Construction method and device of comprehensive evaluation index system, equipment and medium

Abstract

The invention provides a comprehensive evaluation index system construction method and device, equipment and a medium, and relates to the technical field of comprehensive evaluation.The comprehensive evaluation index system construction method comprises the steps that a comprehensive evaluation index system of a railway project is established according to the hierarchical relation between evaluation indexes; sequentially calculating an intra-evaluation-index difference coefficient and an inter-index difference coefficient of each evaluation index; obtaining all evaluation indexes of one hierarchy, and constructing a fitness function according to the difference coefficients of all evaluation indexes in one hierarchy, the difference coefficients among the indexes and the weights; iterating and updating the weight of the evaluation index based on a weight optimization method to obtain an updated weight, and substituting the updated weight into the fitness function to calculate a fitness evaluation value; the weight corresponding to the maximum fitness evaluation value is used as the optimal weight of the evaluation index, and by optimizing the weight of each evaluation index, the actual significance of the evaluation indexes of different levels is more objectively and accurately represented.

Description

Technical Field

[0001] The present invention relates to the technical field of evaluation of railway projects, and in particular, to a method, device, equipment and medium for constructing a comprehensive evaluation index system. Background Art

[0002] The comprehensive evaluation index system of railway projects is composed of multiple interrelated evaluation indicators, which is the basic work of comprehensive evaluation problems and determines the rationality of the final comprehensive evaluation results. Since different evaluation indicators have different degrees of influence on railway projects, it is necessary to assign different weights to all evaluation indicators to characterize the differences and importance of evaluation indicators at different levels in the comprehensive evaluation index system. The existing evaluation methods for railway projects mainly include subjective weighting methods and objective weighting methods. The subjective weighting method mainly relies on expert opinions, and the comprehensive evaluation results are not comprehensive enough. From the perspective of mathematical statistics analysis, some evaluation results of the objective weighting method may conflict with subjective cognition. It can be seen that the above methods cannot comprehensively and objectively describe the differences and importance of evaluation indicators at different levels, resulting in the lack of scientificity and rationality in the constructed railway project evaluation index system. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, device, equipment and medium for constructing a comprehensive evaluation index system to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0004] In a first aspect, the present application provides a method for constructing a comprehensive evaluation index system, including:

[0005] Obtain a number of evaluation indicators of a railway project and the hierarchical relationship between the evaluation indicators, and establish a comprehensive evaluation index system of the railway project according to the hierarchical relationship between the evaluation indicators. The comprehensive evaluation index system includes evaluation indicators at different levels;

[0006] Calculate the within-index difference coefficient and between-index difference coefficient of each evaluation indicator in turn. The within-index difference represents the difference of the railway project in the evaluation indicator, and the between-index difference represents the independence of the evaluation indicator;

[0007] Obtain all the evaluation indicators at one level, initialize the weights of all the evaluation indicators at this level, and construct a fitness function from the difference coefficient, between-index difference coefficient and weights of all the evaluation indicators at one level;

[0008] Based on the weight optimization method, iterate and update the weights of the evaluation indicators to obtain the updated weights, and substitute the updated weights into the fitness function to calculate the fitness evaluation value;

[0009] When the number of iterations reaches the preset number, the weight corresponding to the maximum fitness evaluation value is used as the optimal weight of the evaluation index.

[0010] In a second aspect, the present application further provides a device for constructing a comprehensive evaluation index system, including:

[0011] System establishment module: Obtain a number of evaluation indexes of a railway project and the hierarchical relationship between the evaluation indexes, and establish a comprehensive evaluation index system for the railway project according to the hierarchical relationship between the evaluation indexes. The comprehensive evaluation index system includes evaluation indexes at different levels;

[0012] Calculation module: Calculate the intra-index difference coefficient and the inter-index difference coefficient of each evaluation index in turn. The intra-index difference represents the difference of the railway project in the evaluation index, and the inter-index difference represents the independence of the evaluation index;

[0013] Initialization module: Obtain all the evaluation indexes of a level, initialize the weights of all the evaluation indexes in this level, and construct a fitness function from the difference coefficient, the inter-index difference coefficient and the weights of all the evaluation indexes in a level;

[0014] Iteration module: Iterate and update the weights of the evaluation indexes based on a weight optimization method to obtain the updated weights, and substitute the updated weights into the fitness function to calculate the fitness evaluation value;

[0015] Selection module: When the number of iterations reaches the preset number, the weight corresponding to the maximum fitness evaluation value is used as the optimal weight of the evaluation index.

