CN113379318A

CN113379318A - Method and device for evaluating operation service quality of public transport system and computer equipment

Info

Publication number: CN113379318A
Application number: CN202110753169.4A
Authority: CN
Inventors: 罗建平; 陈欢; 杨森彬; 李志武; 陈招帆; 尹杰丽; 冯川
Original assignee: Guangzhou Jiaoxin Investment Technology Co Ltd
Current assignee: Guangzhou Jiaoxin Investment Technology Co Ltd
Priority date: 2021-07-02
Filing date: 2021-07-02
Publication date: 2021-09-10

Abstract

The application relates to a method and a device for evaluating the operation service quality of a public transport system and computer equipment. The method comprises the following steps: receiving a message carrying an index category, and acquiring a public transportation system operation service evaluation refinement index corresponding to the index category, a discrimination matrix parameter of the public transportation system operation service evaluation refinement index and public transportation system operation data according to a preset public transportation system operation service quality evaluation index system; inputting the operation data of the public transportation system into the trained index statistical model to obtain statistical parameters of index values of the operation service evaluation refinement indexes of the public transportation system; inputting the discrimination matrix parameters of the operation service evaluation refinement indexes of the public transport system into the trained weight determination model to obtain the weights of the operation service evaluation refinement indexes of the public transport system; and evaluating the statistical parameters and the weights of the detailed indexes based on the operation service of the public transport system to obtain the evaluation result of the indexes. The method can improve the evaluation accuracy.

Description

Method and device for evaluating operation service quality of public transport system and computer equipment

Technical Field

The application relates to the technical field of public transportation evaluation, in particular to a method and a device for evaluating the operation service quality of a public transportation system, computer equipment and a storage medium.

Background

Urban public transport is an important component of urban infrastructure, which is closely related to the productive life of people. For a public transport system of a city, the operation system structure of the urban public transport system is an important factor for determining the comprehensive performance of the urban public transport system, so that the evaluation of the public transport system is particularly important. Therefore, experts or scholars propose a public transport operation system evaluation method.

Most of the existing public transport operation service quality evaluation methods determine scores of multiple indexes first, and then adopt a subjective artificial weighting method to obtain one score. The evaluation method basically stays in the dispersive rating of a plurality of indexes, cannot visually express the whole performance, or only evaluates one dimension or two dimensions.

Therefore, the existing public transport system operation service quality evaluation method has the problem of low evaluation accuracy. Due to inaccurate evaluation results, reasonable and reliable data support and reasonable guidance cannot be provided for the operation of the public transportation system.

Disclosure of Invention

In view of the above, it is necessary to provide a method, an apparatus, a computer device and a storage medium for evaluating the service quality of public transportation system operation with higher accuracy.

A method of assessing the quality of service of an operation of a public transportation system, the method comprising:

receiving a public transport system operation service quality evaluation message, wherein the public transport system operation service quality evaluation message carries index types of the operation service evaluation indexes of the public transport system to be evaluated;

acquiring operation data of a public transport system, and acquiring a public transport system operation service evaluation refinement index corresponding to an index category and a discrimination matrix parameter of the public transport system operation service evaluation refinement index according to a preset public transport system operation service quality evaluation index system;

inputting the operation data of the public transportation system into the trained index statistical model to obtain statistical parameters of index values of the operation service evaluation refinement indexes of the public transportation system, and inputting the discrimination matrix parameters of the operation service evaluation refinement indexes of the public transportation system into the trained weight determination model to obtain the weights of the operation service evaluation refinement indexes of the public transportation system;

obtaining an evaluation result of the operation service evaluation refinement index of the public transport system based on the statistical parameter of the operation service evaluation refinement index of the public transport system and the weight of the operation service evaluation refinement index of the public transport system;

the index statistical model and the weight determination model are obtained based on historical operation data training of the public transportation system.

An apparatus for evaluating quality of service in operation of a public transportation system, the apparatus comprising:

the information receiving module is used for receiving the operation service quality evaluation information of the public transport system, and the operation service quality evaluation information of the public transport system carries the index type of the operation service evaluation index of the public transport system to be evaluated;

the data acquisition module is used for acquiring the operation data of the public transportation system and acquiring the operation service evaluation refinement indexes of the public transportation system corresponding to the index categories and the judgment matrix parameters of the operation service evaluation refinement indexes of the public transportation system according to a preset operation service quality evaluation index system of the public transportation system;

the data processing module is used for inputting the operation data of the public transport system into the trained index statistical model to obtain statistical parameters of index values of the operation service evaluation refinement indexes of the public transport system, and inputting the discrimination matrix parameters of the operation service evaluation refinement indexes of the public transport system into the trained weight determination model to obtain the weights of the operation service evaluation refinement indexes of the public transport system;

the quality evaluation module is used for obtaining the evaluation result of the operation service evaluation refinement index of the public transport system based on the statistical parameters of the operation service evaluation refinement index of the public transport system and the weight of the operation service evaluation refinement index of the public transport system;

A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

The method, the device, the computer equipment and the storage medium for evaluating the operation service quality of the public transport system have the advantages that a complete and comprehensive operation service quality evaluation index system of the public transport system is preset, various detailed indexes corresponding to index categories are defined in detail, powerful and reliable data support is provided, and the evaluation accuracy is improved; in addition, the statistical parameters and the weights of the operation service evaluation refinement indexes of the public transport system are determined through the trained index statistical model and the weight determination model, and further, the weights of all the indexes are considered during calculation, and the weights which are set by people are not depended on the weights which are set by people subjectively, so that the calculated scores of the operation service evaluation refinement indexes of the public transport system are more objective and accurate. Therefore, the method can improve the accuracy of the evaluation result, provide powerful and reliable data support for the operation of the public transportation system, and further provide reasonable guidance for the operation of the public transportation system.

