Comprehensive passenger transport hub service quality evaluation method based on SPO-AHP

Abstract

The invention discloses a comprehensive passenger transport hub service quality evaluation method based on SPO-AHP, and relates to the technical field of intelligent transportation, and the evaluation steps comprise: S1, determining an evaluation purpose, determining an evaluation object, and selecting evaluation indexes; s2, constructing a comprehensive passenger transport hub service quality evaluation index system from three dimensions of a service structure, a service process and a service result based on an SPO three-dimensional structure perspective; s3, determining weights corresponding to the indexes based on an AHP method, constructing a comprehensive passenger transport hub evaluation model, inputting the evaluation indexes into the evaluation model, outputting the evaluation indexes, and calculating a comprehensive evaluation result; s4, according to a comprehensive evaluation result, performing different grade division on the service quality of the comprehensive passenger transport hub; and S5, giving different improvement measures according to different divided grades. The method provides support for standardizing the service quality evaluation work of the comprehensive passenger transport hub and promoting the improvement of the service quality of the comprehensive passenger transport hub and integrated construction.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a comprehensive passenger transport hub service quality evaluation method based on SPO-AHP. Background Art

[0002] Comprehensive passenger transport hubs are key nodes in the comprehensive passenger transport network and the main carrier for efficient connection and integrated organization of various modes of transport. By bringing together multiple modes of transport, they provide passengers with distribution and transfer services, which plays an important role in the efficient operation of the comprehensive transport network and the regional transport system. They are also of great significance to facilitating people's travel, alleviating traffic congestion and promoting social and economic development. With the development of the economy and the continuous improvement of people's material and cultural living standards, people's demand for transportation is also increasing, shifting from guaranteed transportation demand to improved transportation demand, and from being able to reach the destination to safe, efficient, smart and green travel. Improving the service quality of comprehensive passenger transport hubs, improving the operating efficiency of comprehensive passenger transport hubs, and adapting to the higher requirements of the economy and society for the comprehensive transport system are the inevitable trends in the development of comprehensive transportation.

[0003] Although my country's comprehensive passenger transport hub development has achieved positive results, compared with accelerating the construction of a strong transportation country and meeting the people's growing needs for a better life, there is still a certain gap in the level of comprehensive transportation services, which is mainly manifested in: (1) The transfer connection is not smooth. The proportion of integrated connection projects in comprehensive passenger transport hubs is less than 30%, and the all-weather and convenient transfer environment needs to be further improved; (2) The network service capacity needs to be improved. The level of effective coordinated operation between comprehensive transportation hubs is low, the degree of facility sharing and use is insufficient, the level of information interconnection is not high, and the diversified and professional service functions are still imperfect; (3) There is a lack of connection between transportation services of different modes. Various modes of transportation between comprehensive passenger transport hubs and within single comprehensive passenger transport hubs are mostly operated independently and closed, with insufficient coordination in dispatching and operation. The phenomenon of "multiple government departments" for relevant public services at the comprehensive transportation operation level is more prominent; (4) The operation management efficiency of comprehensive passenger transport hubs is not strong, and the operation monitoring capacity of passenger transport hubs is insufficient, which affects the operation service efficiency of comprehensive passenger hubs. In this regard, we propose a comprehensive passenger transport hub service quality evaluation method based on SPO-AHP. Summary of the invention

[0004] In order to solve the above technical problems, a comprehensive passenger transport hub service quality evaluation method based on SPO-AHP is provided. This technical solution solves the above problems.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is: a comprehensive passenger transport hub service quality evaluation method based on SPO-AHP, the evaluation steps include:

[0006] S1. Clarify the purpose of the evaluation, determine the object of the evaluation, and select the evaluation indicators;

[0007] S2. Based on the three-dimensional structural perspective of SPO, a comprehensive passenger transport hub service quality evaluation index system is constructed from the three dimensions of service structure, service process and service results;

[0008] S3. Determine the weights corresponding to the indicators based on the AHP method, build a comprehensive passenger transport hub evaluation model, input the evaluation indicators into the evaluation model, output them, and calculate the results of the comprehensive evaluation;

[0009] S4. According to the results of the comprehensive evaluation, the service quality of the comprehensive passenger transport hub is divided into different levels;

[0010] S5. Different improvement measures are given for different classification levels to optimize the service quality of comprehensive passenger transport hubs.

