CN114418467B - Method and device for determining operation quality of airport bus and storage medium - Google Patents
Method and device for determining operation quality of airport bus and storage medium Download PDFInfo
- Publication number
- CN114418467B CN114418467B CN202210321381.8A CN202210321381A CN114418467B CN 114418467 B CN114418467 B CN 114418467B CN 202210321381 A CN202210321381 A CN 202210321381A CN 114418467 B CN114418467 B CN 114418467B
- Authority
- CN
- China
- Prior art keywords
- sample
- service data
- route
- sample detection
- quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000001514 detection method Methods 0.000 claims abstract description 195
- 238000013441 quality evaluation Methods 0.000 claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000003062 neural network model Methods 0.000 claims abstract description 11
- 238000011156 evaluation Methods 0.000 claims description 150
- 238000012545 processing Methods 0.000 claims description 69
- 238000004590 computer program Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 10
- 238000013528 artificial neural network Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000010606 normalization Methods 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013210 evaluation model Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 description 1
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013278 delphi method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The application provides a method, a device and a storage medium for determining the operation quality of an airport bus, comprising the following steps: acquiring operation service data of each to-be-detected route in a plurality of to-be-detected routes of the airport bus to be detected under each operation quality evaluation index in a preset time period; inputting a plurality of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model, and determining the grade of the operation quality of each route to be detected; the airport bus running quality evaluation model is obtained by training an initial neural network model by obtaining a plurality of sample running service data of various sample detection lines and a sample running quality grade corresponding to each sample running service data. Therefore, the specific situation of the operation quality of the airport bus can be visually displayed, the difference of the operation quality of the airport bus among routes can be reflected, and the accuracy of the estimation of the operation quality of the airport bus can be improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for determining an operation quality of an airport bus, and a storage medium.
Background
In recent years, the operation quality is widely applied to the evaluation in the fields of vehicles, air traffic control and the like, the operation quality has strong relevance with an evaluated object, and the evaluated object can be sensed and analyzed so as to reflect the comprehensive condition and the overall situation of the evaluated object. The method aims at the field of airport bus operation management, grasps the operation quality of the airport bus, is favorable for improving the airport bus service level, and has important guiding significance for exerting the advantage of bus capacity and relieving the pressure of airport ground transfer service.
At the present stage, the operation quality of the airport bus is lack of fine description, and the dilemma of lack of evaluation standards also exists, so that the problems of poor flexibility, unobvious grading characteristics of evaluation results and the like are caused. Therefore, how to quickly and accurately determine the operation quality of the airport bus becomes one of the important problems to be solved urgently in the ground traffic of the current airport.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a method, an apparatus and a storage medium for determining the operation quality of an airport bus, which can visually show the specific situation of the operation quality of the airport bus, and can further reflect the difference of the operation quality of the airport bus between routes, so as to improve the accuracy of the estimation of the operation quality of the airport bus.
The embodiment of the application provides a method for determining the operation quality of an airport bus, which comprises the following steps:
acquiring operation service data of each to-be-detected route in a plurality of to-be-detected routes of the airport bus to be detected under each operation quality evaluation index in a preset time period;
inputting a plurality of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model, and determining the grade of the operation quality of each route to be detected;
the airport bus operation quality evaluation model is obtained by training an initial neural network model by acquiring a plurality of sample operation service data of each sample detection line and a sample operation quality grade corresponding to each sample operation service data;
the sample running quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing and natural breakpoint processing on the sample running service data of the sample detection line.
In one possible embodiment, the grade of the sample running quality of each sample detection route is determined by the following steps of:
performing projection comprehensive evaluation processing on the multiple sample operation service data of each sample detection route, and determining sample operation evaluation data of each sample to-be-detected route;
carrying out natural breakpoint processing on a plurality of sample running evaluation data of each sample detection route, and determining the sample running quality value range of each sample detection route;
and carrying out grade division on the sample running evaluation data and the sample running quality range value of each sample detection route, and determining the grade of the sample running quality of each sample detection route.
In a possible implementation manner, the performing projection comprehensive evaluation processing on the multiple sample operation service data of the sample detection routes to determine the sample operation evaluation data of each sample detection route includes:
carrying out standardization processing on the multiple sample operation service data of each sample detection route to determine multiple reference operation service data of each sample detection route;
determining a reference value of each reference operation service data of each sample detection route based on the plurality of reference operation service data of each sample detection route;
and determining a connecting line on a multi-dimensional space based on the reference value of each reference operation service data of each sample detection route, and determining sample operation evaluation data of the sample detection route according to the distance from the vector set of the reference operation service data of the sample detection route to the connecting line on the multi-dimensional space.
In a possible implementation manner, the normalizing the plurality of sample operation service data of each sample testing route to determine the plurality of reference operation service data of each sample testing route includes:
determining the mean value of each sample operation service data of each sample detection line based on the total number of the sample detection lines and each operation service data of each sample detection line;
and determining the reference operation service data of each sample detection line based on the attribute of each sample operation service data, the average value of each sample operation service data and the number of the sample operation service data in the sample detection line.
In a possible embodiment, the performing natural breakpoint processing on multiple sample operation evaluation data of each sample inspection route to determine a sample operation quality value range of each sample inspection route includes:
performing natural breakpoint processing on the plurality of sample operation evaluation data to determine the plurality of sample operation evaluation breakpoint data;
and sequencing the plurality of sample running evaluation breakpoint data in a descending manner, and determining the range of the sample running quality value.
In a possible implementation manner, the performing a ranking process on the sample operation evaluation data and the sample operation quality range value of each sample detection route to determine the rank of the sample operation quality of each sample detection route includes:
determining a grade label of each sample operation quality value range based on the sample operation evaluation data of each sample detection route and the sample operation quality range value;
and matching the sample operation evaluation data of each sample detection line with a plurality of sample operation quality value ranges according to the sample operation evaluation data of each sample detection line, and if the sample operation evaluation data of the sample detection line is within the interval range of any one of the sample operation quality value ranges, giving the sample operation evaluation data of the sample detection line a grade label corresponding to the sample operation quality value range, and determining the grade of the sample operation quality of the sample detection line.