Drawings

FIG. 1 is a diagram of an exemplary implementation of a method for assessing quality of service of a public transportation system;

FIG. 2 is a schematic flow chart illustrating a method for evaluating the quality of service of a public transportation system in one embodiment;

FIG. 3 is a schematic flow chart illustrating the scoring step for determining a detail index for a public transportation system operation service rating in one embodiment;

FIG. 4 is a schematic flow chart of a method for evaluating the quality of service in operation of a public transportation system in another embodiment;

FIG. 5 is a block diagram showing an arrangement of an operation service quality evaluating apparatus of a public transportation system according to an embodiment;

FIG. 6 is a block diagram showing the construction of an apparatus for evaluating the quality of service in operation of a public transportation system in another embodiment;

FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The method for evaluating the operation service quality of the public transport system can be applied to the application environment shown in figure 1. Wherein a user terminal 102 communicates with a server 104 over a network. The user can send a public transportation system operation service quality evaluation message carrying the index category of the public transportation system (hereinafter, may be referred to as a public transportation system) operation evaluation index to be evaluated to the server 104 through the user terminal 102, the server 104 receives the public transportation system operation service quality evaluation message, obtains the public transportation system operation data, obtains the public transportation system operation service evaluation refinement index (hereinafter, may be referred to as a refinement index) corresponding to the index category and the discriminant matrix parameter of the public transportation system operation service evaluation refinement index according to a preset public transportation system operation service quality evaluation index system, then inputs the public transportation system operation data to the trained index statistical model, obtains the statistical parameter of the index value of the public transportation system operation service evaluation refinement index, and inputs the discriminant matrix parameter of the public transportation system operation service evaluation refinement index to the trained weight determination model Obtaining the weight of the operation service evaluation refinement index of the public transport system; and obtaining the evaluation result of the operation service evaluation refinement index of the public transportation system based on the statistical parameter of the operation service evaluation refinement index of the public transportation system and the weight of the operation service evaluation refinement index of the public transportation system. The index statistical model and the weight determination model are obtained based on historical operation data training of the public transportation system. The user terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented as a stand-alone server or a server cluster composed of a plurality of servers.

In one embodiment, as shown in fig. 2, there is provided a method for evaluating the service quality of a public transportation system operation, which is described by taking the method as an example applied to the server in fig. 1, and comprises the following steps

Step 202, receiving a public transportation system operation service quality evaluation message, wherein the public transportation system operation service quality evaluation message carries index types of the operation service evaluation indexes of the public transportation system to be evaluated.

In the present application, the public transportation system takes a public transportation vehicle (which may be referred to as a bus) operation system as an example, and the operation service evaluation index of the public transportation system takes a bus operation system evaluation index as an example for explanation. In practical application, a user may select or input an index category to be evaluated, such as a "secondary index", by operating on an operation interface of a user terminal, and then click a "quantization" button or an "evaluation" button, at this time, the user terminal generates a public transportation system operation service quality evaluation message and sends the message to a server, and the message carries the "index category" for input or selection. In this embodiment, the index category may include a primary index, a secondary index, and a composite index. In practical application, the index selectivity of the user is wide, and the user can selectively evaluate the comprehensive index, each primary index or each secondary index according to the service requirement. From the application of bus operation evaluation, government level regulatory departments pay attention to the overall performance condition of a city and can select the output of comprehensive scores; if the bus enterprise pays attention to the performance condition of different dimensionality indexes of the enterprise per se along with time, the operation service quality of the enterprise is monitored, for example, the performance condition of a first-level index such as convenience is paid attention to, convenience can be selected, and if the performance condition of a second-level index, namely waiting time of the second-level index, subordinate to the convenience is paid attention to, waiting time can be selected.

And 204, acquiring the operation data of the public transportation system, and acquiring the operation service evaluation refinement indexes of the public transportation system corresponding to the index categories and the discrimination matrix parameters of the operation service evaluation refinement indexes of the public transportation system according to a preset operation service quality evaluation index system of the public transportation system.

The public transport system operation data comprises basic bus station data and the like, historical bus operation dynamic data and the like. In practical application, research personnel design a public transport system operation service quality evaluation index system framework in advance based on historical operation data of the public transport system, select and define a primary index and a secondary index, and construct a public transport system operation service quality evaluation index system. In specific implementation, 5 primary indexes, namely convenience, comfort, reliability, safety and enterprise management, and 26 secondary indexes are selected and defined according to the space granularity and the time granularity, wherein the space granularity and the time granularity are days, and the specific reference can be made to a public transport system operation service quality evaluation index system shown in table 1.

In this embodiment, the operation service evaluation refinement indexes of the public transportation system corresponding to the index category include 5 refinement indexes corresponding to (included in) the primary index and 26 refinement indexes corresponding to (included in) the secondary index.

In this embodiment, the decision matrix parameter of the operation service evaluation refinement index of the public transport system includes an FIRST parameter or a SECOND parameter, where the FIRST parameter includes related information of a FIRST-level index, and the data type of the FIRST parameter is a three-dimensional array. The 0 th dimension is a judgment matrix of five first-level indexes of bus operation quality convenience, comfort, reliability and safety and enterprise management, the 1 st dimension is a first-level index code, and the 2 nd dimension represents an index name corresponding to the first-level index code. The FIRST parameters are described in Table 2 below, with the primary index codes CV, CT, RL, SC, EO.

The SECOND parameter comprises judgment matrixes, index codes and index name information of all secondary indexes. In this embodiment, the SECOND parameter includes a SECOND index evaluation matrix, an index code, and index name information corresponding to the five first indexes of convenience, comfort, reliability, and security. The information of each secondary index is similar to the FIRST parameter description table. The detail of the SECOND parameters is shown in Table 3.