[0011] Preferably, the purpose of the evaluation in step S1 is to consider the actual situation of the services provided by the passenger hub in various aspects, determine the overall service quality level, and clarify the advantages and disadvantages; the evaluation object is a group of objective things with the same properties, and the number of evaluation objects is greater than 1; the evaluation index is the operating status of the system represented by a vector, and this vector is called the state vector of the system, in which each sub-vector reflects the status characteristics of the system from a certain aspect, thereby constituting a comprehensive evaluation index.

[0012] Preferably, the service structure in step S2 includes facilities and equipment, human resources, financial guarantees and standards and specifications; the service process includes transportation organization, information services and transfer connections; the service results include indicators of three dimensions: service effect, service efficiency and service fairness, which are characterized by indicators related to passengers' subjective feelings. The above service indicators are collected as the original values ​​of the evaluation indicators, and the original values ​​are preprocessed.

[0013] Preferably, the original value preprocessing adopts a consistent processing method, and is divided into four types of indicators: extremely large indicators, extremely small indicators, medium indicators and interval indicators according to the attributes of the rating indicators themselves. The types of indicators are processed consistently before evaluation, and different types of indicators are converted into consistent ones. The formula for converting extremely small indicators into extremely large indicators is:

[0014] x * =Mx

[0015] x * =1 / x

[0016] Where M is the total amount of constraints, which is taken as an upper limit of the index, x is the extremely small index, and x* is the extremely large index converted from the extremely small index; this method is a differential conversion, which belongs to linear conversion and will not affect the evaluation conclusion;

[0017] The formula for converting a medium-sized index into an extremely large index is:

[0018]

[0019] Where m is an allowed lower bound of the index, x ij is a centered indicator, x * ij It is a very large indicator after the conversion of the medium-sized indicator;

[0020] The formula for converting interval indicators into extremely large indicators is:

[0021]

[0022] Among them, q1 and q2 are set parameters, which are the minimum and maximum values ​​of the intermediate type.

[0023] Preferably, the original value preprocessing also includes a dimensionless index processing method, and the power coefficient method is used to eliminate the difficulties caused by different dimensions and the influence of the large difference in data size on the calculation accuracy. The calculation formula is:

[0024]

[0025] Where M' j and m' j They are respectively j The upper and lower limits of the value are as follows: c and d are known constants. The function of c is to translate the changed value, and the function of d is to enlarge and reduce the transformed value. Here, c=50 and d=50.

[0026] Preferably, the comprehensive passenger transport hub evaluation method of AHP in step S3 is a hierarchical analysis method, which compares multiple indicators in pairs, determines the judgment matrix, and calculates the decision weight; the analysis step includes:

[0027] A1. Decompose the evaluation factors into several levels and construct a hierarchical structure of the system;

[0028] A2. Compare the elements of each level from top to bottom and construct the indicator importance judgment matrix;

[0029] A3. Calculate the weight of each indicator element relative to the criterion;

[0030] A4. Calculate the combined weight of each layer element relative to the system goal.

[0031] Preferably, in step A1, the complex problem is decomposed to make the problem hierarchical and organized, and a hierarchical structural model is constructed. The decomposed components in the model are called elements, which are divided into several groups according to the attributes of the elements to form different levels, which are divided into three layers:

[0032] The target layer, which is the predetermined goal and ideal result of the problem;

[0033] The criterion layer, i.e. the intermediate links considered in achieving the goal, consists of several levels;

[0034] The plan layer, also known as the measure layer, is the measures and decision-making plans taken to achieve the goals. Each layer controls less than 9 elements.