In one possible embodiment, the operation quality evaluation index includes: passenger experience evaluation indexes and bus running evaluation indexes; wherein,
the passenger experience evaluation index is used for representing the receptivity of the bus passengers under the line to be detected;
the bus operation evaluation index is used for representing the operation condition of the bus under the line to be detected.
The embodiment of the application also provides a device for determining the operation quality of the airport bus, which comprises:
the acquisition module is used for acquiring the operation service data of each to-be-detected route in the plurality of to-be-detected routes of the airport bus to be detected under each operation quality evaluation index in a preset time period;
the determining module is used for inputting a plurality of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model and determining the grade of the operation quality of each route to be detected; the method comprises the steps that an airport bus operation quality evaluation model is obtained by training an initial neural network model through obtaining a plurality of sample operation service data of various sample detection lines and a sample operation quality grade corresponding to each sample operation service data; the sample running quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing and natural breakpoint processing on the sample running service data of the sample detection line.
An embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine readable instructions being executed by the processor to perform the steps of a method for determining the operating quality of an airport bus as described above.
The present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to execute the steps of the method for determining the operation quality of an airport bus as described above.
The embodiment of the application provides a method, a device and a storage medium for determining the operation quality of an airport bus, wherein the determining method comprises the following steps: acquiring operation service data of each to-be-detected route in a plurality of to-be-detected routes of the airport bus to be detected under each operation quality evaluation index in a preset time period; inputting a plurality of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model, and determining the grade of the operation quality of each route to be detected; the airport bus operation quality evaluation model is obtained by training and iteratively processing an initial neural network model by obtaining a plurality of sample operation service data of each sample detection line and a sample operation quality grade corresponding to each sample operation service data; the sample operation quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing and natural breakpoint processing on the sample operation service data of the sample detection line.
Therefore, the specific situation of the operation quality of the airport bus can be visually displayed, the difference of the operation quality of the airport bus among routes can be reflected, and the accuracy of the estimation of the operation quality of the airport bus can be improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of a method for determining the operation quality of an airport bus according to an embodiment of the present application;
fig. 2 is a two-dimensional schematic diagram of a projection toposis method according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram illustrating an airport bus operation quality evaluation model according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an apparatus for determining the operation quality of an airport bus according to an embodiment of the present application;
fig. 5 is a second schematic structural diagram of an apparatus for determining the operation quality of an airport bus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and that steps without logical context may be performed in reverse order or concurrently. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.
In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
To enable one skilled in the art to use the present disclosure in connection with a particular application scenario "determining airport bus operation quality," the following embodiments are presented to enable one skilled in the art to apply the general principles defined herein to other embodiments and application scenarios without departing from the spirit and scope of the present application.
The following method, apparatus, electronic device or computer-readable storage medium in the embodiments of the present application may be applied to any scenario where determination of operation quality of an airport bus is required, and the embodiments of the present application do not limit specific application scenarios.
First, an application scenario to which the present application is applicable will be described. The method and the device can be applied to the technical field of data processing.
Research shows that at the present stage, the operation quality of the airport bus is lack of fine description, and the predicament of lack of evaluation standards also exists, so that the problems of poor flexibility, unobvious grading characteristics of evaluation results and the like are caused. Therefore, how to quickly and accurately determine the operation quality of the airport bus becomes one of the important problems to be solved urgently in the ground traffic of the current airport.
In terms of processing the operation quality of the airport bus, a comprehensive evaluation method is generally used, and the comprehensive evaluation method can be mainly classified into a qualitative evaluation method and a quantitative evaluation method. Qualitative evaluation methods such as an expert conference method, a Delphi method and the like can make full use of expert experience knowledge to directly make qualitative judgment on an evaluation object, and have the defect of strong subjectivity. Quantitative evaluation methods such as principal component analysis and artificial neural network analysis, which comprehensively analyze an object to be evaluated using data around the characteristics of the object to be evaluated, cannot accurately determine the operation quality of an airport bus.
Based on this, the embodiment of the application provides a method for determining the operation quality of an airport bus, which can quickly and accurately determine the grade of the operation quality when a plurality of operation service data are input through training an evaluation model of the operation quality of the airport bus, so that the specific situation of the operation quality of the airport bus can be visually shown according to the grade of the operation quality, and the accuracy of the estimation of the operation quality of the airport bus can be improved.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for determining an operation quality of an airport bus according to an embodiment of the present disclosure. As shown in fig. 1, a determination method provided in an embodiment of the present application includes:
s101: the method comprises the steps of obtaining operation service data of each to-be-detected route in a plurality of to-be-detected routes of the airport bus to be detected under each operation quality evaluation index in a preset time period.
In the step, each operation service data of each to-be-detected route of a plurality of to-be-detected routes of the airport bus to be detected under the operation quality evaluation index is acquired within a preset time period.
The preset time period is used to represent the detection period, and here, the preset time period may be set to 30 days, 60 days, or other time periods.
The operation quality embodies that the operation situation of the airport bus is sensed and analyzed, and the operation quality of the airport bus is mastered, so that the service level of the airport bus is improved.
Here, the operation quality evaluation index includes: passenger experience evaluation indexes and bus running evaluation indexes; the passenger experience evaluation index is used for representing the receptivity of the bus passengers under the line to be detected; the bus operation evaluation index is used for representing the operation condition of the bus under the line to be detected.
The service time of the whole day is determined by the time span of the service provided under the condition that the route to be detected is normally operated; the waiting time of the passengers is determined by the average waiting time of the passengers of the bus in the route to be detected; the travel time ratio of the passengers is determined by the average ratio of the in-vehicle time of the passengers under the route to be detected to the whole travel time; the ratio of the number of the passengers to the number of the passengers at the destination station is determined according to the ratio of the number of the passengers to the total number of the passengers on the route to be detected; the cash ratio is determined by the proportion of the number of passengers paid by cash to the total number of passengers under the route to be detected; the bus seating rate is determined by the ratio of the bus passenger carrying total amount to the bus total capacity in the route to be detected; the passenger flow sharing rate is determined by the ratio of the passenger flow to the total passenger flow in the route to be detected; the vehicle operation number difference is determined by the variance between the operation times of the buses under the route to be detected; the single line income is determined by the single day income (yuan) under the route to be detected; the departure interval is determined by the average interval (min) of departure time under the route to be detected; the daily average passenger capacity of a single vehicle is determined by the average number of service persons per day of each vehicle in the route to be detected.