[0016] In a third aspect, the present application further provides a device for constructing a comprehensive evaluation index system, including:

[0017] A memory for storing a computer program;

[0018] A processor for implementing the steps of the method for constructing a comprehensive evaluation index system when executing the computer program.

[0019] In a fourth aspect, the present application further provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for constructing a comprehensive evaluation index system are implemented.

[0020] The beneficial effects of the present invention are:

[0021] The present invention calculates the within-index difference coefficient and the between-index difference coefficient of various evaluation indexes of a railway project, and determines the optimal values of the two, effectively eliminating redundant and repetitive information of the evaluation indexes and highlighting the characteristics and differences of different evaluation indexes. On this basis, based on algorithms such as evolutionary algorithms and reinforcement learning, the weights of the evaluation indexes are dynamically adjusted, and a comprehensive evaluation index system of all evaluation indexes under the optimal weights is constructed. For evaluation indexes with insignificant differences and a large amount of repetitive information, smaller weights are assigned, so that the comprehensive evaluation index system of the railway project can more objectively and accurately represent the practical significance of different levels of evaluation indexes.

[0022] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or can be understood by implementing the embodiments of the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written specification, claims, and drawings. Brief Description of the Drawings

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as a limitation of the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0024] Figure 1 It is a schematic flowchart of the method for constructing the comprehensive evaluation index system described in the embodiments of the present invention;

[0025] Figure 2 It is a schematic diagram of the comprehensive evaluation index system described in the embodiments of the present invention;

[0026] Figure 3 It is a schematic structural diagram of the device for constructing the comprehensive evaluation index system described in the embodiments of the present invention;

[0027] Figure 4 It is a schematic structural diagram of the equipment for constructing the comprehensive evaluation index system described in the embodiments of the present invention.

[0028] Markings in the figure:

[0029] 800, equipment for constructing the comprehensive evaluation index system; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. Detailed Embodiments

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Components of the embodiments of the present invention described and illustrated herein generally may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but is merely representative of selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0031] It should be noted that like reference numerals and letters denote like items in the following drawings. Therefore, once an item is defined in one drawing, it does not require further definition and explanation in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive distinction and cannot be construed as indicating or implying relative importance.

[0032] Embodiment 1:

[0033] This embodiment provides a method for constructing a comprehensive evaluation index system.

[0034] See Figure 1 , which shows that this method includes:

[0035] S1. Obtain a number of evaluation indicators for a railway project and the hierarchical relationship between the evaluation indicators, and establish a comprehensive evaluation index system for the railway project according to the hierarchical relationship between the evaluation indicators. The comprehensive evaluation index system includes evaluation indicators at different levels;

[0036] In this embodiment, the railway project is affected by various factors such as its attributes, characteristics, and implicit values. A small number of single-level influencing factors (i.e., evaluation indicators) cannot accurately reflect the overall state of the railway project.

[0037] In this embodiment, in order to comprehensively and objectively evaluate the overall situation of the railway project, it is necessary to define the evaluation indicators affecting the railway project from multiple dimensions and different perspectives. The evaluation indicators should meet the requirements of comprehensiveness, objectivity, and integrity, that is:

[0038] (1) Comprehensiveness: The evaluation indicators should reflect as comprehensively as possible the overall situation of the railway project and not just one or a few aspects of the railway project. However, a large number of evaluation indicators should not be set either, otherwise the comprehensive evaluation index system will be too complex. Therefore, for several evaluation indicators that have a substitution relationship with each other, methods such as structural equation and analytic hierarchy process can be used for streamlining;

[0039] (2) Objectivity: The evaluation indicators must truly and objectively reflect the attributes and characteristics of railway projects, and cannot be artificially defined as extreme indicators that only reflect a certain aspect.

[0040] (3) Systematicness: When setting evaluation indicators, various relationships such as coordination, inhibition, and trade-off that may exist between indicators should be fully considered. The set of evaluation indicators composed of all evaluation indicators is also an indivisible integrated system.