[0035] Preferably, in step A2, a suitable scale is introduced to judge the relative importance of each factor in each level. Assuming there are n elements, a judgment matrix A can be constructed as follows: ij ) n×n , where a ij It represents the importance of factor i and factor j relative to the target, and its form is as follows:

[0036]

[0037] The matrix A has the following properties:

[0038] a ij >0

[0039] a ji =1 / a ij (i,j=1,2,...,n)

[0040] a ii =1(i,j=1,2,...,n);

[0041] In the AHP, the relative importance of each indicator to the elements in the upper layer is marked, and the scaling method is introduced to form the above-mentioned numerical judgment matrix;

[0042] In step A3, the main calculation of the hierarchical single sorting is performed by calculating the maximum eigenvalue and eigenvector of the judgment matrix.

[0043] Preferably, after the weights are determined in step S3, an evaluation model is constructed based on weighted average, a data set is prepared, the data set is substituted into the model, training is performed, and the model is optimized and improved; after improvement, evaluation indicators are input to obtain evaluation results.

[0044] Preferably, the grade division in step S4 is analyzed based on the K-Means clustering method, and the comprehensive evaluation result data of multiple comprehensive passenger transport hubs are collected as sample data to determine the number of clusters to be divided, and the cluster centers are randomly initialized. Then, the distance from each sample data point to each cluster center is calculated, and the sample point is assigned to the cluster where the nearest cluster center is located according to the distance. Then, the center of each cluster is recalculated, and the process of assigning and updating the cluster center is repeated until the cluster center no longer changes or the set number of iterations is reached. Each cluster represents a service quality level, and the corresponding hub service quality level is determined based on the cluster where the sample is located; the grade division in step S5 includes excellent, good, medium, poor and bad.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] Based on a systematic analysis of the factors affecting the service quality of comprehensive passenger transport hubs, the present invention combines the responsibilities and obligations of comprehensive passenger transport hubs and the concepts and connotations of their service quality, benchmarks the requirements for high-quality development of comprehensive passenger transport hub services, and proposes a set of comprehensive passenger transport hub service quality evaluation method systems, which is convenient for the competent departments of the transportation industry, hub management departments and passengers to grasp the overall situation of the service level of my country's comprehensive passenger transport hubs, and provides support for standardizing the service quality evaluation work of comprehensive passenger transport hubs and promoting the improvement of service quality and integrated construction of comprehensive passenger transport hubs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of the comprehensive evaluation steps of the present invention;

[0048] Figure 2 It is a schematic diagram of the hierarchical structure of the hierarchical analysis method of the present invention. DETAILED DESCRIPTION

[0049] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0050] Reference Figure 1 and Figure 2 As shown in FIG. 1 , a comprehensive passenger hub service quality evaluation method based on SPO-AHP is provided, and the evaluation steps include:

[0051] S1. Clarify the purpose of the evaluation, determine the object of the evaluation, and select the evaluation indicators;

[0052] S2. Based on the three-dimensional structural perspective of SPO, a comprehensive passenger transport hub service quality evaluation index system is constructed from the three dimensions of service structure, service process and service results;

[0053] S3. Determine the weights corresponding to the indicators based on the AHP method, build a comprehensive passenger transport hub evaluation model, input the evaluation indicators into the evaluation model, output them, and calculate the results of the comprehensive evaluation;

[0054] S4. According to the results of the comprehensive evaluation, the service quality of the comprehensive passenger transport hub is divided into different levels;

[0055] S5. Different improvement measures are given for different classification levels to optimize the service quality of comprehensive passenger transport hubs.