Here, the operation service data is data information under an operation quality evaluation index, and for example, the service time of the whole day is an operation quality evaluation index, and the operation service data is data information 12h under the service time of the whole day.
Here, the relationship feasible formalization of the operation service data and the operation evaluation data is represented as:
wherein y represents airport bus operation evaluation data of a single route, X represents an evaluation index set of the single route,
；
a weight representing each of the running service data,
；Nin order to provide a method for normalizing indexes,
the evaluation method was used.
Here, the operation quality evaluation index is calculated specifically as follows: ("+" and "-" represent benefit-type and cost-type indicators, respectively).
1) Service time + all day means the time span (min) of the service provided under the normal operation condition of the route, reflecting the transfer reliability:
wherein,
the departure time of the last bus;
the departure time of the first bus is.
2) Passenger waiting time-, indicates the bus passenger average waiting time (min) of the route, and reflects the convenience of transfer:
wherein,
the time of ticket purchase for the ith passenger,
for the time of ticket checking of the ith passenger,Nthe total number of passengers in the route (the same applies below).
3) The travel time ratio + of the passengers refers to the average ratio of the in-vehicle time of the passengers on the route to the overall travel time, and reflects the convenience of transfer:
wherein,
is as followsThe time (min) is consumed in the i passenger cars,
the time (min) is consumed for the ith passenger to travel integrally.
4) And the terminal passenger proportion + refers to the proportion of the number of passengers to the total number of passengers in the route to the terminal station, and reflects the reasonability of the station setting:
wherein,
the number of passengers (people) for the route to the terminal.
5) Cash ratio + indicates the ratio of the number of passengers paid by cash to the total number of passengers for the route, and reflects the degree of informatization:
wherein,
the number of passengers (people) who use cash payment for the route.
6) The bus seating rate + is the ratio of the bus total passenger carrying capacity to the bus total capacity in the route, and reflects the utilization condition of bus transport capacity:
wherein,
the total number of passengers (people) for the bus for the route,
total bus capacity (human) for this route.
7) The passenger flow sharing rate + refers to the ratio of the passenger flow of the route to the total passenger flow, and reflects the bus shunting capacity:
wherein,
for the route passenger flow (people/day),
is the bus total passenger flow (people/day).
8) The difference value-of the running times of the vehicles refers to the variance between the running times of each bus in the route, and reflects the running intensity of the buses:
wherein,
the set of number of times each bus is run for the route.
9) The income + of a single line refers to the income (yuan) of the line per day, and reflects the situation of bus earnings:
wherein,
the fare of the ith passenger of the route on a single day, and n is the total number of passengers in the route.
10) Departure interval-, meaning the average interval (min) of departure time for the route, reflecting the bus runtime efficiency:
wherein,
the departure interval between every two vehicles on the route,Kthe total number of shifts (car numbers) is dispatched for the route.
11) The daily average passenger capacity-of a single vehicle means the average number of service people per day of each vehicle in the route, and reflects the operation intensity of the bus:
wherein,
the number of buses for the route.
S102: and inputting a plurality of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model to determine the grade of the operation quality of each route to be detected.
In the step, the obtained multiple operation service data of each route to be detected are simultaneously input into an airport bus operation quality evaluation model to carry out grade determination on the multiple operation service data of each route to be detected, and the grade of the operation quality of each route to be detected is determined.
The airport bus operation quality evaluation model is obtained by training and iteratively processing an initial neural network model through obtaining a plurality of sample operation service data of various sample detection lines and a sample operation quality grade corresponding to each sample operation service data.
The airport bus running quality evaluation model is obtained by deep learning and training through an initial neural network and is used for rapidly and accurately outputting the grade of the running quality of each route to be detected. And then, taking the grading evaluation result data corresponding to the operation service data as learning data, training an initial neural network model, and obtaining a final airport bus operation quality evaluation model.
A projection TOPSIS method suitable for grading is provided based on the traditional TOPSIS method, a projection TOPSIS evaluation model is constructed by combining a natural breakpoint method, and scientific and reasonable grading division and evaluation analysis are carried out on the running quality of the airport bus. The neural network has excellent learning ability, and the model solidified by the neural network has good flexibility, so that the model obtained by training by constructing a neural network learning projection TOPSIS evaluation model evaluation experience knowledge and taking index data as input and grade data as output is the final airport bus operation quality evaluation model.
The sample running quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing and natural breakpoint processing on the sample running service data of the sample detection line.
The sample running quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing on the sample running service data of the sample detection line, determining each sample running evaluation data corresponding to each sample running service data, performing natural breakpoint processing on each sample running evaluation data to determine each running quality value range, and performing grade division on each sample running evaluation data and each running quality range value.
Further, the grade of the sample running quality of each sample detection route is determined by the following steps:
1): and performing projection comprehensive evaluation processing on the multiple sample operation service data of each sample detection route, and determining the sample operation evaluation data of each sample detection route.
The method comprises the steps of carrying out projection comprehensive evaluation processing (TOPSIS calculation) on a plurality of acquired sample operation service data of each sample detection route, and determining sample operation evaluation data of each sample to-be-detected route.
Further, the performing projection comprehensive evaluation processing on the multiple sample operation service data of each sample detection route to determine the sample operation evaluation data of each sample detection route includes:
a: and carrying out standardization processing on the multiple sample operation service data of each sample detection route, and determining multiple reference operation service data of each sample detection route.
Here, a plurality of sample running service data of each sample test route is subjected to normalization processing (normalization processing), and a plurality of reference running service data of each sample test route is determined.
The standardization processing (normalization processing) is to normalize the plurality of operation service data in different dimensions to the same dimension, and further determine the operation evaluation data by using the reference operation service data in the same dimension.
The reference operation service data is obtained by standardizing the sample operation service data.
Further, the normalizing the plurality of sample operation service data of each sample detection route to determine a plurality of reference operation service data of each sample detection route includes:
a: and determining the mean value of each sample operation service data of each sample detection line based on the total number of the sample detection lines and each sample operation service data of each sample detection line.