[0041] It should be noted that since the measurement units of each evaluation indicator are different, it will lead to the inability to directly calculate between some evaluation indicators. Therefore, it is necessary to eliminate the above influence through the dimensionless method. For example, for qualitative indicators, they are converted into quantitative indicators through quantification. For reverse indicators and moderate indicators, they are converted into positive indicators through positive processing. For quantitative indicators, they are converted into directly calculable evaluation indicators by describing the linear or non-linear relationship between the dimensionless evaluation value and the actual value of the evaluation indicator.

[0042] Specifically, the step S1 includes:

[0043] S11. Obtain the highest-level evaluation indicators among several evaluation indicators, and the highest-level evaluation indicators form the first-level evaluation indicators of the railway project;

[0044] In this embodiment, the highest-level evaluation indicators are the evaluation indicators that have a direct impact on the railway project, and the first-level evaluation indicator set A1 is expressed as:

[0045]

[0046] In the formula, represents the J1th evaluation indicator in the first-level evaluation indicator set;

[0047] S12. Obtain the next-level evaluation indicators included in the highest-level indicators to form the second-level evaluation indicators of the railway project;

[0048] Specifically, the evaluation indicators included in obtaining A 1,1 include A 1,1,1 , A 1,1,2 and so on, which can be expressed as A 2,1 , A 2,2 …

[0049] Arrange all the second-level evaluation indicators in sequence, and the second-level evaluation indicator set A2 is:

[0050]

[0051] In the formula, represents the J2th evaluation indicator in the second level;

[0052] S13. Repeatedly obtain the evaluation indicators included in the next level until the evaluation indicators at the lowest level are obtained, and form the evaluation indicator set corresponding to the railway project at the corresponding level with the evaluation indicators at the lowest level:

[0053]

[0054] In the formula, represents the Jth L evaluation indicator in the Lth level. Finally, the comprehensive evaluation indicator system constructed by L levels is as Figure 2 shown.

[0055] Based on the above embodiments, the method further includes:

[0056] S2. Calculate the within - indicator difference coefficient and the between - indicator difference coefficient of each evaluation indicator in sequence; the within - indicator difference represents the difference of the railway project in the evaluation indicator, and the between - indicator difference represents the independence of the evaluation indicator;

[0057] Specifically, step S2 includes:

[0058] S21. Determine the position of the current evaluation indicator in the comprehensive evaluation indicator system, where the position is determined by the level to which the current evaluation indicator belongs and the serial number in the belonging level;

[0059] S22. Obtain the comprehensive evaluation indicator systems of multiple railway projects, and obtain the evaluation indicators with the same position as the current evaluation indicator from the comprehensive evaluation indicator systems;

[0060] In this embodiment, taking the evaluation indicator A L,j as an example, there are I railway projects. The value of the jth evaluation indicator A L,j of the ith railway project in the Lth - level evaluation indicator set is

[0061] S23. Calculate the mean and standard deviation of all evaluation indicators at the position, and calculate the within - indicator difference coefficient of the current evaluation indicator according to the mean and standard deviation:

[0062]

[0063] In the formula: S L,j respectively represent the mean and standard deviation of all railway projects at the position where the evaluation indicator A L,j is located, and v L,j represents the within - indicator difference coefficient of the evaluation indicator at the position where the evaluation indicator A L,j is located. I represents the number of railway projects, and i represents the ith railway project.

[0064] In this embodiment, the within - evaluation - index difference coefficient v L,j The larger the value, the more the current evaluation index A L,j can distinguish the differences between different railway projects, and then a larger weight should be assigned to A L,j Conversely, a smaller weight is assigned to A L,j .

[0065] Specifically, step S2 further includes:

[0066] S24. Determine the level to which the current evaluation index belongs and all the evaluation indexes included in this level;

[0067] Taking the set of evaluation indexes at the L - th level as an example in this embodiment, the evaluation indexes it includes are A L ={A L,1 , A L,2 , …, A L,j , …, A L,JL};

[0068] S25. Obtain the correlation coefficients between every two evaluation indexes in this level to establish the multiple - correlation - coefficient matrix R L of this level:

[0069]

[0070] In the formula, r represents the correlation coefficient between every two indexes in the set of evaluation indexes at the L - th level. For example, represents the correlation coefficient between the first evaluation index and the j - th evaluation index in the set of evaluation indexes at the L - th level.

[0071] S26. Obtain the correlation coefficients between the current evaluation index and other evaluation indexes from the multiple - correlation - coefficient matrix to calculate the within - evaluation - index difference coefficient of the current evaluation index:

[0072]

[0073] In the formula, u L,j represents the within - evaluation - index difference coefficient of the evaluation index A L,j , which is equal to the sum of the multiple - correlation coefficients of the evaluation index A L,j with all other evaluation indexes, and j′ represents other evaluation indexes.