[0056] This application constructs an evaluation index system from three dimensions: service structure, service process and service results, avoiding the one-sidedness of single-dimensional evaluation. The service structure dimension can cover the facility layout, functional zoning and hardware-related elements of the hub, and can examine whether it is reasonable and whether it is convenient for passengers to transfer and purchase tickets; the service process dimension focuses on whether the process of the passenger hub is smooth when providing services, the service attitude and efficiency dynamics of the staff; the service results directly reflect the final experience brought to passengers, such as whether the departure is on time and the satisfaction of passengers;

[0057] Different levels of service quality are divided according to the results of comprehensive evaluation, which enables the operators, managers and relevant regulatory departments of passenger transport hubs to understand the current level of service quality at a glance. All parties can quickly know whether the overall service quality of the hub has reached a high standard or has obvious deficiencies, which is convenient for formulating subsequent strategies in a targeted manner;

[0058] The final evaluation results and the corresponding grade classification and improvement measures can serve as an important reference for passenger hub operation and management decision-making. Whether in the allocation of resource inputs or in the formulation of long-term development plans, relevant decision makers can obtain strong support from the output of this evaluation method and make decisions that are more practical and conducive to improving service quality.

[0059] The purpose of the evaluation in step S1 is to consider the actual situation of the services provided by the passenger hub in various aspects, determine the overall service quality level, and identify the advantages and disadvantages; the evaluation object is a group of objective things with the same properties, and the number of evaluation objects is greater than 1; the evaluation index is the operating status of the system, which is represented by a vector, and this vector is called the state vector of the system, in which each sub-vector reflects the status characteristics of the system from a certain aspect, thus forming a comprehensive evaluation index.

[0060] This application can avoid the problem of focusing only on the local and ignoring the overall service level by considering the actual situation of the services provided by the passenger hub in various aspects. The evaluation index is represented by the operating status of the system in the form of a vector, that is, the state vector, and each sub-vector reflects the status characteristics of the system from a certain aspect, which makes the description of the service quality of the passenger hub very detailed and comprehensive.

[0061] In step S2, the service structure includes facilities and equipment, human resources, financial guarantees and standards and specifications; the service process includes transportation organization, information services and transfer connections; the service results include indicators of three dimensions: service effect, service efficiency and service fairness, which are characterized by indicators related to passengers' subjective feelings. The above service indicators are collected as the original values ​​of the evaluation indicators, and the original values ​​are preprocessed.

[0062] This application incorporates facilities and equipment, human input, financial support and standards and specifications into the service structure indicators, which can systematically consider the basic conditions for the operation of passenger hubs. For example, facilities and equipment cover the number and comfort of seats in the waiting hall, whether the various signboards in the station are clear and complete, and the hardware conditions, which are directly related to the passenger experience; human input is related to whether the number of staff is sufficient and whether they can provide timely assistance to passengers; financial support affects the maintenance and updating of facilities and the investment in service improvement; standards and specifications ensure that various services are carried out in a standardized manner in accordance with rules. By collecting the original values ​​of these indicators and pre-processing them, we can fully grasp the configuration and guarantee of passenger hub services at the basic level, and promptly discover potential problems such as aging facilities without financial updates and insufficient manpower leading to untimely service responses.

[0063] The original value preprocessing sampling consistency processing method is divided into four types of indicators: extremely large indicators, extremely small indicators, medium indicators and interval indicators according to the attributes of the rating indicators themselves. The types of indicators are processed consistently before evaluation, and the different types of indicators are converted into consistency. The formula for converting extremely small indicators into extremely large indicators is:

[0064] x * =Mx

[0065] x * =1 / x

[0066] Where M is the total amount of constraints, which is taken as an upper limit of the index, x is the extremely small index, and x* is the extremely large index converted from the extremely small index; this method is a differential conversion, which belongs to linear conversion and will not affect the evaluation conclusion;

[0067] The formula for converting a medium-sized index into an extremely large index is:

[0068]

[0069] Where m is an allowed lower bound of the index, x ij is a centered indicator, x * ij It is a very large indicator after the conversion of the medium-sized indicator;

[0070] The formula for converting interval indicators into extremely large indicators is:

[0071]

[0072] Among them, q1 and q2 are set parameters, which are the minimum and maximum values ​​of the intermediate type.