Here, the mean value of each sample running service data is determined by the following formula:
wherein,
in order to detect the total number of lines for a sample,
the mean of the service data is run for the sample,
service data is run for the jth sample of the ith sample route.
b: and determining the reference operation service data of each sample detection line based on the attribute of each sample operation service data, the average value of each sample operation service data and the number of the sample operation service data in the sample detection line.
Here, if the sample operation quality evaluation index is a benefit type attribute, then:
here, if the sample run quality evaluation index is a cost-type attribute:
wherein n is the number of sample running service data,
the mean of the service data is run for the sample,
running service data for the jth sample of the ith sample route,
service data is run for reference.
Wherein by
The weights of the sample operation service data are calculated and weighted,
the weights of the service data are run for the samples.
B: and determining a reference value of each reference operation service data of each sample detection route based on the plurality of reference operation service data of each sample detection route.
For example, if the reference operating service data of the cash ratio is 0.7, the optimal value of the cash ratio is determined to be 1 by the following formula, and the optimal value 1 is the reference value corresponding to the reference operating service data of 0.7.
Here, a reference value of each reference run service data is determined by the following formula.
Positive reference value:
negative reference value:
wherein,
is benefit type operation service data in the sample operation service data,
is the cost in running the service data on the sampleThe type(s) run service data,
is a positive reference value for the number of bits,
is a negative reference value.
Here, the positive reference value is determined by the above formula to be
Negative reference value of
。
C: and determining a connecting line on a multidimensional space based on the reference value of each reference operation service data of each sample to-be-detected route, and determining sample operation evaluation data of the sample detection route according to the distance from the vector set of the reference operation service data of the sample detection route to the connecting line on the multidimensional space.
Here, a connection line on the multidimensional space is determined by using the reference value of each reference operation service data of the sample detection route, and the sample operation evaluation data of the sample detection route is determined according to the shortest distance from the vector set of the plurality of reference operation service data of the sample detection route to the connection line on the multidimensional space.
Here, the shortest distance from the coordinate information composed of the vector set of the reference run service data to the connection line on the multidimensional space by the reference value of each reference run service data is determined as the sample run evaluation data of the sample detection route.
The sample operation evaluation data is used for representing the operation situation of the airport bus to conduct perception and analysis, and the operation evaluation data of the airport bus is grasped to be beneficial to improving the service level of the airport bus, but the operation evaluation data of the airport bus is only used singly, so that the airport bus service cannot be directly adjusted, and therefore the operation evaluation data needs to be subjected to hierarchical transformation, and the airport bus service can be adjusted.
Here, in the multidimensional space, the sample operation evaluation data is determined by the following formula:
wherein,
the evaluation data was run for the sample,
the jth reference running service data of the ith route is obtained, and n is the number of the sample running service data.
Further, please refer to fig. 2, fig. 2 is a two-dimensional schematic diagram of a toposis projection method according to an embodiment of the present disclosure. As shown in fig. 2, taking the number of the sample operation quality evaluation indexes of the sample detection route as two as an example, the number of the sample operation quality service data is 2, so that the point B coordinate is set as the reference operation service data obtained by normalizing the sample operation service data of the sample detection route, and the reference values of the reference operation service data are determined to be 1 and-1, and then the line connecting (1, 1) and (-1, -1) is determined on the two-dimensional space to determine the line connecting (1, 1) and (-1, -1)
And setting the coordinate value of a point C of which the point B is projected on the Z axis as the Z axis, and taking the coordinate value as sample operation evaluation data of the sample detection line. The coordinate value is a point
To
The calculation formula is as follows:
wherein when
When the sign is negative, when
The sign is positive.
2): and carrying out natural breakpoint processing on the sample running evaluation data of each sample detection route, and determining the sample running quality value range of each sample detection route.
In the step, natural breakpoint processing is performed on the sample running evaluation data of each sample detection route, so that a plurality of sample running quality value ranges are determined, and preparation is made for converting the sample running evaluation data into graded sample running evaluation data.
Here, the sample run quality value ranges are a plurality of interval ranges determined by performing natural breakpoint processing on a plurality of sample run evaluation data.
Further, the natural breakpoint processing is performed on the multiple sample running evaluation data of each sample detection route, and the determining of the sample running quality value range of each sample detection route includes:
And performing natural breakpoint processing on the multiple sample operation evaluation data so as to determine the breakpoint data of the multiple sample operation evaluation data.
For example, if the sample operation evaluation data of 5 sample detection routes are 0.0520, 0.1582, 0.0635, 0.1685, 0.04852, and 0.0365, respectively, natural breakpoint processing is performed based on the sample operation evaluation data of the 5 sample detection routes, and the obtained multiple sample operation evaluation breakpoint data are 0.0420, 0.1682, 0.0535, 0.1685, 0.03342, and 0.0385, respectively.
Here, the multiple sample run evaluation breakpoint data is sorted in descending order, e.g., 0.1685, 0.1682, 0.0535, 0.0420, 0.0385, and 0.03342. After sorting in descending order, the running quality values of the plurality of samples are determined to be [0.1685, 0.1682 ], [0.1682, 0.0535 ], [0.0535, 0.0420 ], [0.0420, 0.0385) and [0.0385, 0.03842 ].
3): and carrying out grade division on the sample running evaluation data and the sample running quality range value of each sample detection route, and determining the grade of the sample running quality of each sample detection route.
In the step, the operation evaluation data of each sample detection route and the plurality of operation sample operation quality range values are subjected to grading conversion, so that the grade of the sample operation quality of each sample detection route is determined.
Here, the ranking is converted into ranking the numerical sample operation evaluation data, and converted into a ranked quality result.
Here, the grade of the running quality of the sample is used for detecting whether the running quality of the route is good, bad, and the like, so as to conveniently adjust the service strategy of the airport bus.