[0074] Based on the above embodiments, this method further includes:

[0075] S3. Obtain all the evaluation indexes of a level, initialize the weights of all the evaluation indexes in this level, and construct a fitness function from the difference coefficients, within - evaluation - index difference coefficients, and weights of all the evaluation indexes in a level;

[0076] In this embodiment, the larger the value of v L,j , the more it indicates that the current evaluation index A L,j can better distinguish the differences between different railway projects, and thus a larger weight should be assigned to A L,j ; conversely, a smaller weight is assigned to A L,j .

[0077] The larger the value of u L,j , the more it indicates that the index j can be replaced by other indexes, and its role in the comprehensive evaluation index system is smaller. Therefore, a relatively smaller weight should be assigned to the evaluation index A L,j . Conversely, a relatively larger weight is assigned to A L,j .

[0078] Therefore, the fitness function is as follows:

[0079]

[0080] In the formula, f(ω L,j ) represents the fitness function, and ω L,j represents the weight of A L,j .

[0081] For the fitness function f(ω L,j ), v L,j and u L,j belong to the positive index and the negative index respectively, that is, the larger the value of v L,j , the smaller the value of u L,j , the larger the value of the fitness function f(ω L,j ), and the larger weight ω L,j should be assigned to the evaluation index A L,j .

[0082] Based on the above embodiments, the method further includes:

[0083] S4. Iteratively update the weights of the evaluation indexes based on the weight optimization method to obtain the updated weights, and substitute the updated weights into the fitness function to calculate the fitness evaluation value;

[0084] Specifically, when the weight optimization method is the genetic algorithm, the step S4 includes:

[0085] S41. Generate N p chromosome individuals based on the heuristic method, and form an initial population from the several chromosome individuals. Among them, each chromosome individual contains the weights of all evaluation indexes in the current layer. Specifically, a chromosome individual E RI can be expressed as:

[0086]

[0087] In the formula, representation weight;

[0088] S42. Optimize the chromosome individuals in the initial population to generate several new chromosome individuals. Specifically, the optimization operations include selection, crossover, and mutation;

[0089] S43. Calculate the fitness evaluation value of each new chromosome individual in turn based on the fitness function, select chromosome individuals according to the size of the fitness evaluation value to form a new population, and select the optimal population individuals for storage;

[0090] Specifically, select the N p chromosome individuals with the largest fitness evaluation value as the new population;

[0091] S44. Repeat the optimization operation on the chromosome individuals in the new population until the iteration number NFE crt reaches the preset number NFE max .

[0092] Specifically, when the weight optimization method is a reinforcement learning method, step S4 includes:

[0093] S45. Take the weights of all evaluation indicators in a layer as the state set in the reinforcement learning environment;

[0094] Specifically, use the computer random initialization method to generate the initial weights of the evaluation indicators Take the initial weights as the initial state set

[0095] S46. Let the current iteration number be k, and the agent generates an execution action A k , and use the execution action A k to update the weights in the state set, and take the updated weights as the state set at the iteration number k;

[0096] S47. Calculate the fitness evaluation value of the updated state set based on the fitness function as the reward function value R of the execution action k ;

[0097] S48. The agent adjusts the execution action according to the reward function value, and repeats to update the weights in the state set until the iteration number reaches the preset number.

[0098] In this embodiment, the agent performs policy evaluation and improvement on the execution action based on the reward function value R k , and at the same time enters the next iteration number k + 1, and judges whether k + 1 is less than the maximum iteration number k max :

[0099] If not, the agent generates the execution action A k+1 , and uses the execution action A k+1 to update the weights in the state set, and uses the updated weights as the state set at the iteration number k + 1

[0100] If the current iteration number reaches k max , it indicates that the off-line training process of reinforcement learning ends, and the action sets at all iteration numbers constitute the learning strategy for optimizing the weights of evaluation indicators

[0101] Based on the above embodiments, the method further includes:

[0102] S5. When the iteration number reaches the preset number, use the weights corresponding to the maximum fitness evaluation value as the optimal weights of the evaluation indicators

[0103] Specifically, when using the genetic algorithm for optimization, use the weights corresponding to the chromosome individual with the maximum fitness evaluation value as the weights of the L level