Specifically, the decision matrix in this embodiment is a simple and easy questionnaire, and the research and development staff designates a series of filling rules, and integrates the score matrix formed by integrating the filling contents in all aspects by extensively inquiring the passengers who take the bus, the bus enterprise leadership and the opinions of the government regulatory department. In this example, the decision matrix is shown in table 4 below.

TABLE 1 evaluation index system for service quality in public transport system operation

TABLE 2 FIRST parameters description

TABLE 3 SECOND parameter description

TABLE 4 discrimination matrix

The public transport system operation service quality evaluation index system constructed by the embodiment provides reliable and powerful algorithm model support for urban public transport system operation service quality evaluation, and can assist traffic management departments and transportation enterprises to improve the operation efficiency of buses and services, so that citizens can experience more convenient, efficient and satisfactory bus trips.

Step 206, inputting the operation data of the public transportation system into the trained index statistical model, determining the statistical parameters of the operation service evaluation refinement indexes of the public transportation system, and inputting the discriminant matrix parameters of the operation service evaluation refinement indexes of the public transportation system into the trained weight determination model to obtain the weights of the operation service evaluation refinement indexes of the public transportation system.

The index statistical model is obtained based on the historical operation data training of the public transportation system. In this embodiment, the operation data of the public transportation system input into the index statistical model includes a bus violation operation table, a historical per-trip scheduling state table, an online bus taking transaction record, bus stop longitude and latitude information, and bus stop reporting data. The statistical parameters refer to the mean, maximum, minimum and variance obtained from the index values of the refinement indexes. The index value of the operation service evaluation refinement index of the public transport system refers to the performance condition of the operation service evaluation refinement index of the public transport system, taking the refinement index of the secondary index as an example, the index value comprises specific numerical values of the indexes such as waiting duration, running speed, clear index and the like.

The weight determination module is obtained by training based on historical operation data of the public transportation system. In specific implementation, the input data of the weight determination model is normalized FIRST parameters and SECOND parameters, and the output data is index codes of the detailed indexes of the public transport system operation service evaluation and the weights of the indexes (also called comprehensive distance weights). Specifically, the method for determining the weight may include a telffe method, a principal component analysis method, an analytic hierarchy method, an entropy method, and the like.

And 208, obtaining an evaluation result of the operation service evaluation refinement index of the public transport system based on the statistical parameters of the operation service evaluation refinement index of the public transport system and the weight of the operation service evaluation refinement index of the public transport system.

After the statistical parameters and the weights of the refining indexes are obtained, an optimal solution and a worst solution can be obtained based on the statistical parameters, then, the distances between the index values of the refining indexes and the optimal solution and the worst solution are solved by considering the weights of the refining indexes, and then, an evaluation result is obtained according to the distances. Specifically, the evaluation result includes a score, a grade, an evaluation report, and the like, and the score includes a composite score and a mean score.

In the method for evaluating the operation service quality of the public transport system, a complete and comprehensive operation service quality evaluation index system of the public transport system is preset, and various detailed indexes corresponding to the index categories are defined in detail, so that powerful and reliable data support is provided, and the evaluation accuracy is improved; in addition, the statistical parameters and the weights of the operation service evaluation refinement indexes of the public transport system are determined through the trained index statistical model and the weight determination model, and further, the weights of all the indexes are considered during calculation, and the weights which are set by people are not depended on the weights which are set by people subjectively, so that the calculated scores of the operation service evaluation refinement indexes of the public transport system are more objective and accurate. By adopting the method, the accuracy of the evaluation result can be improved, powerful and reliable data support is provided for the operation of the public transportation system, and further reasonable guidance can be provided for the operation of the public transportation system.

As shown in FIG. 3, in one embodiment, step 208 includes:

step 220, evaluating the index value of the refinement index based on the operation service of the public transportation system, and constructing an input vector;

step 230, constructing a maximum vector and a minimum vector based on the statistical parameters of the index values of the operation service evaluation refinement indexes of the public transportation system;

step 240, determining a first distance between the input vector and the maximum value vector and a second distance between the input vector and the minimum value vector according to the weight of the evaluation refinement index of the public transportation system operation service;

and 250, obtaining the score of the service evaluation refinement index of the public transportation system according to the first distance and the second distance.

The input vectors include a composite vector and a mean vector, wherein the composite vector is used to calculate a composite score and the mean vector is used to calculate a mean score. In specific implementation, taking the calculation of the scores of the secondary indexes as an example, the input vector may be constructed based on the index values of each secondary index, the maximum value vector may be constructed based on the maximum value of the index values of the secondary indexes, and the minimum value vector may be constructed based on the minimum value of the index values of the secondary indexes. Then, based on the weights of the two-stage indexes, a first distance between the input vector and the maximum value vector and a second distance between the input vector and the minimum value vector are calculated respectively and recorded, and then the score of each two-stage index is obtained according to the first distance and the second distance.

Specifically, a comprehensive vector may be constructed based on the index values of the secondary indexes, and then, the distances between the comprehensive vector and the maximum vector and the distance between the comprehensive vector and the minimum vector are calculated respectively by using the above formula, and then, a comprehensive score is calculated.

Specifically, a value (maximum value) that is optimal for each index or each set of indices (after normalization) may be obtained and constructed as a maximum value vector

Similarly, the value (minimum value) that shows the worst (after normalization processing) in each index or each group of indexes is obtained, and a minimum value vector is constructed

Taking the calculation of the integrated score as an example, the following formula can be used to calculate the distance between the integrated vector and the maximum vector:

the following formula can be used to calculate the distance between the integrated vector and the minimum vector:

based on DI⁺And DI^-And calculating a comprehensive score SI:

as shown in FIG. 4, in another embodiment, step 208 includes: step 210, constructing a mean vector based on a mean value in target index values of the public transport system operation service evaluation refinement indexes; according to the weight of the operation service evaluation refinement index of the public transport system, determining the distance between the mean vector and the maximum vector and the distance between the mean vector and the minimum vector; and obtaining the mean score of the operation service evaluation refinement index of the public transport system according to the distance between the mean vector and the maximum vector and the distance between the mean vector and the minimum vector.