[0073] The original value preprocessing also includes the dimensionless processing method of indicators, and the power coefficient method is used to eliminate the difficulties caused by different dimensions and the influence of the large difference in data size on the calculation accuracy. The calculation formula is:

[0074]

[0075] Where M' j and m' j They are respectively j The upper and lower limits of the value are as follows: c and d are known constants. The function of c is to translate the changed value, and the function of d is to enlarge and reduce the transformed value. Here, c=50 and d=50.

[0076] The comprehensive passenger transport hub evaluation method of AHP in step S3 is the hierarchical analysis method, which compares multiple indicators in pairs, determines the judgment matrix, and calculates the decision weight; the analysis steps include:

[0077] A1. Decompose the evaluation factors into several levels and construct a hierarchical structure of the system;

[0078] A2. Compare the elements of each level from top to bottom and construct the indicator importance judgment matrix;

[0079] A3. Calculate the weight of each indicator element relative to the criterion;

[0080] A4. Calculate the combined weight of each layer element relative to the system goal.

[0081] This application decomposes the evaluation factors into several levels to construct a hierarchical structure, which helps to clearly sort out the numerous interrelated and mutually influential evaluation factors in the complex system of the comprehensive passenger transport hub; by comparing the elements of each level from top to bottom and constructing a judgment matrix, the purpose of quantifying the relative importance of indicators that were originally difficult to measure directly is achieved; calculating the weight value of each indicator element relative to the criterion can accurately reflect the difference in contribution made by different indicators in the process of realizing the corresponding evaluation criteria.

[0082] In step A1, complex problems are decomposed to make them hierarchical and organized, and a hierarchical structural model is constructed. The decomposed components in the model are called elements, which are divided into several groups according to their attributes to form different levels. There are three levels:

[0083] The target layer, which is the predetermined goal and ideal result of the problem;

[0084] The criterion layer, i.e. the intermediate links considered in achieving the goal, consists of several levels;

[0085] The plan layer, also known as the measure layer, is the measures and decision-making plans taken to achieve the goals. Each layer controls less than 9 elements.

[0086] This application sets the target layer as the predetermined goal and ideal result of the problem, which can provide a clear and explicit direction for the service quality evaluation of the entire comprehensive passenger transport hub. The criterion layer is the intermediate link considered for achieving the goal and is composed of several levels. It can break down the abstract overall goal into a specific and operational implementation path.

[0087] In step A2, appropriate scales are introduced to judge the relative importance of each factor in each level. Suppose there are n elements, the judgment matrix A can be constructed as follows: ij ) n×n , where a ij It represents the importance of factor i and factor j relative to the target, and its form is as follows:

[0088]

[0089] The matrix A has the following properties:

[0090] a ij >0

[0091] a ji =1 / a ij (i,j=1,2,...,n)

[0092] a ii =1(i,j=1,2,...,n);

[0093] In the AHP, the relative importance of each indicator to the elements in the upper layer is marked, and the scaling method is introduced to form the above-mentioned numerical judgment matrix;

[0094] Table 1 below shows the meaning of each scale in the hierarchical analysis method

[0095]

[0096] Table 1

[0097] In step A3, the main calculation of the hierarchical single sorting is performed by calculating the maximum eigenvalue and eigenvector of the judgment matrix.

[0098] After the weights are determined in step S3, an evaluation model is constructed based on weighted average, a data set is prepared, the data set is substituted into the model, training is performed, and the model is optimized and improved; after improvement, the evaluation indicators are input to obtain the evaluation results.

[0099] This application uses a weighted average approach to construct an evaluation model, which can scientifically integrate the impact of multiple evaluation indicators. The process of optimizing and improving the model can enable the model to continuously adapt to the changing operating environment and new situations of the passenger hub. With the development of the times, passenger hubs may introduce new technologies and service models, or face new changes in passenger demand. By continuously training and optimizing the model with new data, it can timely adjust its internal parameters and algorithm structure to ensure its own effectiveness and applicability.

[0100] In step S4, the grade division is based on the K-Means clustering method for analysis. The comprehensive evaluation result data of multiple comprehensive passenger transport hubs are collected as sample data, the number of clusters to be divided is determined, the cluster center is randomly initialized, and then the distance from each sample data point to each cluster center is calculated. The sample point is assigned to the cluster with the nearest cluster center according to the distance, and then the center of each cluster is recalculated. The process of assigning and updating the cluster center is repeated until the cluster center no longer changes or the set number of iterations is reached. Each cluster represents a service quality level, and the corresponding hub service quality level is determined based on the cluster where the sample is located; in step S5, the grade division includes excellent, good, medium, poor and bad.

[0101] This application collects comprehensive evaluation result data of multiple comprehensive passenger transport hubs as sample data for grading. The whole process is based on real data, avoiding the arbitrariness of determining the grade solely based on subjective conjecture or experience. The evaluation result data of different passenger transport hubs in terms of the degree of completeness of facilities and equipment, service efficiency, passenger satisfaction, etc. are taken into consideration, so that the final grade can objectively reflect the actual service quality status of each hub, making the grade classification results more convincing. Whether it is the passenger transport hub operator, management department or passengers, they can all recognize the grade assessment based on the data.

[0102] The above shows and describes 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 to the above embodiments, and the above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention, and these changes and improvements fall within the scope of the present invention claimed.

Claims

1. A comprehensive passenger transport hub service quality evaluation method based on SPO-AHP, characterized in that: The evaluation steps include: S1. Clarify the purpose of the evaluation, determine the object of the evaluation, and select the evaluation indicators; S2. Based on the three-dimensional structural perspective of SPO, a comprehensive passenger transport hub service quality evaluation index system is constructed from the three dimensions of service structure, service process and service results; S3. Determine the weights corresponding to the indicators based on the AHP method, build a comprehensive passenger transport hub evaluation model, input the evaluation indicators into the evaluation model, output them, and calculate the results of the comprehensive evaluation; S4. According to the results of the comprehensive evaluation, the service quality of the comprehensive passenger transport hub is divided into different levels; S5. Different improvement measures are given for different classification levels to optimize the service quality of comprehensive passenger transport hubs.

2. The SPO-AHP-based comprehensive passenger transport hub service quality evaluation method according to claim 1 is characterized in that: The purpose of the evaluation in step S1 is to consider the actual situation of the services provided by the passenger hub in various aspects, determine the overall service quality level, and identify the advantages and disadvantages; the evaluation object is a group of objective things with the same properties, and the number of evaluation objects is greater than 1; the evaluation index is the operating status of the system, which is represented by a vector, and this vector is called the state vector of the system, in which each sub-vector reflects the status characteristics of the system from a certain aspect, thus forming a comprehensive evaluation index.

3. The SPO-AHP-based comprehensive passenger transport hub service quality evaluation method according to claim 1 is characterized in that: In step S2, the service structure includes facilities and equipment, human resources, financial guarantees and standards and specifications; the service process includes transportation organization, information services and transfer connections; the service results include indicators of three dimensions: service effect, service efficiency and service fairness, which are characterized by indicators related to passengers' subjective feelings. The above service indicators are collected as the original values ​​of the evaluation indicators, and the original values ​​are preprocessed.

4. The SPO-AHP-based comprehensive passenger transport hub service quality evaluation method according to claim 3 is characterized in that: The original value preprocessing sampling consistency processing method is divided into four types of indicators: extremely large indicators, extremely small indicators, medium indicators and interval indicators according to the attributes of the rating indicators themselves. The types of indicators are processed consistently before evaluation, and the different types of indicators are converted into consistency. The formula for converting extremely small indicators into extremely large indicators is: x * =M-x x * =1 / x Where M is the total amount of constraints, which is taken as an upper limit of the index, x is the extremely small index, and x* is the extremely large index converted from the extremely small index; this method is a differential conversion, which belongs to linear conversion and will not affect the evaluation conclusion; The formula for converting a medium-sized index into an extremely large index is: Where m is an allowed lower bound of the index, x ij is a centered indicator, x * ij It is a very large indicator after the conversion of the medium-sized indicator; The formula for converting interval indicators into very large indicators is: Among them, q1 and q2 are set parameters, which are the minimum and maximum values ​​of the intermediate type.