[0104] When using the reinforcement learning method for optimization, generate the optimal weights of the evaluation indicators according to the learning strategy

[0105] Repeat steps S4 and S5, and calculate the optimal weights of the evaluation indicators at each level in turn, so as to optimize the comprehensive evaluation index system

[0106] Embodiment 2:

[0107] As Figure 3 shown, this embodiment provides a device for constructing a comprehensive evaluation index system, and the device includes:

[0108] System establishment module: Obtain several evaluation indicators of the railway project and the hierarchical relationship between the evaluation indicators, and establish a comprehensive evaluation index system of the railway project according to the hierarchical relationship between the evaluation indicators. The comprehensive evaluation index system includes evaluation indicators at different levels

[0109] Calculation module: Calculate the within-index difference coefficient and the between-index difference coefficient of each evaluation indicator in turn. The within-index difference represents the difference of the railway project in the evaluation indicator, and the between-index difference represents the independence of the evaluation indicator

[0110] Initialization module: Obtain all the evaluation indicators of a level, initialize the weights of all the evaluation indicators in the level, and construct a fitness function from the difference coefficient within the index, the difference coefficient between the indexes, and the weights of all the evaluation indicators in a level

[0111] Iterative module: Iterate and update the weights of evaluation indicators based on the weight optimization method to obtain the updated weights, and substitute the updated weights into the fitness function to calculate the fitness evaluation value;

[0112] Selection module: When the number of iterations reaches the preset number, use the weight corresponding to the maximum fitness evaluation value as the optimal weight of the evaluation indicator.

[0113] Based on the above embodiments, the system establishment module includes:

[0114] First selection unit: Obtain the highest-level evaluation indicators from several evaluation indicators, and form the first-level evaluation indicators of the railway project with the highest-level evaluation indicators;

[0115] Second selection unit: Obtain the next-level evaluation indicators included in the highest-level indicators to form the second-level evaluation indicators of the railway project;

[0116] Third selection unit: Repeatedly obtain the evaluation indicators included in the next level until the lowest-level evaluation indicators are obtained, and form the evaluation indicators of the corresponding level of the railway project with the lowest-level evaluation indicators.

[0117] Based on the above embodiments, the calculation module includes:

[0118] First determination unit: Determine the position of the current evaluation indicator in the comprehensive evaluation indicator system, where the position is determined by the level to which the current evaluation indicator belongs and its serial number in the belonging level;

[0119] First acquisition unit: Obtain the comprehensive evaluation indicator systems of multiple railway projects, and obtain the evaluation indicators with the same position as the current evaluation indicator from the comprehensive evaluation indicator systems;

[0120] First calculation unit: Calculate the mean and standard deviation of all evaluation indicators at the position, and calculate the within-indicator difference coefficient of the current evaluation indicator according to the mean and standard deviation.

[0121] Based on the above embodiments, the calculation module further includes:

[0122] Second determination unit: Determine the level to which the current evaluation indicator belongs and all evaluation indicators included in the level;

[0123] Second acquisition unit: Obtain the correlation coefficients between pairwise evaluation indicators in the level to establish the multiple correlation coefficient matrix of the level;

[0124] Second calculation unit: Obtain the correlation coefficients between the current evaluation indicator and other evaluation indicators from the multiple correlation coefficient matrix to calculate the between-indicator difference coefficient of the current evaluation indicator.

[0125] Based on the above embodiments, the iterative module includes:

[0126] An initialization unit: generating a number of chromosome individuals based on a heuristic method, and forming an initial population by the number of chromosome individuals, wherein each chromosome individual includes the weights of all evaluation indicators in the current layer;

[0127] An optimization unit: performing an optimization operation on the chromosome individuals in the initial population to generate a number of new chromosome individuals;

[0128] A third calculation unit: calculating the fitness evaluation value of each new chromosome individual in turn based on a fitness function, and selecting chromosome individuals according to the size of the fitness evaluation value to form a new population;

[0129] An iteration unit: repeatedly performing an optimization operation on the chromosome individuals in the new population until the number of iterations reaches a preset number.

[0130] Based on the above embodiments, the iterative module further includes:

[0131] A third determination unit: taking the weights of all evaluation indicators in a layer as the state set in the reinforcement learning environment;

[0132] An update unit: generating an execution action by an agent to update the weights in the state set;

[0133] A fourth calculation unit: calculating the fitness evaluation value of the updated state set based on a fitness function as the reward function value of the execution action;

[0134] An adjustment unit: the agent adjusts the execution action according to the reward function value, and repeatedly updates the weights in the state set until the number of iterations reaches a preset number.