The following formula can be used to calculate the distance between the mean vector and the maximum vector:

the distance between the mean vector and the minimum vector can be calculated by the following formula:

based on DA⁺And DA^-Calculating a mean score SA:

the operation service evaluation refinement indexes of the public transport system take two-level indexes as an example, wherein M represents the mth two-level evaluation index, M represents the number of all the two-level indexes in the evaluation system, and b_mIndex value, w, representing the m-th index in the maximum value vector_mIndex value, x, representing the m-th index in the minimum value vector_mIndex value, a, representing the m-th index in the integrated vector_mIndex value, ω, representing the m-th index in the mean vector_mRepresenting the weight of each corresponding secondary index.

In the embodiment, the weight of each refinement index is considered, the distance between the maximum vector and the input vector and the distance between the minimum vector and the input vector are solved, and then the score is calculated, so that the score is more objective and real.

As shown in fig. 4, in an embodiment, after obtaining a mean score of the refinement index of the operation service evaluation of the public transportation system according to the distance between the mean vector and the maximum vector and the distance between the mean vector and the minimum vector, the method further includes: and 212, determining the grade of the operation service evaluation refinement index of the public transport system according to the mean score of the operation service evaluation refinement index of the public transport system and a preset grade division rule.

Specifically, the preset rating rule is as follows:

let the mean score be M and the highest score be A

C＝0.9*M,

D＝1.2*M,

The indexes are divided into four grades of good medium-difference:

and (3) excellent: x is belonged to (B, A)

Good: x is belonged to (C, B)

The method comprises the following steps: x is belonged to (D, C)

Difference: x is an element [0, D ]

In the embodiment, the indexes are graded according to the mean score and the preset grade division rule, so that the quantitative result of the indexes can be expressed more comprehensively and intuitively. Different from the traditional method for judging the grade by good medium-difference, the traditional method for judging the grade by good medium-difference is that the grade value range is generally divided by people in a subjective way when the index grade is judged, and the grade value range is not changed after the grade value range is determined, so that certain hysteresis exists. In the embodiment, the value ranges of four excellent intermediate and poor grades are automatically determined by taking objective historical data as a model, so that artificial subjective interference is avoided; and the value range of the grade can be finely adjusted along with the change of the historical data, so that the grade discrimination is advanced with time.

In one embodiment, step 206 includes: inputting the operation data of the public transportation system into the trained index statistical model, calling the trained index statistical model to determine the index value of the operation service evaluation refinement index of the public transportation system by adopting a preset quantization method of the operation service evaluation refinement index of the public transportation system and a preset interactive query engine for the operation data of the public transportation system, and obtaining the statistical parameter of the operation service evaluation refinement index of the public transportation system based on the index value of the operation service evaluation refinement index of the public transportation system.

In specific implementation, research and development personnel formulate a quantitative method of the secondary index, which can be specifically referred to in fig. 3. The distance indicates a quantization method of several secondary indexes: the direct route rate is the probability that a passenger can directly reach a destination by taking a route. The specific quantification method is as follows:

(1) removing abnormal lines: and eliminating the lines with less than 5 lines recorded by card swiping each day in the database on average, such as some temporarily opened lines.

(2) And (4) according to a passenger od derivation result table in the database, calculating the proportion of the number of the passengers to be driven directly to the route to the total number of the passengers in a certain time interval in history. That is to say that the first and second electrodes,

wherein, direct _ num represents the number of people that the passenger gets on the waiting line, and total represents the total number of passengers on the line.

The transfer duration, namely the time spent on one average transfer in the line to be solved, is used for evaluating the time spent on one transfer in the line, and the index is the comprehensive expression of the duration of the distance from a transfer point and the waiting of another route vehicle at the transfer point. The specific quantification method is as follows:

(1) screening out buses (including an od starting station or an od midway station) as a starting point from a database;

(2) screening out public transport transfer buses or public transport transfer subways;

(3) removing abnormal values: eliminating the brush records of the subway at the beginning; removing the card swiping record of the final stroke of the od; rejecting records with transfer time less than or equal to 0 second; rejecting lines with average daily card swiping records less than 5;

(4) and solving the time consumed by each transfer, finding out the card swiping and boarding time of the next card swiping record of the card swiping records, and solving the average transfer duration. That is to say that the first and second electrodes,

wherein, wt_iIs shown as<4>The transfer duration of the ith record in the environment records screened in the step is n records in total.

The riding experience is defined in the application and is determined by three-dimensional comprehensive representation values of rapid acceleration, rapid deceleration and rapid turning. Wherein each dimension weight is respectively defined as w₂₁＝1.3,w₂₂＝1.2,w₂₃＝1.2,w₂₄1.3, the number of occurrences in each dimension is b₁₁,b₁₂,b₁₃The composite value of riding feeling is

The violation index is defined by the comprehensive expression values of four dimensions of overspeed, door opening with speed, door opening driving and border crossing. Wherein each dimension weight is respectively defined as w₂₁＝1.3,w₂₂＝1.2,w₂₃＝1.2,w₂₄1.3, the number of occurrences in each dimension is b₂₁,b₂₂,b₂₃,b₂₄I.e. violation index of

In practical application, an evaluation index system of the operation service quality of the public transportation system is established on the premise of mass data, for example, more than 700 million passenger riding transaction records are generated in Guangzhou city on average every day. Such a huge amount of data poses new challenges to the computation speed and the computation memory. Based on this, in this embodiment, a distributed big data solution based on an inpala SQL (Structured Query Language) engine is used to solve the statistical problem of the index value of each index of each line. It is understood that in other embodiments, other interactive query engines may be employed, and are not limited thereto. Specifically, different indexes may be processed, and for each index, index values of the indexes may be queried and calculated in different partitions. And after the index values of all the indexes of all the lines are obtained, establishing a temporary table, dropping a disk, and counting the statistical parameters of the index values. If the memory consumption is too large in the process of extracting a single index, a partition method is adopted, for example, the processing is performed in sequence by a single line; or sequentially processing the index values of the indexes every day, falling to a disk, and then counting the statistical parameters of the indexes according to the data obtained by processing every day. If SQL is not realized in the realization process, the functions are realized by adopting an impala self-defined function. In this embodiment, the index statistics is performed by the interactive query engine, so that the index statistics can be completed quickly, and the memory is saved.