Further, please refer to fig. 3, wherein fig. 3 is a schematic view illustrating a model for evaluating the operation quality of the airport bus according to an embodiment of the present application. As shown in fig. 3, a plurality of sample operation service data of a sample detection route are obtained, projection TOPSIS calculation is performed on the plurality of sample operation service data to determine sample operation evaluation data of each sample detection route, then natural breakpoint processing is performed on the sample operation evaluation data of each sample detection route to obtain a plurality of sample operation quality range values, then grade division processing is performed on the sample operation quality range values and the sample operation evaluation data to obtain grades of sample operation quality results, and then the graded evaluation result data corresponding to the sample operation service data is used as learning data to train an initial neural network to obtain a final airport bus operation quality evaluation model. Here, the projection comprehensive evaluation process and the natural breakpoint process may together form a projection evaluation network layer, and the projection evaluation network layer may be formally described as follows:
wherein,
the network layer is evaluated on behalf of the projections,
represents a projection of the TOPSIS method,
in order to represent a natural breakpoint method,
running a collection of service data for a plurality of route airport bus samples,
the evaluation data was run for multiple route airport bus samples.
Further, the step of performing grade division on the sample operation evaluation data and the sample operation quality range value of each sample detection route to determine the grade of the sample operation quality of each sample detection route includes:
(1): and determining a grade label of each sample operation quality value range based on the sample operation evaluation data of each sample detection route and the sample operation quality range value input.
Here, the sample running evaluation data and the sample running quality range value of each sample detection route are subjected to classification processing, and a grade label of each sample running quality range value is determined. Such as, for example,
，
the expression is good, and the expression is good,
the representative is that it is preferable that,
the representation is in general terms and represents,
the representation is poor in that,
representing a difference.
Here, the plurality of sample run quality assessment data is sorted in descending order, e.g., 0.1685, 0.1682, 0.0535, 0.0420, 0.0385, and 0.03342. After sorting in descending order, the running quality values of the plurality of samples are determined to be [0.1685, 0.1682 ], [0.1682, 0.0535 ], [0.0535, 0.0420 ], [0.0420, 0.0385) and [0.0385, 0.03842 ]. And sequentially determining the grade labels corresponding to the five sample running quality value ranges as best, good, common, poor and bad.
(2): and matching the sample operation evaluation data of the line to be detected with a plurality of sample operation quality value ranges according to the sample operation evaluation data of each sample detection line, and if the sample operation evaluation data of the line to be detected is within the interval range of any one of the sample operation quality value ranges, giving the sample operation evaluation data of the sample detection line with a grade label corresponding to the sample operation quality value range, and determining the grade of the sample operation quality of the sample detection line.
Here, for example, the obtained sample operation evaluation data 0.0520, 0.1582, 0.0635, 0.1685, 0.04852 and 0.0365 of the to-be-sample measurement route are matched with a plurality of sample operation quality value ranges [0.1685, 0.1682 ], [0.1682, 0.0535), [0.0535, 0.0420), [0.0420, 0.0385) and [0.0385, 0.03342), and the operation quality value range corresponding to the sample operation evaluation data is detected, for example, if the value range corresponding to the sample operation evaluation data of 0.0520 is [0.1682, 0.0535 ], the grade of the sample operation evaluation data of 0.0520 is good, and so on, which is not repeated herein.
Here, it is further included that, if the grade of the operation quality of the route to be detected is poor, the service policy of the route to be detected needs to be adjusted.
In a specific embodiment, eighty days of airport bus related data from 26 days 2-5-16 days 5-1 year 2021 of a certain airport are obtained, nine available routes are selected from fourteen urban line data of the airport and used as routes to be detected, and the routes are named as route 1-route 9. In actual evaluation, the 80 days are taken as a whole, the 80 days are taken as a unit, and the running service data of the nine routes to be detected in 80 days are input into the airport bus running quality evaluation model, so that the running quality grades of the nine routes to be detected are determined.
The method for determining the operation quality of the airport bus provided by the embodiment of the application comprises the following steps: acquiring operation service data of each to-be-detected route in a plurality of to-be-detected routes of the airport bus to be detected under each operation quality evaluation index in a preset time period; inputting a plurality of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model, and determining the grade of the operation quality of each route to be detected; the airport bus operation quality evaluation model is obtained by training and iteratively processing an initial neural network model by obtaining a plurality of sample operation service data of each sample detection line and a sample operation quality grade corresponding to each sample operation service data; the sample running quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing and natural breakpoint processing on the sample running service data of the sample detection line. Therefore, the specific situation of the operation quality of the airport bus can be visually displayed, the difference of the operation quality of the airport bus among routes can be reflected, and the accuracy of the estimation of the operation quality of the airport bus can be improved.
Therefore, the specific situation of the operation quality of the airport bus can be visually displayed, the difference of the operation quality of the airport bus among routes can be reflected, and the accuracy of the estimation of the operation quality of the airport bus can be improved.
Referring to fig. 4 and 5, fig. 4 is a first schematic structural diagram of an apparatus for determining an operation quality of an airport bus according to an embodiment of the present application, and fig. 5 is a second schematic structural diagram of an apparatus for determining an operation quality of an airport bus according to an embodiment of the present application. As shown in fig. 4, the determining means 400 includes:
the obtaining module 410 is configured to obtain, within a preset time period, operation service data of each of the multiple routes to be detected of the airport bus to be detected under each operation quality evaluation index;
the determining module 420 is configured to input the multiple pieces of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model, and determine a level of operation quality of each route to be detected; the airport bus operation quality evaluation model is obtained by training an initial neural network model by acquiring a plurality of sample operation service data of each sample detection line and a sample operation quality grade corresponding to each sample operation service data; the sample running quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing and natural breakpoint processing on the sample running service data of the sample detection line.
Further, the determining apparatus 400 further includes a model training module 430, which is further configured to determine the grade of the sample running quality of each sample detection route by:
performing projection comprehensive evaluation processing on the multiple sample operation service data of each sample detection line, and determining sample operation evaluation data of each sample detection line;
carrying out natural breakpoint processing on a plurality of sample running evaluation data of each sample detection route, and determining the sample running quality value range of each sample detection route;
and carrying out grade division on the sample running evaluation data and the sample running quality range value of each sample detection route, and determining the grade of the sample running quality of each sample detection route.
