure 2 shown method for constructing an equipment evaluation index system based on intelligent learning. The purpose of this method is to construct an equipment evaluation index system based on intelligent learning for evaluating the capabilities of equipment. Evaluation index system: It refers to an organic whole with an internal structure composed of multiple indicators that characterize various aspects of the evaluation object and their interrelationships. The specific process includes

[0086] Step 1. According to the equipment ability description materials, establish an equipment indicator feature extraction model

[0087] The equipment product description materials are descriptions of the uses and operating conditions of the equipment. The indicators of equipment quality can be defined as an ordered set of semantic elements describing the equipment quality indicators. Then, the semantic specification of the equipment quality indicators is defined as:

[0088] <Indicator> :: = <Equipment Name><Indicator Description><Indicator Quantification> (1)

[0089] According to the index semantic keywords "ability", "efficiency", and "performance", using semantic association technology, retrieve the quality description materials such as the uses, functions, and compositions of the equipment. According to the equipment index semantic specification, retrieve and analyze to form the index representation of the equipment, denoted as:

[0090] Q = {C, E, P} (2)

[0091] Where: C is the ability index representation, represented by the ability index semantic specification formula (3); E is the efficiency index representation, represented by the efficiency index semantic specification formula (4); P is the performance index representation, represented by the performance index semantic specification formula (5);

[0092] <Ability Index> ::= <Equipment Name><Ability Description><Ability Quantification> (3)

[0093] <Efficiency Index> ::= <Equipment Name><Efficiency Description><Efficiency Quantification> (4)

[0094] <Performance Index> ::= <Equipment Name><Performance Description><Performance Quantification> (5);

[0096] Step 2. Based on the tree analysis strategy, establish a task evaluation index model

[0097] Step 21. According to the tree analysis idea, first establish an evaluation index hierarchical structure and construct the framework of the evaluation index system, denoted as:

[0098] IA(r) = {I t} (6)

[0099] Where: r ∈ R; t = 1, 2,..., r; r is the number of levels of the index; I t is the index set of the t-th level,

[0100] I t = {IF i , m; IS ij , n i} (7)

[0101] Where: i = 1, 2,…, m; j = 1, 2,…, n i ;

[0102] In the formula: IF i is the i-th parent index; m is the total number of indexes at the t-th level; IS ij is the j-th sub-index of the i-th parent index; n i is the total number of sub-indexes of the i-th parent index.

[0103] Step 22. According to the description of the equipment evaluation task materials, analyze the purpose, content, and requirements of the evaluation, select the index requirements of the equipment, and establish an evaluation index system for a specific evaluation task, denoted as:

[0104] IA(3) = {I1, I2, I3} (8)

[0105] I1 = {IF i , m; IS ij , n i} (9)

[0106] Where: IF i ∈C, IS ij ∈E, i = 1, 2, …, m, j = 1, 2, …, n i ; m is the number of equipment capability indicators; n i is the number of sub - indicators of the i - th equipment capability indicator;

[0107] I2 = {IF i , s; IS ij , t i} (10)

[0108] Where: IF i ∈E, IS ij ∈P, i = 1, 2, …, s, j = 1, 2, …, t i ; s is the number of equipment effectiveness indicators; t i is the number of sub - indicators of the i - th equipment effectiveness indicator;

[0109]

[0110] Where: IF i ∈P, i = 1, 2, …, u, is an empty set; u is the total number of equipment performance indicators;

[0111] Step 3. Establish a consistency test and confirmation model for the evaluation index system

[0112] Step 31. Establish an independent consistency test model

[0113] For the established evaluation index system of a specific task, conduct independent consistency verification on the parent indicators of the capability indicator set formula (9), the effectiveness indicator set formula (10), and the performance indicator set formula (11) respectively. The method is as follows;

[0114] (1) Establish the following independent consistency verification matrix:

[0115]

[0116] Where d ij takes values according to the following rules:

[0117]

[0118] Where: When performing the independent consistency test on the ability index set, the indexes i and j belong to IFi in Equation (9), that is, i, j ∈ {IF1, IF2, …, IF m}; When performing the independent consistency test on the effectiveness index set, the indexes i and j belong to IFi in Equation (10), that is, i, j ∈ {IF1, IF2, …, IF s}; When performing the independent consistency test on the performance index set, the indexes i and j belong to IFi in Equation (11), that is, i, j ∈ {IF1, IF2, …, IF u};

[0119] (2) Define the independent consistency factor α, and the calculation formula is as follows

[0120]

[0121]

[0122] Step 32. Establish an aggregation consistency test model

[0123] Then perform the aggregation consistency verification on the effectiveness index and the ability index, and the performance index and the effectiveness index respectively. The method is as follows;

[0124] (1) Establish the following aggregation consistency verification matrix:

[0125]

[0126] When testing the aggregation consistency of the effectiveness index and the ability index, i takes the sub-index IS of Equation (9) ij , and j takes the parent index IF of Equation (9) i , as follows

[0127]

[0128] When testing the aggregation consistency of the performance index and the effectiveness index, i takes the sub-index IS of Equation (10) ij , and j takes the parent index IF of Equation (10) i , as follows