In one embodiment, step 220 includes: the index value of the operation service evaluation refinement index of the public transport system is subjected to forward processing and standardization processing to obtain a target index value of the operation service evaluation refinement index of the public transport system, and an input vector is constructed on the basis of the target index value of the operation service evaluation refinement index of the public transport system;

step 230 includes: screening out the maximum value and the minimum value in the target index values of the operation service evaluation refinement indexes of the public transport system; and evaluating the maximum value of the target index value of the refinement index based on the operation service of the public transportation system, constructing a maximum value vector, evaluating the minimum value of the target index value of the refinement index based on the operation service of the public transportation system, and constructing a minimum value vector.

In practical applications, the index type may include not only an extremely large index (i.e., a forward index), but also several types of indexes such as an extremely small index, a block index, and an intermediate index. Therefore, it is necessary to perform a normalization process on each refinement index. The index forward processing means processing the index value, so that the index has the characteristic that the larger the value is, the better the performance is. Specifically, the extremely small scale index is normalized:

x′_i＝max-x_i

forward regional indexes:

assuming that the optimal interval value range of the interval type index is between [ a, b ], then,

M＝max{a-min{x_i},max{x_i}-b}

normalizing intermediate indexes:

suppose that the optimal value of the intermediate index is x_bestThen, the first step is executed,

after the index is subjected to forward processing, further normalization processing is required, and specifically, the normalization processing can be performed in the following manner:

in specific implementation, after the index values of the refining indexes are subjected to forward and standardization processing, the input vector, the maximum vector and the minimum vector are respectively constructed, so that the data tend to be normalized, and the score is convenient to calculate.

In one embodiment, evaluating the weight of the refinement indicator according to a public transportation system operation service, the determining a first distance of the input vector from the maximum value vector and a second distance of the input vector from the minimum value vector comprises: and according to the weight of the operation service evaluation refinement index of the public transport system, determining a first distance between the input vector and the maximum value vector and a second distance between the input vector and the minimum value vector by combining a preset distance weighting topsis algorithm.

In this embodiment, a distance weighted topsis algorithm is adopted to determine the first distance and the second distance. The distance between vectors is determined by adopting a distance weighting topsis algorithm, the advantages of the topsis algorithm that the data distribution and the sample content index are not strictly limited are fully utilized, and the distance weighting topsis algorithm is combined with a bus scene to solve the problems of multiple indexes and strong uncertainty of data distribution in the scene; and the comprehensive score is more objective and real.

In one embodiment, the decision matrix parameter of the public transportation system operation service evaluation refinement index comprises a decision matrix of the public transportation system operation service evaluation index;

inputting the discrimination matrix parameters of the operation service evaluation refinement indexes of the public transport system into the trained weight determination model, and obtaining the weights of the operation service evaluation refinement indexes of the public transport system comprises the following steps:

determining the n-th-order root of a discrimination matrix of the operation service evaluation refinement index of the public transport system;

carrying out normalization processing on the n-th-order root of the discrimination matrix of the operation service evaluation refinement index of the public transport system to obtain the importance weight of the operation service evaluation refinement index of the public transport system;

and obtaining the weight of the operation service evaluation refinement index of the public transport system according to the importance weight and a preset weight coefficient of the operation service evaluation refinement index of the public transport system.

In this embodiment, the evaluation index of the operation service of the public transportation system to be evaluated is a secondary index, the decision matrix is a decision matrix in table 3, and the decision matrix is of 5 th order, so that n is 5, and the root of the 5 th power of each row parameter in table 3 is obtained and is 0.7028, 0.4503, 1.4310, 4.9036 and 0.4503 respectively. Then, the 5-time root is normalized to obtain the importance weight of the primary index, namely, the importance weight of the 5 primary indexes of convenience, comfort, reliability, safety and enterprise operation is obtained according to the judgment matrix when the bus operation quality is evaluated. Specifically, normalization is performed according to the following formula:

when the direct target of bus operation quality evaluation is obtained, the important weights of convenience, comfort, reliability, safety and enterprise operation are 0.0885, 0.0567, 0.1803, 0.6177 and 0.0567 respectively. And multiplying each importance weight by a preset weight coefficient of the secondary index to obtain the weight of each secondary index, namely the weight of the index corresponding to the discriminant matrix relative to the index target. In this embodiment, the calculated weight can be made more accurate by performing normalization processing on the discrimination matrix.

As shown in fig. 4, in one embodiment, after step 208, the method further includes:

step 214, when receiving an evaluation report generation message of an index category carrying the public transportation system operation service evaluation index sent by the user terminal, obtaining an index value and an evaluation result of the public transportation system operation service evaluation refinement index corresponding to the index category, and generating an evaluation report of the public transportation system operation service evaluation index based on the index value and the evaluation result of the public transportation system operation service evaluation refinement index and by combining a preset report field generation rule.