[0135] It should be noted that regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0136] Embodiment 3:

[0137] Corresponding to the above method embodiment, in this embodiment, a comprehensive evaluation index system construction device is further provided. The comprehensive evaluation index system construction device described below can be correspondingly referred to the comprehensive evaluation index system construction method described above.

[0138] Figure 4 It is a block diagram of a comprehensive evaluation index system construction device 800 shown according to an exemplary embodiment. As Figure 4As shown, the device 800 for constructing the comprehensive evaluation index system may include: a processor 801 and a memory 802. The device 800 for constructing the comprehensive evaluation index system may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0139] Among them, the processor 801 is used to control the overall operation of the device 800 for constructing the comprehensive evaluation index system to complete all or part of the steps in the above method for constructing the comprehensive evaluation index system. The memory 802 is used to store various types of data to support the operation of the device 800 for constructing the comprehensive evaluation index system. These data may include, for example, instructions for any application or method operating on the device 800 for constructing the comprehensive evaluation index system, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 802 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the device 800 for constructing the comprehensive evaluation index system and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them. Accordingly, the communication component 805 may include: a Wi-Fi module, a Bluetooth module, and an NFC module.

[0140] In an exemplary embodiment, the device 800 for constructing the comprehensive evaluation index system may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components, and is used to execute the above-mentioned method for constructing the comprehensive evaluation index system.

[0141] In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions. When the program instructions are executed by a processor, the steps of the above-mentioned method for constructing the comprehensive evaluation index system are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions may be executed by the processor 801 of the device 800 for constructing the comprehensive evaluation index system to complete the above-mentioned method for constructing the comprehensive evaluation index system.

[0142] Embodiment 4:

[0143] Corresponding to the above method embodiment, in this embodiment, there is also provided a readable storage medium. A readable storage medium described below can be correspondingly referred to with a method for constructing a comprehensive evaluation index system described above.

[0144] A readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the method for constructing the comprehensive evaluation index system in the above method embodiment are implemented.

[0145] Specifically, the readable storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc., which are all readable storage media capable of storing program codes.

[0146] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention may have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0147] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for constructing a comprehensive evaluation index system, characterized in that Including: Obtain several evaluation indicators of the railway project and the hierarchical relationship between the evaluation indicators. According to the hierarchical relationship between the evaluation indicators, establish a comprehensive evaluation index system for the railway project. The comprehensive evaluation index system includes evaluation indicators at different levels; Calculate the within-index difference coefficient and the between-index difference coefficient of each evaluation indicator in turn. The within-index difference indicates the difference of the railway project in the evaluation indicator, and the between-index difference indicates the independence of the evaluation indicator; Obtain all the evaluation indicators at one level, initialize the weights of all the evaluation indicators at this level, and construct a fitness function from the difference coefficient, the between-index difference coefficient, and the weights of all the evaluation indicators at one level; Iteratively update the weights of the evaluation indicators based on the weight optimization method to obtain the updated weights, and substitute the updated weights into the fitness function to calculate the fitness evaluation value; When the number of iterations reaches the preset number, use the weight corresponding to the maximum fitness evaluation value as the optimal weight of the evaluation indicator.

2. The method for constructing the comprehensive evaluation index system according to claim 1, wherein , calculating the within-index difference coefficient of the evaluation indicator, including: Determine the position of the current evaluation indicator in the comprehensive evaluation index system. The position is determined by the level to which the current evaluation indicator belongs and its serial number in the belonging level; Obtain the comprehensive evaluation index systems of multiple railway projects, and obtain the evaluation indicators with the same position as the current evaluation indicator from the comprehensive evaluation index systems; Calculate the mean and standard deviation of all the evaluation indicators at this position, and calculate the within-index difference coefficient of the current evaluation indicator according to the mean and standard deviation.

3. The method for constructing the comprehensive evaluation index system according to claim 1, characterized in that , calculating the between-index difference coefficient of the evaluation indicator, including: Determine the level to which the current evaluation indicator belongs and all the evaluation indicators included in this level; Obtain the correlation coefficients between every two evaluation indicators in this level to establish a multiple correlation coefficient matrix of this level; Obtain the correlation coefficients between the current evaluation indicator and other evaluation indicators from the multiple correlation coefficient matrix to calculate the between-index difference coefficient of the current evaluation indicator.