Further, when the model training module 430 is configured to perform projection comprehensive evaluation processing on the multiple sample operation service data of each sample detection route, and determine the sample operation evaluation data of each sample detection route, the model training module 430 is specifically configured to:
carrying out standardization processing on the multiple sample operation service data of each sample detection route to determine multiple reference operation service data of each sample detection route;
determining a reference value of each reference operation service data of each sample detection route based on the plurality of reference operation service data of each sample detection route;
and determining a connecting line on a multidimensional space based on the reference value of each reference operation service data of each sample detection route aiming at the reference value of each reference operation service data of each sample detection route, and determining sample operation evaluation data of the sample to-be-detected route according to the distance from the vector set of the plurality of reference operation service data of the sample detection route to the connecting line on the multidimensional space.
Further, when the model training module 430 is configured to perform the normalization processing on the multiple sample operation service data of each sample detection route, and determine multiple reference operation service data of each sample detection route, the model training module 430 is specifically configured to:
determining the mean value of each sample operation service data of each sample detection line based on the total number of the sample detection lines and each sample operation service data of each sample detection line;
and determining the reference operation service data of each sample detection line based on the attribute of each sample operation service data, the average value of each sample operation service data and the number of the sample operation service data in the sample detection line.
Further, when the model training module 430 is configured to perform natural breakpoint processing on the multiple sample operation evaluation data of each sample detection route and determine the sample operation quality value range of each sample detection route, the model training module 430 is specifically configured to:
performing natural breakpoint processing on the plurality of sample operation evaluation data to determine the plurality of sample operation evaluation breakpoint data;
and sequencing the plurality of sample running evaluation breakpoint data in a descending manner, and determining the range of the sample running quality value.
Further, when the model training module 430 is configured to perform grade division processing on the sample operation evaluation data and the sample operation quality range value of each sample detection route, and determine the grade of the sample operation quality of each sample detection route, the model training module 430 is specifically configured to:
determining a grade label of each sample operation quality value range based on the sample operation evaluation data of each sample detection route and the sample operation quality range value;
and matching the sample operation evaluation data of each sample detection line with a plurality of sample operation quality value ranges according to the operation evaluation data of each sample detection line, and if the sample operation evaluation data of the sample detection line is within the interval range of any one of the sample operation quality value ranges, giving the sample operation evaluation data of the sample detection line a grade label corresponding to the sample operation quality value range, and determining the grade of the operation quality of the sample detection line.
The device for determining the operation quality of the airport bus provided by the embodiment of the application comprises: the acquisition module is used for acquiring the operation service data of each to-be-detected route in the plurality of to-be-detected routes of the airport bus to be detected under each operation quality evaluation index in a preset time period; the determining module is used for inputting a plurality of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model and determining the grade of the operation quality of each route to be detected; the airport bus operation quality evaluation model is obtained by training an initial neural network model by acquiring a plurality of sample operation service data of each sample detection line and a sample operation quality grade corresponding to each sample operation service data; the sample operation quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing and natural breakpoint processing on the sample operation service data of the sample detection line.
Therefore, through training of the airport bus running quality evaluation model, when a plurality of running service data are input, the grade of the running quality can be rapidly and accurately determined, the specific situation of the running quality of the airport bus can be visually shown according to the grade of the running quality, and the accuracy of the airport bus running quality evaluation can be improved.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 6, the electronic device 600 includes a processor 610, a memory 620, and a bus 630.
The memory 620 stores machine-readable instructions executable by the processor 610, when the electronic device 600 runs, the processor 610 communicates with the memory 620 through the bus 630, and when the machine-readable instructions are executed by the processor 610, the steps of the method for determining the operation quality of the airport bus in the method embodiment shown in fig. 1 may be executed.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the step of the method for determining the operation quality of an airport bus in the method embodiment shown in fig. 1 may be executed.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (6)
1. A method for determining the operating quality of an airport bus, comprising:
acquiring operation service data of each to-be-detected route in a plurality of to-be-detected routes of the airport bus to be detected under each operation quality evaluation index in a preset time period; the running quality evaluation indexes comprise full-day service time, passenger waiting time, passenger travel time occupation ratio, final passenger occupation ratio, cash ratio, bus passenger seat ratio, passenger flow sharing rate, vehicle operation frequency difference, single line income, departure interval and single-vehicle daily average passenger capacity;
inputting a plurality of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model, and determining the grade of the operation quality of each route to be detected;
the airport bus operation quality evaluation model is obtained by training an initial neural network model by acquiring a plurality of sample operation service data of each sample detection line and a sample operation quality grade corresponding to each sample operation service data;
the sample running quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing and natural breakpoint dividing processing on the sample running service data of the sample detection line;
determining a grade of sample run quality for each sample testing route by:
performing projection comprehensive evaluation processing on the multiple sample operation service data of each sample detection line, and determining sample operation evaluation data of each sample detection line;
carrying out natural breakpoint processing on a plurality of sample running evaluation data of each sample detection route, and determining the sample running quality value range of each sample detection route;
carrying out grade division on the sample running evaluation data and the sample running quality range value of each sample detection route to determine the grade of the sample running quality of each sample detection route;
the method for performing projection comprehensive evaluation processing on the multiple sample operation service data of each sample detection line and determining the sample operation evaluation data of each sample detection line comprises the following steps:
carrying out standardization processing on the multiple sample operation service data of each sample detection route to determine multiple reference operation service data of each sample detection route;
determining a reference value of each reference operation service data of each sample detection route based on the plurality of reference operation service data of each sample detection route;
determining a connection line on a multi-dimensional space based on a reference value of each reference operation service data of each sample detection route aiming at a reference value of each reference operation service data of each sample detection route, and determining sample operation evaluation data of each sample detection route according to the shortest distance from a vector set of a plurality of reference operation service data of each sample detection route to the connection line on the multi-dimensional space;
the standardizing the multiple sample operation service data of each sample detection route to determine multiple reference operation service data of each sample detection route includes:
determining the mean value of each sample operation service data of each sample detection line based on the total number of the sample detection lines and each sample operation service data of each sample detection line;
and determining the reference operation service data of each sample detection line based on the attribute of each sample operation service data, the average value of each sample operation service data and the number of the sample operation service data in the sample detection line.