After the score and the grade corresponding to the operation service evaluation refinement index of the public transport system are obtained, a corresponding evaluation report can be generated. In specific implementation, an evaluation report of the operation service evaluation index of the public transport system is generated by combining a preset report field generation rule based on the index value and the evaluation result of the operation service evaluation refinement index of the public transport system corresponding to the index category. The evaluation report is a simple and easy-to-understand line or enterprise operation service report for the user, and comprises six fields of report date, route, index type, state, trend and suggestion of specified indexes of the time period to be evaluated. Specifically, the method comprises the step of generating simple and comprehensive constructive suggestions in a text form according to the evaluation level, the score records of each index, the time characteristics and the like. The principle of the automatic generation of the fields is as follows: the generation of the three fields of the report date, the report line and the index type is obtained according to the operation data obtained by the user in the process of using the evaluation system. The report date is the specific time for printing the report; a line field, wherein if the monitored space granularity is the operation condition of the whole vehicle enterprise, the field is the name of the vehicle enterprise, and if the monitored space granularity is a certain line, the field is the name of the line, and so on; the index types comprise comprehensive indexes, primary indexes and secondary index codes, and can be obtained by input data when a user evaluates.

A state field: the status field takes on the values "normal", "poor" and "better". When the number of times that the evaluation result level in the evaluated date is "medium" is more than half, the status field is "normal"; when the evaluation result level in the evaluation date is that the ratio of the number of times of "superior" is more than half, the state field is "superior"; the status field is "poor" when the result level of evaluation in the evaluated date is "poor" more than half the number of times.

A trend field: the trend field takes values of "stable", "rising", "falling", "fluctuating". And judging the trend by adopting an average slope judgment method. Specifically, one average line is selected, the average line inclines upwards, the trend is determined to be upwards, the average line inclines downwards, and the trend is determined to be downwards. The above four states of the trend are judged by different expressions of the average line.

A proposal field: the field is mainly used for screening out indexes with index values smaller than the mean value from the index values of the comprehensive indexes, the first-level indexes and the second-level indexes, and then providing directional suggestions and guidance. The method comprises the following specific steps:

the method comprises the following steps: calculating the mean value of each index corresponding to the index type;

step two: calculating the actual value of each index evaluated at this time;

step three: screening out indexes with actual values smaller than the average value, and judging the indexes with poor performance;

step four: and providing directional guidance based on the indexes with poor performance, for example, if the comfort of the first-level index is poor in overall performance, automatically giving suggestions by a program: "[ comfortableness ] indexes of the line are poor and can be improved; if the thousand kilometers income of the second grade index under the first grade index enterprise operation is poor, the procedure gives automatically: the enterprise management can properly improve the kilokilometer income index. In the embodiment, the operation quality of the public transportation system can be simply and intuitively reflected by generating the evaluation report, and the convenience and experience of a user are improved.

The application constructs a set of perfect public transport system operation service quality evaluation index system, can assist the traffic management department and the traffic enterprises to improve the efficiency of public transport vehicles and service operation, and is specifically represented as the following application:

the application one is as follows: from the perspective of industry supervision, a city supervision department can monitor the trend that the comprehensive score of the overall operation service of the bus changes along with the change of dates; the trend that a certain more detailed index (such as convenience) score of the bus changes along with the change of the date can also be monitored. The method is beneficial to dynamically monitoring the urban bus operation service quality by a supervision department, so that relevant systems and policies which are more reasonable are made for macroscopic regulation and control and designation.

The application II comprises the following steps: from the perspective of a public transportation group, for example, the public transportation group belongs to a plurality of public transportation enterprises, and under the same time dimension, the public transportation group can compare the overall operation conditions of different enterprises or the more detailed performance conditions of indexes (such as convenience). Therefore, the quality conditions of different public transportation enterprises are evaluated, so that good competition among enterprises in a group is formed, service quality early warning is provided for the enterprises, and higher-quality public transportation travel service is provided for urban residents.

The application is as follows: from the perspective of a public transportation enterprise, the enterprise can use the evaluation system to monitor the overall performance of a certain line, or check the performance of a certain primary index, such as the performance of a primary index for monitoring convenience, or monitor the performance of a certain refined secondary index. And specific detailed schemes such as line adjustment, shift time adjustment, driver behavior training and the like are made to improve line evaluation scores and provide better urban public transportation service.

It should be understood that, although the steps in the flowcharts related to the above embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in each flowchart related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.

In one embodiment, as shown in fig. 5, there is provided a public transportation system operation service quality evaluation device, including: a message receiving module 510, a data obtaining module 520, a data processing module 530 and a quality evaluation module 540, wherein:

the message receiving module 510 is configured to receive a public transportation system operation service quality evaluation message, where the public transportation system operation service quality evaluation message carries an index type of a public transportation system operation service evaluation index to be evaluated.

The data acquisition module 520 is configured to acquire the operation data of the public transportation system, and acquire the operation service evaluation refinement index of the public transportation system corresponding to the index category and the decision matrix parameter of the operation service evaluation refinement index of the public transportation system according to a preset operation service quality evaluation index system of the public transportation system.

The data processing module 530 is configured to input the operation data of the public transportation system to the trained index statistical model to obtain a statistical parameter of an index value of the operation service evaluation refinement index of the public transportation system, and input a decision matrix parameter of the operation service evaluation refinement index of the public transportation system to the trained weight determination model to obtain a weight of the operation service evaluation refinement index of the public transportation system.

And the quality evaluation module 540 is used for obtaining an evaluation result of the operation service evaluation refinement index of the public transport system based on the statistical parameters of the operation service evaluation refinement index of the public transport system and the weight of the operation service evaluation refinement index of the public transport system.

The operation service quality evaluation device of the public transport system is provided with a complete and comprehensive operation service quality evaluation index system of the public transport system in advance, and detailed definition of various detailed indexes corresponding to index categories provides powerful and reliable data support, and is beneficial to improving the evaluation accuracy; in addition, the statistical parameters and the weights of the operation service evaluation refinement indexes of the public transport system are determined through the trained index statistical model and the weight determination model, and further, the weights of all the indexes are considered during calculation, and the weights which are set by people are not depended on the weights which are set by people subjectively, so that the calculated scores of the operation service evaluation refinement indexes of the public transport system are more objective and accurate. The evaluation result obtained by the device can provide powerful and reliable data support for the operation of the public transportation system, and further provide reasonable guidance for the operation of the public transportation system.