4. The method for constructing the comprehensive evaluation index system according to claim 1, wherein , iteratively updating the weights of the evaluation indicators based on the weight optimization method to obtain the updated weights, and substituting the updated weights into the fitness function to calculate the fitness evaluation value, including: Generate several chromosome individuals based on the heuristic method, and form an initial population by the several chromosome individuals. Each chromosome individual includes the weights of all the evaluation indicators at the current level; Perform an optimization operation on the chromosome individuals in the initial population to generate several new chromosome individuals; Calculate the fitness evaluation value of each new chromosome individual in turn based on the fitness function, and select chromosome individuals according to the size of the fitness evaluation value to form a new population; Repeat the optimization operation on the chromosome individuals in the new population until the number of iterations reaches the preset number.

5. An apparatus for constructing a comprehensive evaluation index system, characterized in that, Including: System establishment module: Obtain several evaluation indicators of the railway project and the hierarchical relationship between the evaluation indicators. According to the hierarchical relationship between the evaluation indicators, establish a comprehensive evaluation index system for the railway project. The comprehensive evaluation index system includes evaluation indicators at different levels; Calculation module: Calculate the within-index difference coefficient and between-index difference coefficient of each evaluation index in sequence. The within-index difference represents the difference of the railway project in the evaluation index, and the between-index difference represents the independence of the evaluation index. Initialization module: Obtain all the evaluation indexes of a level, initialize the weights of all the evaluation indexes in this level, and construct a fitness function from the difference coefficients, between-index difference coefficients, and weights of all the evaluation indexes in a level. Iteration module: Iterate and update the weights of the evaluation indexes based on the weight optimization method to obtain the updated weights, and substitute the updated weights into the fitness function to calculate the fitness evaluation value. Selection module: When the number of iterations reaches the preset number, take the weight corresponding to the maximum fitness evaluation value as the optimal weight of the evaluation index.

6. The comprehensive evaluation index system construction device according to claim 5, characterized in that The calculation module includes: First determination unit: Determine the position of the current evaluation index in the comprehensive evaluation index system, where the position is determined by the level to which the current evaluation index belongs and its serial number in the belonging level. First acquisition unit: Obtain the comprehensive evaluation index system of multiple railway projects, and acquire the evaluation indexes with the same position as the current evaluation index from the comprehensive evaluation index system. First calculation unit: Calculate the mean and standard deviation of all the evaluation indexes at this position, and calculate the within-index difference coefficient of the current evaluation index according to the mean and standard deviation.

7. The device for constructing the comprehensive evaluation index system according to claim 5, wherein The calculation module further includes: Second determination unit: Determine the level to which the current evaluation index belongs and all the evaluation indexes included in this level. Second acquisition unit: Obtain the correlation coefficients between every two evaluation indexes in this level to establish the multiple correlation coefficient matrix of this level. Second calculation unit: Obtain the correlation coefficients between the current evaluation index and other evaluation indexes from the multiple correlation coefficient matrix to calculate the between-index difference coefficient of the current evaluation index.

8. The device for constructing the comprehensive evaluation index system according to claim 5, wherein The iteration module includes: Initialization unit: Generate a number of chromosome individuals based on the heuristic method, and form an initial population by the number of chromosome individuals. Each chromosome individual includes the weights of all the evaluation indexes in the current level. Optimization unit: Perform optimization operations on the chromosome individuals in the initial population to generate a number of new chromosome individuals. Third calculation unit: Calculate the fitness evaluation values of each new chromosome individual in sequence based on the fitness function, and select chromosome individuals according to the magnitude of the fitness evaluation values to form a new population. Iteration unit: Repeatedly perform optimization operations on the chromosome individuals in the new population until the number of iterations reaches the preset number.

9. An equipment for constructing a comprehensive evaluation index system, characterized in that It includes: A memory for storing computer programs. A processor for implementing the steps of the comprehensive evaluation index system construction method according to any one of claims 1 to 4 when executing the computer program.

10. A readable storage medium, characterized in that: The computer program is stored on the readable storage medium, and when the computer program is executed by the processor, it implements the steps of the comprehensive evaluation index system construction method according to any one of claims 1 to 4.

Images