2. The determination method according to claim 1, wherein the natural breakpoint processing is performed on the plurality of sample operation evaluation data of each sample detection route, and the determining of the sample operation quality value range of each sample detection route includes:
performing natural breakpoint processing on the plurality of sample operation evaluation data to determine the plurality of sample operation evaluation breakpoint data;
and sequencing the plurality of sample running evaluation breakpoint data in a descending manner, and determining the range of the sample running quality value.
3. The determination method according to claim 1, wherein the step of performing a ranking process on the sample running evaluation data and the sample running quality range value of each sample detection route to determine the rank of the sample running quality of each sample detection route comprises:
determining a grade label of each sample operation quality value range based on the sample operation evaluation data of each sample detection route and the sample operation quality range value;
and matching the sample operation evaluation data of each sample detection line with a plurality of sample operation quality value ranges according to the sample operation evaluation data of each sample detection line, and if the sample operation evaluation data of the sample detection line is within the interval range of any one of the sample operation quality value ranges, giving the sample operation evaluation data of the sample detection line a grade label corresponding to the sample operation quality value range, and determining the grade of the sample operation quality of the sample detection line.
4. An airport bus operation quality determination apparatus, comprising:
the acquisition module is used for acquiring the operation service data of each to-be-detected route in the plurality of to-be-detected routes of the airport bus to be detected under each operation quality evaluation index in a preset time period; the running quality evaluation indexes comprise full-day service time, passenger waiting time, passenger travel time occupation ratio, final passenger occupation ratio, cash ratio, bus passenger seat ratio, passenger flow sharing rate, vehicle operation frequency difference, single line income, departure interval and single-vehicle daily average passenger capacity;
the determining module is used for inputting a plurality of operation service data of each route to be detected into a pre-trained airport bus operation quality evaluation model and determining the grade of the operation quality of each route to be detected; the method comprises the steps that an airport bus operation quality evaluation model is obtained by training an initial neural network model through obtaining a plurality of sample operation service data of various sample detection lines and a sample operation quality grade corresponding to each sample operation service data; the sample running quality grade of each sample detection line is obtained by performing projection comprehensive evaluation processing and natural breakpoint processing on the sample running service data of the sample detection line;
the determining device further comprises a model training module, and the model training module is further used for determining the grade of the sample running quality of each sample detection route through the following steps:
performing projection comprehensive evaluation processing on the multiple sample operation service data of each sample detection line, and determining sample operation evaluation data of each sample detection line;
carrying out natural breakpoint processing on a plurality of sample running evaluation data of each sample detection route, and determining the sample running quality value range of each sample detection route;
carrying out grade division on the sample running evaluation data and the sample running quality range value of each sample detection route to determine the grade of the sample running quality of each sample detection route;
the model training module is configured to perform projection comprehensive evaluation processing on the multiple sample operation service data of each sample detection route, and when the sample operation evaluation data of each sample detection route is determined, the model training module is specifically configured to:
carrying out standardization processing on the multiple sample operation service data of each sample detection route to determine multiple reference operation service data of each sample detection route;
determining a reference value of each reference operation service data of each sample detection route based on the plurality of reference operation service data of each sample detection route;
determining a connecting line on a multidimensional space based on the reference value of each reference operation service data of each sample detection route aiming at the reference value of each reference operation service data of each sample detection route, and determining sample operation evaluation data of the sample to-be-detected route according to the shortest distance from the vector set of a plurality of reference operation service data of the sample detection route to the connecting line on the multidimensional space;
the model training module is specifically configured to, when the model training module is used to normalize the multiple sample operation service data of each sample detection route and determine the multiple reference operation service data of each sample detection route:
determining the mean value of each sample operation service data of each sample detection line based on the total number of the sample detection lines and each sample operation service data of each sample detection line;
and determining the reference operation service data of each sample detection line based on the attribute of each sample operation service data, the average value of each sample operation service data and the number of the sample operation service data in the sample detection line.
5. An electronic device, comprising: processor, memory and bus, said memory storing machine-readable instructions executable by said processor, said processor and said memory communicating over said bus when the electronic device is operating, said machine-readable instructions being executed by said processor to perform the steps of a method for determining the quality of operation of an airport bus as claimed in any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that it has stored thereon a computer program which, when being executed by a processor, carries out the steps of a method for determining the quality of an airport bus operation as claimed in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210321381.8A CN114418467B (en) | 2022-03-30 | 2022-03-30 | Method and device for determining operation quality of airport bus and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210321381.8A CN114418467B (en) | 2022-03-30 | 2022-03-30 | Method and device for determining operation quality of airport bus and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114418467A CN114418467A (en) | 2022-04-29 |
| CN114418467B true CN114418467B (en) | 2022-08-16 |
Family