In one embodiment, the quality evaluation module 540 is further configured to construct an input vector based on the index value of the public transportation system operation service evaluation refinement index; the method comprises the steps of evaluating statistical parameters of index values of thinning indexes based on public transport system operation service, and constructing a maximum vector and a minimum vector; according to the weight of the thinning index of the public transport system operation service evaluation, determining a first distance between the input vector and the maximum value vector and a second distance between the input vector and the minimum value vector; and obtaining the score of the operation service evaluation refinement index of the public transport system according to the first distance and the second distance.

In one embodiment, the metric statistics module 530 is further configured to input public transportation system operational data to the trained metric statistics model; calling a trained index statistical model to determine an index value of the operation service evaluation refinement index of the public transport system by adopting a preset quantization method of the operation service evaluation refinement index of the public transport system and a preset interactive query engine on operation data of the public transport system; and obtaining the statistical parameters of the operation service evaluation refinement indexes of the public transport system based on the index values of the operation service evaluation refinement indexes of the public transport system.

As shown in fig. 6, in an embodiment, the quality evaluation module 540 includes a vector construction unit 542, configured to perform forward processing and standardization processing on the index value of the public transportation system operation service evaluation refinement index to obtain a target index value of the public transportation system operation service evaluation refinement index; based on a target index value of a public transport system operation service evaluation refinement index, constructing an input vector; screening out the maximum value and the minimum value in the target index values of the operation service evaluation refinement indexes of the public transport system; and evaluating the maximum value of the target index value of the refinement index based on the operation service of the public transportation system, constructing a maximum value vector, evaluating the minimum value of the target index value of the refinement index based on the operation service of the public transportation system, and constructing a minimum value vector.

In one embodiment, the quality evaluation module 540 comprises a distance determination unit 544 for determining a first distance between the input vector and the maximum value vector and a second distance between the input vector and the minimum value vector in combination with a preset distance weighted topsis algorithm according to the weight of the public transportation system operation service evaluation refinement indicator.

In one embodiment, the quality evaluation module 540 is further configured to construct a mean vector based on a mean of target index values of the public transportation system operation service evaluation refinement index; according to the weight of the operation service evaluation refinement index of the public transport system, determining the distance between the mean vector and the maximum vector and the distance between the mean vector and the minimum vector; and obtaining the mean score of the operation service evaluation refinement index of the public transport system according to the distance between the mean vector and the maximum vector and the distance between the mean vector and the minimum vector.

As shown in fig. 6, in one embodiment, the quality evaluation module 540 comprises a ranking unit 546 for determining a ranking of the public transportation system operation service evaluation refinement indicator according to a preset ranking rule and a mean score of the public transportation system operation service evaluation refinement indicator.

In one embodiment, the quality evaluation module 540 further includes an evaluation report generating unit 548, configured to, when receiving an evaluation report generating message of an index category carrying a public transportation system operation service evaluation index sent by a user terminal, obtain an index value and an evaluation result of a public transportation system operation service evaluation refinement index corresponding to the index category; and generating an evaluation report of the operation service evaluation index of the public transport system by combining a preset report field generation rule based on the index value and the evaluation result of the operation service evaluation refinement index of the public transport system.

In one embodiment, the data processing module 530 is further configured to determine a root of the discriminant matrix of the public transportation system operation service evaluation refinement indicators; carrying out normalization processing on the n-th-order root of the discrimination matrix of the operation service evaluation refinement index of the public transport system to obtain the importance weight of the operation service evaluation refinement index of the public transport system; and obtaining the weight of the operation service evaluation refinement index of the public transport system according to the importance weight and a preset weight coefficient of the operation service evaluation refinement index of the public transport system.

For a specific embodiment of the device for evaluating the operation service quality of the public transportation system, reference may be made to the above embodiment of the method for evaluating the operation service quality of the public transportation system, and details are not described here. All or part of each module in the public transport system operation service quality evaluation device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing a public transport system operation service quality evaluation index system, a discrimination matrix parameter of a public transport system operation service evaluation refinement index, public transport system operation data and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a public transportation system operation service quality evaluation method.

Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the method for evaluating the operation service quality of the public transportation system when executing the computer program.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the above-mentioned public transportation system operation service quality evaluation method.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A method for evaluating the service quality of public transportation system operation is characterized by comprising the following steps:

receiving a public transport system operation service quality evaluation message, wherein the public transport system operation service quality evaluation message carries index categories of public transport system operation service evaluation indexes;

acquiring operation data of a public transport system, and acquiring a public transport system operation service evaluation refinement index corresponding to the index category and a decision matrix parameter of the public transport system operation service evaluation refinement index according to a preset public transport system operation service quality evaluation index system;

inputting the operation data of the public transportation system into a trained index statistical model to obtain statistical parameters of the operation service evaluation refinement indexes of the public transportation system, and inputting the discrimination matrix parameters of the operation service evaluation refinement indexes of the public transportation system into a trained weight determination model to obtain the weights of the operation service evaluation refinement indexes of the public transportation system;

the index statistical model and the weight determination model are obtained by training based on historical operation data of a public transport system.

2. The method for evaluating the operation service quality of the public transportation system according to claim 1, wherein the step of inputting the operation data of the public transportation system into the trained index statistical model to obtain the statistical parameters of the refined index of the operation service evaluation of the public transportation system comprises the following steps:

inputting the public transportation system operation data into a trained index statistical model;

calling the trained index statistical model to determine an index value of the public transport system operation service evaluation refinement index by adopting a preset quantization method of the public transport system operation service evaluation refinement index and a preset interactive query engine for the public transport system operation data;

and obtaining the statistical parameters of the operation service evaluation refinement indexes of the public transport system based on the index values of the operation service evaluation refinement indexes of the public transport system.