5. The SPO-AHP-based comprehensive passenger transport hub service quality evaluation method according to claim 3 is characterized in that: The original value preprocessing also includes the dimensionless processing method of indicators, and the power coefficient method is used to eliminate the difficulties caused by different dimensions and the influence of the large difference in data size on the calculation accuracy. The calculation formula is: Where M' j and m' j They are respectively j The upper and lower limits of the value are as follows: c and d are known constants. The function of c is to translate the changed value, and the function of d is to enlarge and reduce the transformed value. Here, c=50 and d=50.

6. The SPO-AHP-based comprehensive passenger transport hub service quality evaluation method according to claim 1 is characterized in that: The comprehensive passenger transport hub evaluation method of AHP in step S3 is the hierarchical analysis method, which compares multiple indicators in pairs, determines the judgment matrix, and calculates the decision weight; the analysis steps include: A1. Decompose the evaluation factors into several levels and construct a hierarchical structure of the system; A2. Compare the elements of each level from top to bottom and construct the indicator importance judgment matrix; A3. Calculate the weight of each indicator element relative to the criterion; A4. Calculate the combined weight of each layer element relative to the system goal.

7. The SPO-AHP-based comprehensive passenger transport hub service quality evaluation method according to claim 6 is characterized in that: In step A1, complex problems are decomposed to make them hierarchical and organized, and a hierarchical structural model is constructed. The decomposed components in the model are called elements, which are divided into several groups according to their attributes to form different levels. There are three levels: The target layer, which is the predetermined goal and ideal result of the problem; The criterion layer, i.e. the intermediate links considered in achieving the goal, consists of several levels; The plan layer, also known as the measure layer, is the measures and decision-making plans taken to achieve the goals. Each layer controls less than 9 elements.

8. The SPO-AHP-based comprehensive passenger transport hub service quality evaluation method according to claim 6 is characterized in that: In step A2, appropriate scales are introduced to judge the relative importance of each factor in each level. Suppose there are n elements, the judgment matrix A can be constructed as follows: ij ) n×n , where a ij It represents the importance of factor i and factor j relative to the target, and its form is as follows: The matrix A has the following properties: a ij ＞0 a ji =1 / a ij (i,j=1,2,...,n) a ii =1(i,j=1,2,...,n); In the AHP, the relative importance of each indicator to the elements in the upper layer is marked, and the scaling method is introduced to form the above-mentioned numerical judgment matrix; In step A3, the main calculation of the hierarchical single sorting is performed by calculating the maximum eigenvalue and eigenvector of the judgment matrix.

9. The SPO-AHP-based comprehensive passenger transport hub service quality evaluation method according to claim 1 is characterized in that: After the weights are determined in step S3, an evaluation model is constructed based on weighted average, a data set is prepared, and the data set is substituted into the model for training to optimize and improve the model; After completion, input the evaluation indicators and obtain the evaluation results.

10. The SPO-AHP-based comprehensive passenger transport hub service quality evaluation method according to claim 1, characterized in that: In step S4, the grade division is based on the K-Means clustering method for analysis. The comprehensive evaluation result data of multiple comprehensive passenger transport hubs are collected as sample data, the number of clusters to be divided is determined, the cluster center is randomly initialized, and then the distance from each sample data point to each cluster center is calculated. The sample point is assigned to the cluster with the nearest cluster center according to the distance, and then the center of each cluster is recalculated. The process of assigning and updating the cluster center is repeated until the cluster center no longer changes or the set number of iterations is reached. Each cluster represents a service quality level, and the corresponding hub service quality level is determined based on the cluster where the sample is located; in step S5, the grade division includes excellent, good, medium, poor and bad.

Images