[0129]

[0130] Among them, h ij The value-taking rule is as follows:

[0131]

[0132] (2) Define the aggregation consistency factor, and the calculation formula is as follows

[0133]

[0134]

[0135] Step 4. Establish an adjustment and optimization model for the evaluation index system

[0136] According to the results of the independent consistency and aggregation consistency verification of the evaluation indexes, based on the consistency verification correction amount, the consistency verification correction amount is calculated as follows:

[0137] Step 41. The independent consistency verification correction amount is:

[0138] δ1 = α - α0 (22)

[0139] where α0 is the reference standard value of the independent consistency factor;

[0140] Step 42. The aggregation consistency verification correction amount is:

[0141] δ2 = β - β0 (23)

[0142] where β0 is the reference standard value of the aggregation consistency factor;

[0143] According to the consistency verification correction amount, optimize and adjust the ability index of formula (9), the effectiveness index of formula (10) and the performance index of formula (11), and then conduct independent consistency and aggregation consistency verification until the consistency verification correction amount tends to zero; output the equipment ability evaluation index system as shown in formula (8).

[0144] Through the above method, an equipment evaluation index system based on intelligent learning is established, including an equipment index feature extraction model, a task evaluation index model, a consistency verification confirmation model and an evaluation index system adjustment and optimization model; where

[0145] The equipment index feature extraction model is used to extract the equipment evaluation index features based on natural language preprocessing for the equipment product description materials through processes such as Chinese word segmentation, part-of-speech screening and feature extraction;

[0146] The task evaluation index model is used to establish an evaluation index system for a specific evaluation task for the evaluation task description materials through processes such as the index system framework, evaluation task identification and task evaluation index system establishment;

[0147] The consistency verification confirmation model is used to conduct independent consistency verification on the parent indexes of the ability index set, effectiveness index set and performance index set of the evaluation index system; conduct aggregation consistency verification on the effectiveness index and ability index, and performance index and effectiveness index respectively;

[0148] The evaluation index system adjustment and optimization model is used to adjust and optimize the evaluation index system based on the independent consistency and aggregation consistency verification results of the evaluation indexes and the consistency test correction amount.

[0149] The process of constructing the above-mentioned equipment capability evaluation index system is as Figure 2 shown. When evaluating the equipment evaluation indexes of the equipment capability evaluation index system, the specific process is as follows:

[0150] Step S1. Input the equipment quality description file, and use semantic association technology to retrieve the input file to obtain the index representation of the equipment, that is, formula (2), which includes the equipment capability index representation C, the equipment effectiveness index representation E, and the equipment performance index representation P;

[0151] Step S2. Input the equipment index representation formula (2), and use tree analysis technology to decompose the index requirements to obtain the equipment index system, that is, formula (6), which includes parent indexes and sub-indexes;

[0152] Step S3. Input the equipment evaluation requirement file and the input equipment index system formula (6), and respectively output the index system framework, the capability index set, the effectiveness index set, and the performance index set, that is, formula (8), formula (9), formula (10), and formula (11), as the initial index system set;

[0153] Step S4. Input the capability index set formula (9), the effectiveness index set formula (10), and the performance index set formula (11), and respectively perform independent consistency verification to check whether the indexes at the same level meet the requirements of independence and completeness, and calculate the independent consistency factor according to formulas (12)-(15);

[0154] Step S5. Input the capability index set formula (9) and the effectiveness index set formula (10), and respectively perform aggregation consistency verification to check whether the sub-indexes meet the aggregation requirements when aggregating to the parent indexes, and calculate the aggregation consistency factor according to formulas (16)-(21);

[0155] Step S6. Calculate the consistency test correction amount according to formulas (22) and (23), adjust and optimize the capability index set formula (9), the effectiveness index set formula (10), and the performance index set formula (11), and judge whether the consistency test correction amount tends to zero. Otherwise, go to step S3 to perform reduction and optimization adjustment on the capability index set formula (9), the effectiveness index set formula (10), and the performance index set formula (11);

[0156] Step S7. Output formula (8) to obtain the equipment capability evaluation index system IA(r).

[0157] The foregoing has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only to illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An evaluation method for an evaluation index system of equipment based on intelligent learning, characterized in that: The process of using an evaluation index system for equipment capability evaluation includes: Step S1. Input the equipment quality description file, and use semantic association technology to retrieve the input file to obtain the index representation of the equipment; Step S2. Input the equipment index representation, and use tree analysis technology to decompose the index requirements to obtain the equipment index system; Step S3. Input the equipment evaluation requirement file and the input equipment index system, and output the index system framework, the set of ability indexes, the set of effectiveness indexes, and the set of performance indexes respectively, as the initial index system set; Step S4. Input the set of ability indexes, the set of effectiveness indexes, and the set of performance indexes, and perform independent consistency verification respectively to check whether the indexes at the same level meet the requirements of independence and completeness, and calculate the independent consistency factor; Step S5. Input the set of ability indexes and the set of effectiveness indexes, and perform aggregation consistency verification respectively to check whether the sub-indexes to the parent indexes meet the aggregation requirements, and calculate the aggregation consistency factor; Step S6. Calculate the consistency verification correction amount, adjust and optimize the set of ability indexes, the set of effectiveness indexes, and the set of performance indexes, and judge whether the consistency verification correction amount tends to zero. Otherwise, go to Step S3 to perform reduction and optimization adjustment on the set of ability indexes, the set of effectiveness indexes, and the set of performance indexes; Step S7. Output the evaluation index system for a specific evaluation task to obtain the equipment capability evaluation index system IA(r); Among them, the construction of the evaluation index system includes: Step 1. Establish an equipment index feature extraction model according to the equipment capability description materials; Step 2. Establish a task evaluation index model based on the tree analysis strategy; Step 3. Establish a consistency verification and confirmation model for the evaluation index system; Step 4. Establish an adjustment and optimization model for the evaluation index system; The establishment process of the equipment index feature extraction model described in Step 1 includes Define the index of equipment quality as an ordered set of semantic elements describing the equipment quality index, and obtain the index semantic specification for defining equipment quality as: <Index> = <Equipment Name><Index Description><Index Quantification> (1) According to the equipment index semantic specification, retrieve and analyze to form the index representation of the equipment, denoted as: （2） Wherein: C is the representation of the ability index, which is represented by the semantic specification formula (3) of the ability index; E is the representation of the effectiveness index, which is represented by the semantic specification formula (4) of the effectiveness index; P is the representation of the performance index, which is represented by the semantic specification formula (5) of the performance index; <Ability Index> = <Equipment Name><Ability Description><Ability Quantification> (3) <Effectiveness Index> = <Equipment Name><Effectiveness Description><Effectiveness Quantification> (4) <Performance Index> = <Equipment Name><Performance Description><Performance Quantification> (5); The establishment process of the task evaluation index model described in Step 2 includes: Step 21. First, establish an evaluation index hierarchical architecture and construct an evaluation index system framework: IA ( r )={ I t} （6） Where: r ∈ R; t = 1, 2,..., r; r is the number of levels of the index; It is the index set of the t-th level, I t ={ IF i , m ; IS ij , n i} （7） Wherein: ; Wherein: IF i is the i th parent index; m is the t total number of hierarchical indices; IS ij is the i th sub-index of the j th parent index; n i is the i total number of sub-indices of the th parent index; Step 22. According to the equipment evaluation task material description, select the index requirements of the equipment to establish an evaluation index system for a specific evaluation task: IA (3)={ I 1, I 2, I 3} （8） I 1={ IF i , m ; IS ij , n i} （9） Wherein: IF i ∈ C , IS ij ∈ E , ; m is the number of equipment capability indicators; n i is the i th number of sub - indicators of the equipment capability indicator; I 2={ IF i , s ; IS ij , t i} （10） Wherein: IF i ∈ E , IS ij ∈ P , ; s is the number of equipment effectiveness indicators; t i is the i th number of sub - indicators of the equipment effectiveness indicator; I 3={ IF i , u ; φ , 0} （11） Wherein: IF i ∈ P , is an empty set; u is the total number of equipment performance indicators.

2. The evaluation method of an equipment evaluation index system based on intelligent learning according to claim 1, wherein: Step 3. The consistency verification and confirmation model of the evaluation index system described includes an independent consistency verification model and an aggregation consistency verification model.

3. The evaluation method of an equipment evaluation index system based on intelligent learning according to claim 2, characterized in that: The establishment process of the described independent consistency verification model includes (1) Establish an independent consistency check matrix: （12） Among them d ij The value-taking rules are as follows: （13） In the formula: When conducting an independent consistency test on the ability index set, the index i and j belong to the IF i of formula (9), ; When conducting an independent consistency test on the performance index set, the index i and j belong to the IF i in Equation (10), ; when conducting an independent consistency test on the performance index set, the index i and j belong to the IF i in Equation (11), ; (2)Define the independent consistency factor α , and the calculation formula is as follows （14） （15）。 4. The evaluation method of an equipment evaluation index system based on intelligent learning according to claim 3, characterized in that: The establishment process of the described aggregation consistency check model includes (1) Establish an aggregation consistency check matrix: （16） When aggregating the consistency of the test performance indicators and the ability indicators, i Take the sub-indicators of formula (9) IS ij , j Take the parent indicators of formula (9) IF i , such as （17） When checking the aggregation consistency of the inspection performance indicators and the effectiveness indicators, i Take the sub-indicators of formula (10) IS ij , j Take the parent indicators of formula (10) IF i , such as （18） Among them h ij The value-taking rules are as follows: （19） (2) Define the aggregation consistency factor, and the calculation formula is as （20） （21）。 5. The evaluation method of an equipment evaluation index system based on intelligent learning according to claim 4, characterized in that: The establishment process of the evaluation index system adjustment and optimization model described in step 4 includes The independent consistency check correction amount in step 41 is: （22） Among them, α 0 is the reference standard value of the independent consistency factor; The aggregation consistency check correction amount in step 42 is: （23） Among them, β 0 is the reference standard value of the aggregation consistency factor.

Images