3. The method for evaluating the operation service quality of the public transportation system according to claim 2, wherein obtaining the evaluation result of the operation service evaluation refinement index of the public transportation system based on the statistical parameter of the operation service evaluation refinement index of the public transportation system and the weight of the operation service evaluation refinement index of the public transportation system comprises:

constructing an input vector based on the index value of the operation service evaluation refinement index of the public transportation system;

constructing a maximum value vector and a minimum value vector based on the statistical parameters of the operation service evaluation refinement indexes of the public transportation system;

determining a first distance between the input vector and the maximum value vector and a second distance between the input vector and the minimum value vector according to the weight of the refinement index evaluated by the public transportation system operation service;

and obtaining the score of the service evaluation refinement index of the public transport system according to the first distance and the second distance.

4. The mass transit system operation service quality evaluation method of claim 3, wherein the determining a first distance of the input vector from the maximum value vector and a second distance of the input vector from the minimum value vector according to the weight of the mass transit system operation service evaluation refinement indicator comprises:

and determining a first distance between the input vector and the maximum value vector and a second distance between the input vector and the minimum value vector by combining a preset distance weighting topsis algorithm according to the weight of the operation service evaluation refinement index of the public transport system.

5. The method of claim 3, wherein the constructing an input vector based on the index value of the service evaluation refinement index of the public transportation system comprises:

carrying out forward processing and standardization processing on the index value of the public transport system operation service evaluation refinement index to obtain a target index value of the public transport system operation service evaluation refinement index;

constructing an input vector based on a target index value of the operation service evaluation refinement index of the public transportation system;

the constructing a maximum vector and a minimum vector according to the statistical parameters of the service evaluation refinement indexes of the public transportation system comprises:

screening out the maximum value and the minimum value in the target index values of the operation service evaluation refinement indexes of the public transport system;

and constructing a maximum value vector based on the maximum value of the target index value of the public transportation system operation service evaluation refinement index, and constructing a minimum value vector based on the minimum value of the target index value of the public transportation system operation service evaluation refinement index.

6. The mass transit system operation quality of service evaluation method of claim 5, wherein the input vector comprises a mean vector and the score comprises a mean score; the obtaining of the score of the operation service evaluation refinement index of the public transportation system based on the statistical parameter of the operation service evaluation refinement index of the public transportation system and the weight of the operation service evaluation refinement index of the public transportation system comprises:

screening out the mean value in the target index values of the operation service evaluation refinement indexes of the public transport system, and constructing a mean value vector;

according to the weight of the operation service evaluation refinement index of the public transport system, determining the distance between the mean vector and the maximum vector and the distance between the mean vector and the minimum vector;

and obtaining the mean score of the operation service evaluation refinement index of the public transport system according to the distance between the mean vector and the maximum vector and the distance between the mean vector and the minimum vector.

7. The method of claim 6, wherein after obtaining the mean score of the refinement index of the public transportation system operation service evaluation according to the distance between the mean vector and the maximum vector and the distance between the mean vector and the minimum vector, the method further comprises:

and determining the grade of the operation service evaluation refinement index of the public transport system according to the mean score of the operation service evaluation refinement index of the public transport system and a preset grade division rule.

8. The method for evaluating the operation service quality of the public transportation system according to any one of claims 1 to 7, further comprising, after obtaining the evaluation result of the refinement index of the operation service evaluation of the public transportation system:

when receiving an evaluation report generation message of an index category carrying a public transport system operation service evaluation index sent by a user terminal, acquiring an index value and an evaluation result of a public transport system operation service evaluation refinement index corresponding to the index category;

and generating an evaluation report of the operation service evaluation index of the public transport system by combining a preset report field generation rule based on the index value and the evaluation result of the operation service evaluation refinement index of the public transport system.

9. The method of claim 1, wherein the discriminant matrix parameters of the operating service evaluation refinement indicators of the public transportation system comprise a discriminant matrix of the operating service evaluation indicators of the public transportation system;

the step of inputting the discrimination matrix parameters of the operation service evaluation refinement indexes of the public transport system into the trained weight determination model to obtain the weights of the operation service evaluation refinement indexes of the public transport system comprises the following steps:

and obtaining the weight of the operation service evaluation refinement index of the public transport system based on the importance weight and a preset weight coefficient of the operation service evaluation refinement index of the public transport system.

10. An apparatus for evaluating quality of service in operation of a public transportation system, the apparatus comprising:

the system comprises a message receiving module, a service quality evaluation module and a service quality evaluation module, wherein the message receiving module is used for receiving a public transport system operation service quality evaluation message, and the public transport system operation service quality evaluation message carries the index type of a public transport system operation service evaluation index to be evaluated;

the data acquisition module is used for acquiring the operation data of the public transportation system and acquiring the operation service evaluation refinement indexes of the public transportation system corresponding to the index categories and the discrimination matrix parameters of the operation service evaluation refinement indexes of the public transportation system according to a preset operation service quality evaluation index system of the public transportation system;

the data processing module is used for inputting the operation data of the public transport system into the trained index statistical model to obtain statistical parameters of the operation service evaluation refinement indexes of the public transport system, and inputting the discriminant matrix parameters of the operation service evaluation refinement indexes of the public transport system into the trained weight determination model to obtain the weights of the operation service evaluation refinement indexes of the public transport system;

the quality evaluation module is used for obtaining the evaluation result of the operation service evaluation refinement index of the public transport system based on the statistical parameter of the operation service evaluation refinement index of the public transport system and the weight of the operation service evaluation refinement index of the public transport system;