ID=81263239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210321381.8A Active CN114418467B (en) | 2022-03-30 | 2022-03-30 | Method and device for determining operation quality of airport bus and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114418467B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103745089A (en) * | 2013-12-20 | 2014-04-23 | 北京工业大学 | Multi-dimensional public transport operation index evaluation method |
| CN106779408A (en) * | 2016-12-13 | 2017-05-31 | 深圳先进技术研究院 | The appraisal procedure and device of public transit system service quality |
| CN107798411A (en) * | 2016-09-07 | 2018-03-13 | 北京嘀嘀无限科技发展有限公司 | The evaluation process method and server of a kind of regular bus route |
| CN109919387A (en) * | 2019-03-15 | 2019-06-21 | 福建工程学院 | A kind of Metro Passenger crowding prediction technique using resampling recurrent neural network |
| CN109934482A (en) * | 2019-03-07 | 2019-06-25 | 中国民用航空总局第二研究所 | A kind of terminal fining operation assessment system and method based on big data |
| CN110415513A (en) * | 2018-04-28 | 2019-11-05 | 深圳先进技术研究院 | A kind of public transportation lane Service Index dissemination method, system and electronic equipment |
| CN111160731A (en) * | 2019-12-13 | 2020-05-15 | 东南大学 | Air-rail joint service comprehensive evaluation method based on passenger perception |
| CN112149919A (en) * | 2020-10-15 | 2020-12-29 | 武汉译码当先科技有限公司 | Bus operation line evaluation method, device, equipment and storage medium |
| CN112232652A (en) * | 2020-10-12 | 2021-01-15 | 中国民航信息网络股份有限公司 | Passenger risk level classification method and device, electronic equipment and storage medium |
| CN112561730A (en) * | 2020-12-02 | 2021-03-26 | 国网浙江省电力有限公司营销服务中心 | Power supply service analysis method based on double-layer clustering and fuzzy comprehensive evaluation |
| CN112801460A (en) * | 2021-01-06 | 2021-05-14 | 武汉大学 | Groundwater pollution monitoring network optimization method based on two-step TOPSIS method |
| CN113379318A (en) * | 2021-07-02 | 2021-09-10 | 广州交信投科技股份有限公司 | Method and device for evaluating operation service quality of public transport system and computer equipment |
| CN114078322A (en) * | 2020-08-18 | 2022-02-22 | 上海市交通发展研究中心 | Bus running state evaluation method, device, equipment and storage medium |
-
2022
- 2022-03-30 CN CN202210321381.8A patent/CN114418467B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103745089A (en) * | 2013-12-20 | 2014-04-23 | 北京工业大学 | Multi-dimensional public transport operation index evaluation method |
| CN107798411A (en) * | 2016-09-07 | 2018-03-13 | 北京嘀嘀无限科技发展有限公司 | The evaluation process method and server of a kind of regular bus route |
| CN106779408A (en) * | 2016-12-13 | 2017-05-31 | 深圳先进技术研究院 | The appraisal procedure and device of public transit system service quality |
| CN110415513A (en) * | 2018-04-28 | 2019-11-05 | 深圳先进技术研究院 | A kind of public transportation lane Service Index dissemination method, system and electronic equipment |
| CN109934482A (en) * | 2019-03-07 | 2019-06-25 | 中国民用航空总局第二研究所 | A kind of terminal fining operation assessment system and method based on big data |
| CN109919387A (en) * | 2019-03-15 | 2019-06-21 | 福建工程学院 | A kind of Metro Passenger crowding prediction technique using resampling recurrent neural network |
| CN111160731A (en) * | 2019-12-13 | 2020-05-15 | 东南大学 | Air-rail joint service comprehensive evaluation method based on passenger perception |
| CN114078322A (en) * | 2020-08-18 | 2022-02-22 | 上海市交通发展研究中心 | Bus running state evaluation method, device, equipment and storage medium |
| CN112232652A (en) * | 2020-10-12 | 2021-01-15 | 中国民航信息网络股份有限公司 | Passenger risk level classification method and device, electronic equipment and storage medium |
| CN112149919A (en) * | 2020-10-15 | 2020-12-29 | 武汉译码当先科技有限公司 | Bus operation line evaluation method, device, equipment and storage medium |
| CN112561730A (en) * | 2020-12-02 | 2021-03-26 | 国网浙江省电力有限公司营销服务中心 | Power supply service analysis method based on double-layer clustering and fuzzy comprehensive evaluation |
| CN112801460A (en) * | 2021-01-06 | 2021-05-14 | 武汉大学 | Groundwater pollution monitoring network optimization method based on two-step TOPSIS method |
| CN113379318A (en) * | 2021-07-02 | 2021-09-10 | 广州交信投科技股份有限公司 | Method and device for evaluating operation service quality of public transport system and computer equipment |
Non-Patent Citations (5)
| Title |
|---|
| 基于TOPSIS和BP神经网络的高标准农田综合识别;吕雅慧等;《农业机械学报》;20180325;第196-204页 * |
| 基于结构熵-改进TOPSIS法的公交旅游服务能力评价;于世军等;《交通运输研究》;20211025;第27-34页 * |
| 机场到港旅客换乘时间效率评价指标优选;罗谦等;《北京航空航天大学学报》;20210630;第1-9页 * |
| 空港枢纽机场巴士运行与服务评价体系研究;钟敏等;《交通工程》;20211215;第23-30页 * |
| 面向公交全出行链的短时服务评价模型研究;刘冬梅等;《公路交通科技》;20180815;第123-133页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114418467A (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110634080B (en) | Abnormal electricity utilization detection method, device, equipment and computer readable storage medium | |
| CN107545422B (en) | Cashing detection method and device | |
| CN108764375B (en) | Highway goods stock transprovincially matching process and device | |
| CN111343147B (en) | Network attack detection device and method based on deep learning | |
| CN110929224A (en) | Safety index system establishing method based on bus driving safety | |
| CN109791677A (en) | System and method for carrying out Geographic Reference and scoring to vehicle data in community | |
| CN115034821A (en) | Vehicle estimation method and device, computer equipment and storage medium | |
| CN114418467B (en) | Method and device for determining operation quality of airport bus and storage medium | |
| CN112184495B (en) | Stock low-efficiency land monitoring system and analysis platform using same | |
| CN105427171A (en) | Data processing method of Internet lending platform rating | |
| CN112215451A (en) | Differentiation security check method and system based on civil aviation passenger classification | |
| Shu et al. | Characterizing occupations with data from thedictionary of occupational titles | |
| CN108256766A (en) | A kind of car insurance accounting method based on dangerous driving behavior | |
| CN113569902A (en) | Method and system for analyzing satisfaction evaluation quality of aviation enterprise based on Lekter scale | |
| CN114462700A (en) | Railway track quality evaluation method and device | |
| CN111832834B (en) | Airport pavement service performance prediction method and device and electronic equipment | |
| CN113808393A (en) | Method for eliminating influence of hybrid control object | |
| CN114416686A (en) | Vehicle equipment fingerprint CARID identification system and identification method | |
| CN113191805A (en) | Vehicle owner replacement evaluation method, system, electronic equipment and storage medium | |
| CN113064883A (en) | Method for constructing logistics wind control model, computer equipment and storage medium | |
| Kumar | Driver Usage Risk Profiling by Analyzing Vehicle Driving Behavior using Machine Learning Model Based on Vehicular Cloud Telematics Data | |
| CN110555659A (en) | method for analyzing value of fourth logistics platform to shipper | |
| CN112396342B (en) | Passenger value calculation method, device and server | |
| US11934364B2 (en) | System and method facilitating determination of automotive signal quality marker | |
| CN114782120B (en) | Internet-based intelligent analysis method for electronic invoice tax data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |