CN107633339B - Performance evaluation system and method - Google Patents
Performance evaluation system and method Download PDFInfo
- Publication number
- CN107633339B CN107633339B CN201710176941.4A CN201710176941A CN107633339B CN 107633339 B CN107633339 B CN 107633339B CN 201710176941 A CN201710176941 A CN 201710176941A CN 107633339 B CN107633339 B CN 107633339B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- driver
- event
- data analysis
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims description 21
- 238000007405 data analysis Methods 0.000 claims abstract description 120
- 238000005265 energy consumption Methods 0.000 claims abstract description 100
- 239000011159 matrix material Substances 0.000 claims description 177
- 238000004891 communication Methods 0.000 claims description 69
- 238000001514 detection method Methods 0.000 claims description 34
- 239000013598 vector Substances 0.000 claims description 33
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 230000001133 acceleration Effects 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 13
- 210000004556 brain Anatomy 0.000 claims description 8
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 4
- 230000005611 electricity Effects 0.000 claims description 3
- 239000003345 natural gas Substances 0.000 claims description 3
- 238000001816 cooling Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 18
- 238000004364 calculation method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 14
- 239000008186 active pharmaceutical agent Substances 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 8
- 239000000446 fuel Substances 0.000 description 8
- 238000012546 transfer Methods 0.000 description 7
- 206010039203 Road traffic accident Diseases 0.000 description 6
- 230000006399 behavior Effects 0.000 description 6
- 230000007812 deficiency Effects 0.000 description 4
- 239000003502 gasoline Substances 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 239000002828 fuel tank Substances 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention relates to a performance evaluation system and a performance evaluation method, which mainly receive vehicle equipment information of the vehicle equipment information from a plurality of vehicle equipment through a data analysis server device, wherein the vehicle equipment information comprises information such as energy consumption or danger factors, and then calculate the performance represented by the driving behavior of a driver through a performance evaluation algorithm, so that the performance of all the drivers can be ranked.
Description
Technical Field
The invention relates to a performance evaluation system and a method thereof, in particular to a system and a method for collecting energy consumption information or danger factors of a plurality of vehicle devices and user devices and comprehensively considering the energy consumption information or the danger factors so as to know the influence of various driving behaviors on performance.
Background
The cost of fuel oil is one of the main cost factors for the automobile freight industry, and important attention needs to be paid, and in addition, the illegal driving behavior of the driver in the freight industry not only affects the reputation of the company, but also has considerable influence on operation.
In the prior art, although there is a technology of obtaining and correcting the fuel quantity value by using the vehicle type, the fuel gauge voltage and the driving speed of the historical data, there is also a technology of detecting the battery voltage and calculating the fuel consumption of the vehicle, or a technology of diagnosing the feedback fuel quantity data of the fuel tank, etc.; however, they lack effective feedback methods, or cannot comprehensively estimate the fuel cost required by the freight industry through traffic conditions of the road network, driver differences, and other factors, and they all have their disadvantages and still need to be improved.
In the prior art, a system and a method for uploading the working conditions of employees to a cloud server through a work recording unit, a target analysis request unit and the like included in a plurality of mobile devices and then comparing the working conditions with a working target to analyze a target completion ratio are provided.
The invention collects energy consumption information and violation information through a plurality of vehicle devices and user devices, comprehensively counts various driving behaviors according to various factors and sorts the performance, and is an extremely effective performance estimation technology.
Disclosure of Invention
In order to solve the problem that the influence of various factors on the driving performance during driving cannot be comprehensively considered in the prior art, the invention provides a performance evaluation system which at least comprises a plurality of vehicle devices, a data analysis server device and a database device.
The data analysis server device can store the transmitted data in the database device, and then the data analysis server device calculates and arranges the driving performance of each vehicle device.
Wherein, each vehicle device at least comprises a driver identity identification device, a positioning module, a middleware module and a communication module;
the communication module can support wireless network transmission so as to establish communication between each piece of vehicle equipment and the data analysis server equipment.
The Positioning module supports a Positioning method such as a Global Positioning System (GPS) or wireless network signal Positioning, so that each vehicle device can obtain position information and vehicle speed information through the module.
The middleware module may support at least one of HyperText Transfer Protocol (HTTP), Message sequence Telemetry Transport (MQTT), restricted Application Protocol (CoAP), and other Transport protocols, so that each of the vehicle devices may interface with the data analysis server device through the middleware module and the communication module, so as to transmit vehicle device information to the data analysis server device.
The driver identity recognition device can read the driver identity recognition certificate to obtain the driver number.
To this end, the vehicle device information transmitted by each of the vehicle devices via the middleware module and the communication module includes a vehicle number, a vehicle model, a driver number, time information, position information, vehicle speed information, and the like.
Each of the vehicle devices may further optionally include an energy detection device, the energy detection device may detect energy consumption information of the vehicle device, the energy consumption information may be oil consumption information, electricity consumption information or natural gas information, and the energy consumption information is also included in the vehicle device information and transmitted to the data analysis server device.
Each of the vehicle devices may further optionally include an azimuth sensor for detecting azimuth information of each of the vehicle devices during driving, the azimuth information being used to determine event information such as an overspeed event, a sudden acceleration event, a sudden braking event, or a sudden turning event, and the event information being included in the vehicle device information and transmitted to the data analysis server device.
Each of the vehicle devices may further optionally include a concentration detection device, which is a wearable brain wave detection device for wearing on the head of the driver to detect the brain wave of the driver to obtain concentration information, which is used to determine event information such as absentism events, and the event information is included in the vehicle device information and transmitted to the data analysis server device.
Each of the vehicle devices may further selectively include a preceding vehicle distance detecting device and a lane deviation detecting device, the preceding vehicle distance detecting device detects preceding vehicle distance information between the vehicle devices and a preceding vehicle when the vehicle devices are traveling, the lane deviation detecting device detects deviation lane information of the vehicle devices that do not turn on a turn signal when the vehicle devices are traveling, the preceding vehicle distance information and the deviation lane information are respectively used for determining event information such as an event that a safety distance is not kept or a lane deviation event is not kept, and the event information is included in the vehicle device information and transmitted to the data analysis server device.
Each of the vehicle devices may further optionally include an on-board diagnostic system that detects vehicle state information of each of the vehicle devices in which the vehicle is installed, and a temperature sensor that detects temperature information of a refrigerator of each of the vehicle devices in which the vehicle is installed, the vehicle state information and the temperature information being included in the vehicle device information and transmitted to the data analysis server device.
So far, the vehicle equipment information transmitted by each vehicle equipment through the middleware module and the communication module includes a vehicle number, a vehicle model, a driver number, time information, position information, vehicle speed information, energy consumption information, event information, vehicle state information, temperature information and the like, wherein the event information can be an overspeed event, a rapid acceleration event, a rapid braking event, a sharp turning event, a absentism event, an event without keeping a safe distance, a lane deviation event and the like.
The database device of the present invention may store a schedule data table, where the schedule data table is used to record station information and scheduled arrival time information of the cargos received and sent by each vehicle device, and when the data analysis server device receives the vehicle device information, the data analysis server device may generate a door closing abnormal event, a temperature abnormal event, a pre-cooling insufficient event, or an arrival time abnormal event, etc. according to the vehicle state information and the temperature information in the vehicle device information, where the station information may be longitude and latitude coordinates, etc.
The data analysis server equipment of the invention receives the vehicle equipment information from each vehicle equipment, and calculates the performance of the driver during driving through a performance evaluation algorithm, and can sort the performance of the driver.
The performance evaluation algorithm executed by the data analysis server device corresponds to the performance evaluation method of the present invention, and includes at least the following steps:
1. collecting and analyzing the vehicle equipment information, reporting the vehicle equipment information to the data analysis server equipment by the vehicle equipment arranged on the vehicle, analyzing the vehicle equipment information of the vehicle equipment in a time interval by the data analysis server equipment, and storing the vehicle equipment information to a database equipment;
2. selecting at least one characteristic element, and selecting at least one characteristic element from the characteristic elements such as vehicle equipment number, vehicle model and driver from the vehicle equipment information to perform performance evaluation;
3. constructing a hierarchical structure, and setting an upper-layer and a lower-layer associated structure of each feature element according to each selected feature element;
4. executing a comparison matrix generation algorithm to generate a comparison matrix according to each characteristic element set by each level;
5. calculating characteristic values and characteristic vectors, and calculating a characteristic vector matrix of characteristic elements in each level by using numerical analysis;
6. selecting a solution, generating a plurality of solution scores according to the eigenvector matrix of each characteristic element in each level, and screening out an optimal solution.
In the performance evaluation method of the present invention, the pair-wise comparison matrix generation algorithm can be achieved by the following methods:
1. counting the values of the characteristic elements set by each hierarchical structure, and generating a pair comparison matrix according to the ratio of the values.
2. Calculating the value of each feature set by each hierarchical structure by using a distance function or a similarity function, and generating a pair comparison matrix according to the value.
3. The paired comparison matrix generation algorithm calculates the value of each characteristic element set by each hierarchical structure by using a fuzzy attribution function, and generates the paired comparison matrix according to the value.
In addition, in the solution selection step of the data analysis server device, after the score of each solution is generated, the best solution is selected according to the best score among the solutions, or the best solution is selected by applying a decision tree information profit method.
In the performance evaluation method of the invention, when each characteristic element is selected, the energy consumption information of each vehicle device can be further selected, so that the optimal solution can evaluate the energy-saving driving performance; or selecting event information of overspeed events, urgent acceleration events, urgent braking events, urgent turning events, absenteeism events, events without keeping safe distance or lane deviation events and the like of each vehicle device so as to enable the optimal solution to evaluate dangerous driving performance; or selecting event information such as door closing abnormal events, temperature abnormal events, precooling insufficient events or arrival time abnormal events of the vehicle equipment so as to enable the optimal solution to evaluate the performance of the logistic soldier.
When the performance evaluation system and the performance evaluation method are compared with other conventional technologies, the following advantages are provided:
1. the vehicle equipment returns the information of the driver and the vehicle information, and the data analysis server equipment calculates the performance and ranking of the driver, so that the performance evaluation result can be automatically generated.
2. The performance evaluation method provided by the invention combines the fuzzy attribution function to generate the paired comparison matrix, so that the difference analysis between data can be strengthened and infinite or meaningless numerical values can be avoided.
3. The performance evaluation method provided by the invention combines the distance function or the similarity function to generate the paired comparison matrix, and can find out the data with the maximum difference.
4. The performance evaluation method provided by the invention can be applied to energy consumption estimation, so that the energy quantity consumed by different drivers, different vehicle devices and different driving behaviors is considered, and a solution with the lowest energy consumption is selected and provided for enterprise managers for reference.
5. The performance evaluation method provided by the invention can be applied to dangerous driving evaluation, can consider the risk degrees generated by different drivers, different vehicle devices and different driving behaviors, and can evaluate and select the solution with the lowest risk degree to provide for enterprise managers for reference.
6. The performance evaluation method provided by the invention can be applied to evaluation of logistics staffs, can consider violation degrees generated by different drivers, different vehicle devices and different driving behaviors, and can evaluate and select a solution with the lowest violation degree to provide for reference of enterprise managers.
Drawings
Fig. 1 is a system architecture diagram of an embodiment of a performance assessment system of the present invention.
Fig. 2 is a flowchart illustrating the steps of an embodiment of the performance evaluation method of the present invention.
Fig. 3 is a schematic diagram of a hierarchical structure of an embodiment of the performance evaluation method of the present invention.
Fig. 4 is a schematic diagram of a hierarchical structure of an embodiment of the performance evaluation method of the present invention.
Fig. 5 is a system architecture diagram of an embodiment of the performance assessment system of the present invention.
Fig. 6 is a schematic diagram of a hierarchical structure of an embodiment of the performance evaluation method of the present invention.
Fig. 7 is a system architecture diagram of an embodiment of the performance assessment system of the present invention.
Fig. 8 is a schematic diagram of a hierarchical structure of an embodiment of the performance evaluation method of the present invention.
Description of reference numerals:
1 vehicle device
100 communication module
101 middleware module
102 positioning module
103 driver identity identification device
104 energy detecting device
105 azimuth angle sensor
106 concentration detection equipment
107 front vehicle distance detection equipment
108 lane deviation detection equipment
109 on-board diagnostic system
110 temperature sensor
2 data analysis server apparatus
20 communication module
22 middleware module
24 performance assessment module
3 database device
30 communication module
32 operation module
34 storage module
4 external information equipment
Step S201-S206 flow
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail with reference to the accompanying drawings and embodiments; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, a system architecture diagram of a performance evaluation system according to a first embodiment of the present invention is shown, wherein the system includes a plurality of vehicle devices 1 (only one of them is shown to avoid complexity of the drawing), a data analysis server device 2 and a database device 3.
The vehicle device 1 can transmit vehicle device information about its set vehicle to the data analysis server device 2, the data analysis server device 2 can store the data to the database device 3, and the data analysis server device 2 can execute the performance evaluation algorithm of the present invention to calculate the performance and ranking of each driver.
In this embodiment, the vehicle device 1 includes a communication module 100, a middleware module 101, a positioning module 102, a driver identity recognition device 103, and an energy detection device 104, wherein the communication module 100 can support a 4G (Long Term Evolution, LTE) communication technology, so that the vehicle device 1 can link a 4G network via the communication module 100 and establish communication with the data analysis server device 2; the middleware module 101 may support hypertext Transfer protocol and Representational State Transfer (REST), the vehicle device 1 may call an Application Programming Interface (APIs) of the data analysis server device 2 via the middleware module 101, and transmit vehicle device information to the data analysis server device 2 in a periodic or aperiodic manner, where the vehicle device information may include a vehicle number, a vehicle model, a driver number, time information, location information, vehicle speed information, or the like; the positioning module 102 can support a global positioning system, so that the vehicle device 1 can obtain position information and vehicle speed information via satellite signals; the driver Identification device 103 is a Radio Frequency Identification (RFID) card reader, and the driver Identification certificate of each driver is an RFID tag (tag) which can store a driver number, and when approaching the driver Identification device 103, the driver Identification device 103 can obtain the driver number therein; the energy detecting device 104 is a fuel amount detecting device, and is capable of detecting the amount of gasoline in the fuel tank of the vehicle to calculate the difference of the amount of gasoline to obtain energy consumption information, and providing the energy consumption information to the vehicle device 1, so that the vehicle device information transmitted by the vehicle device 1 includes a vehicle number, a vehicle model number, a driver number, time information, position information, vehicle speed information, and energy consumption information.
In this embodiment, however, C is commonNPlatform vehicle device, TNModel of vehicle, DNA driver, the vehicle device 1 may transmit vehicle device information to the data analysis server device 2 once every 30 seconds, as shown in the example of table one below; for example: the first driver drives a vehicle with a first vehicle number at 2015/01/01, the vehicle is provided with a vehicle device with a first vehicle type, the vehicle device obtains the identity of the driver as the first driver number through the driver identity recognition device, and the vehicle device can obtain the position information (i.e. longitude 102.5423383 degree and latitude 24.09490167 degree) and the vehicle speed information (i.e. speed 44 km/h) of the vehicle device at 06:00:00 via the positioning module, and the vehicle device obtains the information which is eliminated within 30 seconds (2015/01/0105: 59: 30-2015/01/0106: 00:00) through the energy detection deviceThe fuel consumption is 0.037 liters (i.e. energy consumption information), and then the REST APIs of the data analysis server are called through the middleware module to transmit the vehicle equipment information to the data analysis server.
The following is table one:
referring to fig. 1, the data analysis server apparatus 2 includes a communication module 20, a middleware module 22, and a performance evaluation module 24; in this embodiment, the data analysis server device 2 may support Linux operating system, microsoft Windows operating system, etc., and may build a web service server on the operating system; the communication module 20 can support wired network transmission to establish communication between the vehicle device 1, the database device 3 and the data analysis server device 2; the middleware module 22 is implemented by a Tomcat web service server to establish a plurality of REST APIs for interfacing with the vehicle device 1, and is capable of receiving the vehicle device information transmitted by the vehicle device 1 via the http, and storing the received vehicle device information and the energy consumption information in the database device 3, wherein the vehicle device information may include a vehicle number, a vehicle model, a driver number, time information, location information, vehicle speed information, and energy consumption information; the performance evaluation module 24 executes a performance evaluation algorithm, collects vehicle equipment information transmitted by each vehicle equipment, analyzes the energy consumption quantity of each driver, and calculates the energy consumption performance and ranking of each driver.
Referring to fig. 1, the database device 3 includes a communication module 30, an operation module 32 and a storage module 34; in this embodiment, the database device 3 is implemented by using a microsoft Structured Query Language (SQL) server, MySQL, PostgreSQL, an oracle database server, a MongoDB server, an HBase server, and the like; the communication module 30 can support wired network transmission to establish communication between the database device 3 and the data analysis server device 2; the operation module 32 can receive the request transmitted by the data analysis server device 3 through the communication module 30 to access the storage module 34; the storage module 34 interfaces with the operation module 32 to provide operations such as adding, modifying, deleting, querying, etc., and the storage module 34 can store the vehicle device information (as shown in the above table).
Referring to fig. 2 again, a flow chart of the steps of the performance evaluation method of the present invention is shown, the performance evaluation method, i.e. the performance evaluation algorithm executed by the performance evaluation module in the data analysis server device, at least includes the following steps:
1. step S201 collects and analyzes vehicle device information, each vehicle device reports the vehicle device information to the data analysis server device, the data analysis server device analyzes the vehicle device information, especially the vehicle device information in a time zone, and stores the vehicle device information to the database device;
2. step S202, selecting characteristic elements, wherein the characteristic elements comprise vehicle equipment, vehicle models, drivers and the like, and a plurality of characteristic elements can be selected for performance evaluation;
3. step S203, constructing a hierarchical structure, and setting an upper-layer and a lower-layer associated structure according to the selected characteristic elements;
4. step S204, generating an algorithm for generating a pair comparison matrix according to the characteristic elements set by each level;
5. step S205, calculating characteristic values and characteristic vectors, and calculating a characteristic vector matrix of characteristic elements of each level by using numerical analysis;
6. step S206 selects solutions, which can generate scores of each solution according to the eigenvector matrix of each level of feature elements, and then screen out the best solution corresponding to a best score.
According to the performance evaluation method, in the embodiment, the step S201 of collecting and analyzing vehicle device information refers to the performance evaluation module querying and analyzing each vehicle device information in a time interval, which is one year in this embodiment, from the database device; taking the ith vehicle model as an example, the performance assessment module queries and evaluates the database deviceThe energy consumption information of the i-th vehicle model in 2015 year in the whole year is counted
In this example, T is commonNThe vehicle models are classified, and energy consumption information of all the vehicle models is counted
Step S202 selects a feature element, and analyzes the feature element by using two feature elements, i.e., the vehicle model and the driver, and then step S203 is performed to establish a hierarchical structure, and the optimal solution is used as the first layer, the vehicle model is used as the second layer, and the driver is used as the third layer in sequence, and the schematic diagram of the hierarchical structure is shown in fig. 3.
The pairwise comparison matrix generation algorithm of step S204 counts the values of the feature elements set at each level, and generates a pairwise comparison matrix according to the ratio of the values;
in this embodiment, the vehicle model of the second layer may correspond to a comparison matrix, and the pair of comparison matrices may be generated by comparing and analyzing the energy consumption of each vehicle model with the pair of comparison matrices, and calculating a feature vector matrix of feature elements in the hierarchy by using a numerical analysis method;
initialization of vehicle model pairwise comparison matrix:
normalized pair-wise comparison matrix for vehicle model:
the feature vector matrix of the second layer of feature elements, namely the influence factor weight matrix of each vehicle model:
in this embodiment, the drivers of the vehicle models of the third layer may correspond to a comparison matrix, and the pair of comparison matrices may be generated in such a way that the energy consumption of the drivers of the vehicle models can be compared and analyzed by the pair of comparison matrices; if the energy consumption of each driver driving the first vehicle model is taken as an example:
initialization of drivers of a first vehicle model is a pairwise comparison matrix:
normalized paired comparison matrix for drivers of a first vehicle model:
the influence factor weight matrix of each driver of the first vehicle model:
according to the above calculation method, the driver of the xth vehicle model of the third layer may correspond to a pair comparison matrix, and the pair comparison matrix may be generated in the following manner, and the energy consumption of each driver of each vehicle model may be compared and analyzed by the pair comparison matrix;
initialization of drivers for the xth vehicle model is a pairwise comparison matrix:
normalized paired comparison matrix for driver of xth vehicle model:
the influence factor weight matrix of each driver of the x-th vehicle model is as follows:
by analogy, T can be generated at the third layerNIndividual pairwise comparison matrices, i.e.
And can establish the feature vector matrix W of the feature elements of the third layer2：
In step S205, the eigenvalue and the eigenvector are calculated. Step S206 is entered to select the solution, the score of each solution is generated according to the feature vector matrix of each level feature element, and then the best solution is screened out; in this embodiment, the score for each solution is generated by matrix multiplication (as shown in the following formula), and the score for each solution represents the proportion of energy consumption, v, for that solution as compared to other drivers1Score (i.e., the score of the first driver), upsilon, representing solution 12Score representing solution 2 (i.e., the score of the second driver), …,
Representative solution DNFraction of (i.e. D th)NThe score of the driver);
in this embodiment, the lower the energy consumption, the better the energy consumption, so the score of each solution is compared, the solution with the lowest score is obtained, and the driver corresponding to the solution is the best driver; that is, assume that the lowest score is upsilon1It means that the first driver is better than the other drivers, and the first driver can obtain the least energy consumption when driving various vehicle models.
According to the above calculation method, let T beN3, the energy consumption quantity of the first vehicle model is 1.011 times of that of the second vehicle model, and the energy consumption quantity of the first vehicle model is 1.022 times of that of the third vehicle model, then the initialized pairwise comparison matrix of the vehicle models is shown as the following table two example:
| |
|
|
|
| |
1.000 | 1.011 | 1.022 |
| |
0.989 | 1.000 | 1.011 |
| |
0.978 | 0.989 | 1.000 |
Then, a normalized paired comparison matrix of the vehicle model is calculated according to the initialized paired comparison matrix of the vehicle model, as shown in the following table three examples:
| |
|
|
|
| |
0.337 | 0.337 | 0.337 |
| |
0.333 | 0.333 | 0.333 |
| |
0.330 | 0.330 | 0.330 |
Then, the feature vector matrix of the second layer is calculated according to the normalized paired comparison matrix of the vehicle model, as shown in the following table four examples:
| |
|
|
| 0.337 | 0.333 | 0.330 |
According to the above calculation method, assume DNIf 3, the energy consumption amount of the first driver driving the first vehicle model is 0.981 times that of the second driver driving the first vehicle model, and the energy consumption amount of the first driver driving the first vehicle model is 0.972 times that of the third driver driving the first vehicle model, then the driver of the first vehicle model initializes the pairwise comparison matrix as shown in the following table five examples:
| |
|
|
|
| |
1 | 0.981 | 0.972 |
| |
1.019 | 1 | 0.991 |
| |
1.029 | 1.009 | 1 |
Then, the driver normalized pair-wise comparison matrix of the first vehicle model is calculated according to the pair-wise comparison matrix initialized by the driver of the first vehicle model, as shown in the following six examples:
| |
|
|
|
| |
0.328 | 0.328 | 0.328 |
| |
0.334 | 0.334 | 0.334 |
| |
0.338 | 0.338 | 0.338 |
And calculating an influence factor weight matrix of each driver of the first vehicle model according to the driver normalization pair comparison matrix of the first vehicle model, as shown in the following seven examples:
| |
|
|
| 0.328 | 0.334 | 0.338 |
According to the above calculation method, assuming that the energy consumption amount of the first driver driving the second vehicle model is 0.941 times as much as the energy consumption amount of the second driver driving the second vehicle model, and the energy consumption amount of the first driver driving the second vehicle model is 0.974 times as much as the energy consumption amount of the third driver driving the second vehicle model, the initialized paired comparison matrix of the drivers of the second vehicle model is as shown in the following eight examples:
| |
|
|
|
| |
1 | 0.941 | 0.974 |
| |
1.063 | 1 | 1.035 |
| |
1.027 | 0.966 | 1 |
The normalized pair-wise comparison matrix for the driver of the second vehicle model may be calculated from the initialized pair-wise comparison matrix for the driver of the second vehicle model, as shown in the nine examples of table below:
the influencing factor weight matrix for each driver of the second vehicle model may be calculated from the normalized pairwise comparison matrix of drivers of the second vehicle model as shown in the following ten examples:
| |
|
|
| 0.324 | 0.344 | 0.332 |
According to the above calculation method, assuming that the energy consumption amount of the first driver driving the third vehicle model is 0.998 times the energy consumption amount of the second driver driving the third vehicle model, and the energy consumption amount of the first driver driving the third vehicle model is 0.999 times the energy consumption amount of the third driver driving the third vehicle model, the initialized pairwise comparison matrix of the drivers of the third vehicle model is as shown in the following eleventh example:
| |
|
|
|
| |
1 | 0.998 | 0.999 |
| |
1.002 | 1 | 1.001 |
| |
1.001 | 0.999 | 1 |
The normalized pair-wise comparison matrix for the driver of the third vehicle model may be calculated from the initialized pair-wise comparison matrix for the driver of the third vehicle model, as shown in the twelve example table below:
| |
|
|
|
| |
0.333 | 0.333 | 0.333 |
| |
0.334 | 0.334 | 0.334 |
| |
0.333 | 0.333 | 0.333 |
The influence factor weight matrix for each driver of the third vehicle model may be calculated from the normalized pair-wise comparison matrix for the driver of the third vehicle model as shown in the thirteen examples of table below:
| |
|
|
| 0.333 | 0.334 | 0.333 |
And the feature vector matrix of the third layer is combined with the influence factor weight matrix of each driver of the first vehicle model, the influence factor weight matrix of each driver of the second vehicle model and the influence factor weight matrix of each driver of the third vehicle model, as shown in the fourteenth example of the following table:
| |
|
|
|
| |
0.328 | 0.334 | 0.338 |
| |
0.324 | 0.344 | 0.332 |
| |
0.333 | 0.334 | 0.333 |
The scores for each solution can be obtained by matrix multiplication, i.e., the result of matrix multiplication of table four and table fourteen or two, as shown in the fifteen examples below.
| Driver 1 (solution 1) | Driver 2 (solution 2) | Driver 3 (solution 3) |
| 0.328 | 0.337 | 0.334 |
Wherein the first solution (i.e. the first driver) has the lowest score, i.e. the lowest energy consumption, which represents the best solution for the first driving calculated by the method of the present invention.
The invention further provides another embodiment, which is a performance evaluation system and method, and can be applied to the purpose of energy-saving driving performance evaluation, and the performance evaluation system executes a performance evaluation algorithm to collect and analyze the energy consumption of a plurality of drivers for driving vehicles so as to evaluate and select a solution with the lowest consumption.
The performance evaluation system in this embodiment is the same as the configuration of fig. 1, and the vehicle device 1 includes a communication module 100, a middleware module 101, a positioning module 102, a driver identity identification device 103, and an energy detection device 104, where the communication module 100 can support a 4G (Long Term Evolution, LTE) communication technology, so that the vehicle device 1 can link a 4G network via the communication module 100 and establish communication with the data analysis server device 2; the middleware module 101 may support hypertext Transfer protocol and Representational State Transfer (REST), the vehicle device 1 may call an Application Programming Interface (APIs) of the data analysis server device 2 via the middleware module 101, and transmit vehicle device information to the data analysis server device 2 in a periodic or aperiodic manner, where the vehicle device information may include a vehicle number, a vehicle model, a driver number, time information, location information, vehicle speed information, or the like; the positioning module 102 can support a global positioning system, so that the vehicle device 1 can obtain position information and vehicle speed information via satellite signals; the driver Identification device 103 is a Radio Frequency Identification (RFID) card reader, and the driver Identification certificate of each driver is an RFID tag (tag) which can store a driver number, and when approaching the driver Identification device 103, the driver Identification device 103 can obtain the driver number therein; the energy detecting device 104 is a fuel amount detecting device, and is capable of detecting the amount of gasoline in the fuel tank of the vehicle to calculate the difference of the amount of gasoline to obtain energy consumption information, and providing the energy consumption information to the vehicle device 1, so that the vehicle device information transmitted by the vehicle device 1 includes a vehicle number, a vehicle model number, a driver number, time information, position information, vehicle speed information, and energy consumption information.
In this embodiment, C is commonNPlatform vehicle device, TNModel of vehicle, DNThe driver is positioned, and the vehicle equipment transmits the vehicle equipment information once every 30 secondsTo the data analysis server device, as shown in table sixteen below; for example: the first driver drives 2015/01/01 a vehicle with the first vehicle number, the vehicle type of the vehicle equipment arranged on the vehicle is a first vehicle type, the vehicle equipment obtains the identity of the driver as a first driver number through the driver identity identification device, and the vehicular apparatus can acquire the position information (i.e. the longitude 102.5423383 degrees and the latitude 24.09490167 degrees) and the vehicle speed information (i.e. the speed per hour 44 km/h) of the vehicular apparatus at 06:00:00 via its positioning module, and the vehicle equipment obtains the consumed electric quantity of 0.019 degree (kilowatt hour (1kWh) (namely energy consumption information) within 30 seconds (2015/01/0105: 59: 30-2015/01/0106: 00:00) through the energy detection device, and calls REST APIs of the data analysis server through the middleware module to transmit the vehicle equipment information to the data analysis server.
Table sixteen examples are as follows:
referring to fig. 1, the system architecture of the present embodiment continues, wherein the data analysis server device 2 includes a communication module 20, a middleware module 22, and a performance evaluation module 24; in this embodiment, the data analysis server device 2 may support Linux operating system, microsoft Windows operating system, etc., and may build a web service server on the operating system; the communication module 20 can support wired network transmission to establish communication between the vehicle device 1, the database device 3 and the data analysis server device 2; the middleware module 22 is implemented by a Tomcat web service server to establish a plurality of REST APIs for interfacing with the vehicle device 1, and is capable of receiving the vehicle device information transmitted by the vehicle device 1 via the http, and storing the received vehicle device information and the energy consumption information in the database device 3, wherein the vehicle device information may include a vehicle number, a vehicle model, a driver number, time information, location information, vehicle speed information, and energy consumption information; the performance evaluation module 24 executes a performance evaluation algorithm, collects vehicle equipment information transmitted by each vehicle equipment, analyzes the energy consumption quantity of each driver, and calculates the energy consumption performance and ranking of each driver.
The database device 3 comprises a communication module 30, an operation module 32 and a storage module 34; in this embodiment, the database device 3 is implemented by using a microsoft Structured Query Language (SQL) server, MySQL, PostgreSQL, an oracle database server, a MongoDB server, an HBase server, and the like; the communication module 30 can support wired network transmission to establish communication between the database device 3 and the data analysis server device 2; the operation module 32 can receive the request transmitted by the data analysis server device 3 through the communication module 30 to access the storage module 34; the storage module 34 interfaces with the operation module 32 to provide operations such as adding, modifying, deleting, querying, etc., and the storage module 34 can store the vehicle device information (as shown in the sixteen table above).
The step flowchart of the performance evaluation method of the present embodiment is also the same as that of the first embodiment, please refer to fig. 2, which includes the steps of: step S201 collects and analyzes vehicle equipment information; step S202, selecting characteristic elements; step S203, constructing a hierarchical structure; step S204, generating an algorithm by a pair comparison matrix; step S205, calculating a characteristic value and a characteristic vector; step S206 selects solutions to screen out the best solution corresponding to a best score.
In this embodiment, the step S201 of collecting and analyzing the vehicle equipment information is to query and analyze the vehicle equipment information in the database device for each year by the performance evaluation module, and calculate the average energy consumption information of different speed-per-hour intervals, in this embodiment, there are fourteen speed-per-hour intervals, including: the 1 st speed interval is 0 km/h, the 2 nd speed interval is more than 0 km/h and less than or equal to 10 km/h, the 3 rd speed interval is more than 10 km/h and less than or equal to 20 km/h, the 4 th speed interval is more than 20 km/h and less than or equal to 30 km/h, the 5 th speed interval is more than 30 km/h and less than or equal to 40 km/h, the 6 th speed interval is more than 40 km/h and less than or equal to 50 km/h, the 7 th speed interval is more than 50 km/h and less than or equal to 60 km/h, the 8 th speed interval is more than 60 km/h and less than or equal to 70 km/h, the 9 th speed interval is more than 70 km/h and less than or equal to 80 km/h, The 10 th speed interval is more than 80 km/h and less than or equal to 90 km/h, the 11 th speed interval is more than 90 km/h and less than or equal to 100 km/h, the 12 th speed interval is more than 100 km/h and less than or equal to 110 km/h, the 13 th speed interval is more than 110 km/h and less than or equal to 120 km/h, and the 14 th speed interval is more than 120 km/h.
Taking the ith vehicle equipment as an example, the performance evaluation module inquires and analyzes the energy consumption information of each speed interval of the ith vehicle equipment within 2015 from the database equipment: energy consumption information of 1 st speed interval of ith vehicle equipment
Energy consumption information of speed, 2 nd speed interval of ith vehicle equipment
Energy consumption information of the 3 rd hour interval of the ith vehicle equipment
Energy consumption information of the 4 th hour interval of the ith vehicle equipment
Energy consumption information of the 5 th hour interval of the ith vehicle equipment
Energy consumption information of the 6 th hour interval of the ith vehicle equipment
Energy consumption information of 7 th hour interval of speed, i-th vehicle equipment
Energy consumption information of the 8 th hour interval of the ith vehicle equipment
Energy consumption information of the 9 th hour interval of the ith vehicle equipment
Energy consumption information of the 10 th speed interval of the ith vehicle equipment
Energy consumption information of the 11 th hour interval of the ith vehicle equipment
Energy consumption information of 12 th hour interval of speed, i-th vehicle equipment
Energy consumption information of 13 th hour interval of speed, i-th vehicle equipment
Energy consumption information of 14 th hour interval of speed, i-th vehicle equipment
And (4) degree.
According to the performance evaluation method, taking the ith driver driving the xth vehicle equipment as an example, the performance evaluation module inquires and analyzes the energy consumption information of the xth driver driving the xth vehicle equipment in 2015 year and whole year in each speed interval from the database equipment: the energy consumption information of the ith driver driving the xth vehicle equipment in the 1 st speed interval is
The energy consumption information of the ith driver driving the xth vehicle equipment in the 2 nd speed interval is
Energy consumption information of the ith driver driving the xth vehicle equipment in the 3 rd speed interval is
The energy consumption information of the ith driver driving the x-th vehicle equipment in the 4 th speed interval is
The energy consumption information of the ith driver driving the xth vehicle equipment in the 5 th speed interval is
Energy consumption information of the ith driver driving the xth vehicle equipment in the 6 th speed interval is
The energy consumption information of the ith driver driving the x-th vehicle equipment in the 7 th speed interval is
The energy consumption information of the ith driver driving the x-th vehicle equipment in the 8 th speed interval is
Energy consumption information of the ith driver driving the xth vehicle equipment in the 9 th speed interval is
Energy consumption information of the ith driver driving the xth vehicle equipment in the 10 th speed interval is
Energy consumption information of the ith driver driving the xth vehicle equipment in the 11 th speed interval is
The energy consumption information of the ith driver driving the x-th vehicle equipment in the 12 th speed interval is
Energy consumption information of the ith driver driving the xth vehicle equipment in the 13 th speed interval is
The energy consumption information of the 14 th speed interval of the ith driver driving the x th vehicle equipment is
And (4) degree.
In this embodiment, step S202 selects a feature, and the two feature are used for analysis, and step S203 is performed to establish a hierarchical structure, and the optimal solution is used as the first layer, the vehicle device is used as the second layer, and the driver is used as the third layer in sequence, and the schematic diagram of the hierarchical structure is shown in fig. 4.
In the paired comparison matrix generating algorithm in step S204, the distance function or the similarity function may be used to calculate the value of the feature elements set in each level, and the paired comparison matrix is generated according to the value.
In this embodiment, the vehicle device of the second layer may correspond to a comparison matrix, and the pair of comparison matrices may be generated by Cosine Similarity (Cosine Similarity), and may be utilized to calculate a normalized pair of comparison matrices of the vehicle device and an eigenvector matrix of the feature element of the second layer, respectively;
initialization of vehicle devices into a comparison matrix:
normalized paired comparison matrix for vehicle devices:
a feature element feature vector matrix of the second layer, that is, an influence factor weight matrix of each vehicle device:
in this embodiment, the driver of each vehicle device of the third layer may correspond to a comparison matrix, the comparison matrix pair may be generated in a cosine similarity manner, and the comparison and analysis of the energy consumption of each driver of each vehicle device may be performed by the comparison matrix pair, taking the ith driving xth vehicle device as an example, the comparison matrix pair may be initialized by the driver of the xth vehicle device, and then the normalized comparison matrix pair of the driver of the xth vehicle device and the feature vector matrix of the third layer may be calculated;
wherein the initialization of the driver of the xth vehicle device is a pairwise comparison matrix:
wherein the normalized pair-wise comparison matrix for the driver of the xth vehicle device:
the driver influence factor weight matrix for the xth vehicle device:
by analogy, C can be generated at the third layerNIndividual pairwise comparison matrices, i.e.
And can establish the feature vector matrix W of the feature element of the third layer2：
In step S205, the eigenvalue and the eigenvector are calculated. Step S206 is entered to select a solution, in this embodiment, the score of each solution can be obtained by multiplying the eigenvector matrix (as shown below), and the score of each solution represents the energy consumption ratio of the solution compared with other drivers, v1Score (i.e., the score of the first driver), upsilon, representing solution 12Score representing solution 2 (i.e., the score of the second driver), …,
Representative solution DNFraction of (i.e. D th)NThe score of the driver);
the cosine similarity can be used to calculate the similarity of each solution, and the solution with the lowest score is found out according to the similarity, namely, the solution represents the largest difference with other solutions, so as to find out the driver with the largest energy consumption difference.
The performance evaluation module executes a performance evaluation algorithm, collects and analyzes event information of a plurality of drivers driving vehicles, wherein the event information is an overspeed event, a rapid acceleration event, a rapid braking event, a sharp turning event, a absenteeism event, an event without maintaining a safe distance, a lane deviation event and the like, so as to evaluate and select a solution with the lowest risk degree.
Referring to fig. 5, the system architecture diagram of the performance evaluation system of the present embodiment includes a plurality of vehicle devices 1 (only one of them is shown to avoid complexity of the drawing), a data analysis server device 2, and a database device 3.
The vehicle device 1 can transmit vehicle device information about its set vehicle to the data analysis server device 2, the data analysis server device 2 can store the data to the database device 3, and the data analysis server device 2 can execute the performance evaluation algorithm of the present invention to calculate the performance and ranking of each driver.
In this embodiment, the vehicle apparatus 1 includes a communication module 100, a middleware module 101, a positioning module 102, a driver identification device 103, an azimuth sensor 105, a concentration detection apparatus 106, a preceding vehicle distance detection apparatus 107, and a lane departure detection apparatus 108; the communication module 100 can support a 4G (Long Term Evolution, LTE) communication technology, so that the vehicle device 1 can link to a 4G network via the communication module 100 and establish communication with the data analysis server device 2; the middleware module 101 may support hypertext Transfer protocol and Representational State Transfer (REST), the vehicle device 1 may call an Application Programming Interface (APIs) of the data analysis server device 2 via the middleware module 101, and transmit vehicle device information to the data analysis server device 2 in a periodic or aperiodic manner, where the vehicle device information may include a vehicle number, a vehicle model, a driver number, time information, location information, vehicle speed information, or the like; the positioning module 102 can support a global positioning system, so that the vehicle equipment 1 can obtain position information and vehicle speed information through satellite signals, and judge event information such as an overspeed event, a rapid acceleration event, a rapid braking event and the like through the vehicle speed information; the driver Identification device 103 is a Radio Frequency Identification (RFID) card reader, and the driver Identification certificate of each driver is an RFID tag (tag) that stores a driver number, and when approaching the driver Identification device 103, the driver Identification device 103 can obtain the driver number therein.
The azimuth sensor 105 is a gyroscope capable of detecting azimuth information of the vehicle driving so that the vehicle device 1 can obtain the azimuth information, and the azimuth information is a value between 0 and 360 and can be used for judging whether the vehicle has event information such as a sharp turning event; the concentration detection device 106 is a wearable brain wave detection device capable of being worn on the head of the driver to detect brain wave information of the driver, and the vehicle device 1 can obtain the brain wave information through the brain wave detection device 106 to generate concentration information.
The preceding vehicle distance detecting device 107 can detect preceding vehicle distance information between a vehicle and a preceding vehicle, so that the vehicle device 1 can obtain the preceding vehicle distance information through the preceding vehicle distance detecting device 107, wherein the preceding vehicle distance information is a numerical value which can be used for judging whether the vehicle has event information such as an event of not keeping a safe distance and the like; the lane departure detection device 108 can detect the departure of the vehicle from the lane and the status of the turn signal, so that the vehicle device 1 can obtain the lane departure information through the lane departure detection device 108, wherein the lane departure information is a value of 0 or 1, 0 is a lane departure-free lane, 1 is a lane departure-free lane, and can be used to determine whether the vehicle has event information such as a lane departure event.
In summary, the vehicle device information transmitted by the vehicle device 1 in this embodiment includes a vehicle number, a driver number, time information, and event information, where the event information may be an overspeed event, a sudden acceleration event, a sudden braking event, a sudden turning event, a absenteeism event, an event without maintaining a safe distance, and a lane deviation event.
Among them, in the present embodiment, C is commonNPlatform vehicle device, DNDriver, RNThe vehicle device 1 can obtain position information, vehicle speed information, azimuth information, concentration information, vehicle distance information, and lane offset information from the positioning module 102, the azimuth sensor 105, the concentration detection device 106, the vehicle distance detection device 107, and the lane offset detection device 108 every second, and determine whether the information conforms to the risk factor after the vehicle device 1 analyzes the information, and if the information conforms to the risk factor, the vehicle device information includes event information conforming to the risk factor when the vehicle device information is transmitted to the data analysis server device 2.
In this embodiment, the risk factor class RN7, representing event information containing a total of seven risk factors, respectively: an overspeed event, a sudden acceleration event, a sudden braking event, a sudden turn event, a absenteeism event, a non-maintained safe distance event, or a lane departure event.
The first danger factor is overspeed, the vehicle device 1 can obtain information from the positioning module 102 every second to determine vehicle speed information, and the vehicle device 1 can interface with an external information device 4 through the middleware module 101 and the communication module 100 to obtain road information on a road where the vehicle is positioned, such as speed limit, from the external information device 4, and then compare the vehicle speed information with the speed limit; when the vehicle speed information is greater than the speed limit, the vehicle device 1 interfaces with the data analysis server device 2 via the communication module 100 to transmit vehicle device information to the data analysis server device 2, where the vehicle device information at least includes a vehicle number, a driver number, time information, and event information, and the event information is an overspeed event.
The second risk factor is rapid acceleration, the vehicle device can obtain the vehicle speed information from the positioning module 102 every second, and the vehicle device 1 can record the vehicle speed information of the previous second and set a first acceleration threshold, when the difference between the vehicle speed information and the vehicle speed information of the previous second is greater than the first acceleration threshold, the vehicle device 1 interfaces with the data analysis server device 2 through the communication module 100 to transmit the vehicle device information to the data analysis server device 2, the vehicle device information at least includes a vehicle number, a driver number, time information and event information, and the event information is a rapid acceleration event.
The third risk factor is emergency braking, the vehicle device 1 can obtain the vehicle speed information from the positioning module 102 every second, and the vehicle device 1 can record the vehicle speed information of the previous second and set a second acceleration threshold, when the difference between the current vehicle speed information of the previous second and the vehicle speed information is greater than the second acceleration threshold, the vehicle device 1 interfaces with the data analysis server device 2 via the communication module 100, and transmits the vehicle device information to the data analysis server device 2, the vehicle device information at least includes a vehicle number, a driver number, time information and event information, and the event information is an emergency braking event.
The fourth risk factor is a sharp turn, the vehicle device 1 may obtain the azimuth information from the azimuth sensor 105 every second, and the vehicle device 1 may record the azimuth information of the previous second and set a first azimuth threshold and a second azimuth threshold, where the first azimuth threshold is smaller than the second azimuth threshold, and when the absolute value of the difference between the azimuth information and the azimuth information of the previous second is greater than the first acceleration threshold and the difference is smaller than the second azimuth threshold, the vehicle device 1 interfaces with the data analysis server device 2 via the communication module 100 to transmit the vehicle device information to the data analysis server device 2, where the vehicle device information at least includes a vehicle number, a driver number, time information, and event information, and the event information is a sharp turn event.
The fifth risk factor is absenteeism in driving, the vehicle device 1 can acquire the concentration information from the concentration detection device 106 every second, and the vehicle device 1 can set a concentration threshold, when the concentration information is smaller than the concentration threshold, the vehicle device 1 interfaces with the data analysis server device 2 via the communication module 100 to transmit the vehicle device information to the data analysis server device 2, the vehicle device information at least includes a vehicle number, a driver number, time information and event information, and the event information is a absenteeism event.
The sixth risk factor is that the safety distance is not maintained, the vehicle device 1 may obtain the vehicle speed information from the positioning module 102 every one second, obtain the distance information to the vehicle ahead from the vehicle ahead distance detecting device 107, calculate a value obtained by subtracting twenty times from the vehicle speed information (in kilometers per hour), determine whether the value is greater than the distance information to the vehicle ahead, and when the value is greater than the distance information to the vehicle ahead, the vehicle device 1 interfaces with the data analysis server device 2 via the communication module 100 to transmit the vehicle device information to the data analysis server device 2, where the vehicle device information at least includes a vehicle number, a driver number, time information, and event information, and the event information is an event that the safety distance is not maintained.
The seventh risk factor is lane deviation, the vehicle device 1 may obtain lane deviation information from the lane deviation detecting device 108 every second and determine whether the value is 1, and when the value of the lane deviation information is 1, the vehicle device 1 interfaces with the data analysis server device 2 via the communication module 100 to transmit vehicle device information to the data analysis server device 2, where the vehicle device information at least includes a vehicle number, a driver number, time information, and event information, and the event information is a lane deviation information event.
With reference to fig. 5, the data analysis server apparatus 2 includes a communication module 20, a middleware module 22, and a performance evaluation module 24; in this embodiment, the data analysis server device 2 may support Linux operating system, microsoft Windows operating system, etc., and may build a web service server on the operating system; the communication module 20 can support wired network transmission to establish communication between the vehicle device 1, the database device 3 and the data analysis server device 2; the middleware module 22 is implemented by using a Tomcat web service server to establish a plurality of REST APIs for interfacing with the vehicle device 1, and is capable of receiving the vehicle device information transmitted by the vehicle device 1 via the http, and storing the received vehicle device information and the energy consumption information in the database device 3, wherein the vehicle device information may include a vehicle number, a vehicle model, a driver number, time information, location information, vehicle speed information, and event information, as shown in the seventeenth example of the following table; the performance evaluation module 24 executes a performance evaluation algorithm, collects vehicle equipment information transmitted by each vehicle equipment, analyzes dangerous driving factors of each driver, and calculates the performance and ranking of each driver.
TABLE seventeen is:
the data analysis server 2 can interface with the external information device 4 through the communication module 20 via the middleware module 22, and obtain the probability of the traffic accident of each risk factor to the external information device 4, and store the probability of the traffic accident to the database device 3, as shown in the eighteenth example of the following table:
the database device 3 includes a communication module 30, an operation module 32 and a storage module 34; in this embodiment, the database device 3 is implemented by using a microsoft Structured Query Language (SQL) server, MySQL, PostgreSQL, an oracle database server, a MongoDB server, an HBase server, and the like; the communication module 30 can support wired network transmission to establish communication between the database device 3 and the data analysis server device 2; the operation module 32 can receive the request transmitted by the data analysis server device 3 through the communication module 30 to access the storage module 34; the storage module 34 interfaces with the operation module 32 to provide operations of adding, modifying, deleting, querying, etc., and the storage module 34 can store the vehicle device information (as shown in the seventeenth table).
The steps of the performance evaluation method of the present embodiment also refer to the step flowchart of fig. 2, and the steps include: step S201 collects and analyzes vehicle equipment information; step S202, selecting characteristic elements; step S203, constructing a hierarchical structure; step S204, generating an algorithm by a pair comparison matrix; step S205, calculating a characteristic value and a characteristic vector; step S206 selects solutions to screen out the best solution corresponding to a best score.
In this embodiment, the step S201 of collecting and analyzing vehicle device information may query and analyze the database device for each piece of vehicle device information within one month by the performance evaluation module.
Taking the ith risk factor of the jth driver as an example, the performance evaluation module inquires and counts the quantity of event information of the ith risk factor of the jth driver in the month of January 2015 to the database device
In this example, R is commonNThe risk factors can be used for counting the number of the event information of the jth driver with various risk factors
In this embodiment, step S202 selects feature elements to analyze with two feature elements, namely risk factor and driver, and step S203 is performed to establish a hierarchical structure, and the optimal solution is used as the first layer, the risk factor is used as the second layer, and the driver is used as the third layer in sequence, and the schematic diagram of the hierarchical structure is shown in fig. 6.
In step S204, the pairwise comparison matrix generation algorithm may count the values of the feature elements set in each level, and generate a pairwise comparison matrix according to the ratio of the values.
In this embodiment, the risk factors of the second layer may correspond to a comparison matrix, the pair of comparison matrices may be generated in the following manner, and the pair of comparison matrices may compare and analyze the probability of the traffic accident of each risk factor, and then calculate the feature vector matrix of the feature elements of each layer by using numerical analysis;
wherein the initialization of the risk factors is based on a comparison matrix:
normalized pair-wise comparison matrix for risk factors:
the feature vector matrix of the second layer, namely the influence factor weight matrix of each risk factor:
in this embodiment, each risk factor of the third level driver may correspond to a pair comparison matrix, the pair comparison matrix may be generated in the following manner, and in order to avoid the case where the denominator is 0, the number of risk factor event information is increased by one, and the comparison and analysis of the number of risk factor event information of each driver may be performed by the pair comparison matrix; in the following, the number of event messages generated by the first risk factor of each driver is taken as an example:
wherein the driver generates an initialized pairwise comparison matrix of the first risk factors:
wherein the driver generates a normalized pairwise comparison matrix of the first risk factors:
wherein, the driver generates an influence factor weight matrix of the first risk factor:
according to the same calculation mode, the x-th risk factor of each driver on the third layer can correspond to a comparison matrix, the pair of comparison matrices can be generated in the following mode, and the comparison and analysis of the number of the risk factor event information of each driver can be carried out through the pair of comparison matrices;
wherein the driver generates an initialized pairwise comparison matrix of the xth risk factor:
wherein the driver generates a normalized pairwise comparison matrix of the xth risk factor:
wherein, the driver generates the weight matrix of the influence factors of the x-th risk factor:
by analogy, R can be generated at the third layerNIndividual pairwise comparison matrices, i.e.
And can establish the feature vector matrix W of the feature element of the third layer2：
In the embodiment, step S206 selects solutions, which may generate a score for each solution according to the eigenvector matrix of each level of feature elements, and then screen out the best solution corresponding to a best score; the score for each solution can be generated by matrix multiplication (as shown below), and the score for each solution is represented as its proportion, upsilon, of the likelihood of a traffic accident as compared to other drivers1Score (i.e., the score of the first driver), upsilon, representing solution 12Score representing solution 2 (i.e., the score of the second driver), …,
Representative solution DNFraction of (i.e. D th)NThe score of the driver);
in this embodiment, the lower the possibility of a traffic accident, the better, so the scores of each solution are compared to obtain the solution with the lowest score, and the driver corresponding to the best solution is represented as the best driver, which will obtain the least risk of a traffic accident under each risk factor.
Another disclosed embodiment is also a performance evaluation system and method for performance evaluation of dangerous driving, which can be based on the third embodiment, wherein the performance evaluation module executes a performance evaluation algorithm, but when a solution is selected, a score of each solution is generated according to a feature vector matrix of each level of feature elements, and then a decision tree information profit method is used to screen out an optimal solution; the decision tree information profit method comprises the steps of calculating a normalized solution score vector matrix, calculating the confusion degree of scores of each risk factor of each driver after normalization, and calculating the confusion degree to obtain information profit.
Like the third embodiment described above, the feature vector matrix W of the feature elements of the second layer is obtained1Feature element feature vector matrix W of the third layer2And scores of solutions
Then, a normalized solution score vector matrix omega is generated by the performance evaluation module using the following calculation method, wherein,
represents the normalized fraction of the ith risk factor of the jth driver:
according to the calculation mode, the performance evaluation module calculates the confusion degree of the scores of each driver after each risk factor is normalized by using an entropy (entropy) formula, and calculates the confusion degree E of the scores of each driver after the jth driver generates each risk factorjFor example, the calculation is as follows:
according to the calculation mode, the performance evaluation module calculates the confusion degree of the scores of each normalized risk factor of each driver by using an entropy formula, and then reduces the scores by oneRemove the degree of disorder to obtain information profit, profit G with information of jth driverjFor example, the calculation is as follows: gj＝1-Ej。
In the following, let R beNIs 3, DNTo 3, a normalized solution fractional vector matrix may be computed as follows:
wherein the content of the first and second substances,
the normalized first risk factor for the first driver has a score of 0.7976,
The third driver normalized the risk factor for the third driver to a score of 0.4225, and so on.
According to the calculation mode, the performance evaluation module calculates the confusion degree of the scores of each driver after each risk factor is normalized by using an entropy formula;
wherein the degree of confusion E of the scores normalized by each risk factor of the first driver1：
Wherein the confusion degree E of the scores of the normalized danger factors of the second driver2：
Wherein the degree of confusion E of the scores of the normalized risk factors of the third driver3：
According to the calculation mode, the performance evaluation module calculates the confusion degree of the scores of each normalized risk factor of each driver by using an entropy formula, and then reduces the confusion degree by using one to obtain information profit; wherein the information of the first driver is profitable G1＝1-E11-0.586-0.414; information gain G of the second driver2＝1-E21-0.868-0.132; information gain G of third driver3＝1-E3＝1-0.853＝0.147。
After the information profit of each driver is completed, the performance evaluation module sorts the information profit, and selects a solution with the highest information profit, namely an optimal solution, which represents that the corresponding driver has obvious abnormality compared with other drivers under one or more risk factors; in this embodiment, the first driver's information profit G1And finally, selecting the first driver, and recording that the first driver is the abnormal driver by the performance evaluation module.
Still another embodiment of the present invention is a performance evaluation system and method, which can be applied to the performance evaluation of logistics staffs, and the performance evaluation system performs a performance evaluation algorithm to collect and analyze event information of vehicles driven by a plurality of logistics staffs so as to evaluate a solution with the lowest violation degree.
Referring to fig. 7, a system architecture diagram of the performance evaluation system according to the fifth embodiment includes a plurality of vehicle devices 1 (only one of them is shown to avoid complexity of the drawing), a data analysis server device 2, and a database device 3.
The vehicle device 1 can transmit vehicle device information about its set vehicle to the data analysis server device 2, the data analysis server device 2 can store the data to the database device 3, and the data analysis server device 2 can execute the performance evaluation algorithm of the present invention to calculate the performance and ranking of each driver.
In this embodiment, the vehicle device 1 includes a communication module 100, a middleware module 101, a positioning module 102, a driver identification device 103, an on-board diagnostic system 109, and a temperature sensor 110, and the vehicle device 1 has a vehicle number and a vehicle model; the functions of the communication module 100, the middleware module 101, the positioning module 102 and the driver identification device 103 are the same as those of the previous embodiment; in addition, the on-board diagnostic system 109 may detect vehicle status information of the vehicle, so that the vehicle device 1 may obtain the vehicle status information through the on-board diagnostic system 109, and the vehicle status information may include a door switch information; in addition, the temperature sensor 110 can detect the refrigerator temperature information in the vehicle, so that the vehicle equipment 1 can obtain the temperature information through the temperature sensor 110; therefore, in the present embodiment, the vehicle device information transmitted by the vehicle device 1 includes a vehicle number, a vehicle model number, a driver number, time information, position information, vehicle speed information, door opening/closing information, temperature information, and the like.
In this embodiment, however, C is commonNPlatform vehicle device, TNModel of vehicle, DNA driver, the vehicular apparatus 1 may transmit the vehicular apparatus information to the data analysis server apparatus 2 once every 30 seconds as shown in the example of the nineteenth table below; wherein: the first driver drives a vehicle with a first vehicle number at 2015/01/01, the vehicle is provided with a vehicle device with a vehicle model of the first vehicle model, the vehicle device obtains the identity of the driver as the first driver number through the driver identity identification device, and the vehicleThe device can obtain the position information (namely, the longitude 102.5423383 degrees and the latitude 24.09490167 degrees) and the vehicle speed information (namely, the speed per hour 44 km/h) of the vehicle device at 06:00:00 through the positioning module, the vehicle device obtains the vehicle state information (namely, the vehicle door switch information, the value of the vehicle door switch information is 1, which represents that the vehicle door switch is abnormal) through the on-board diagnosis system, and the vehicle device calls the REST APIs of the data analysis server through the middleware module to transmit the vehicle device information to the data analysis server.
Then, the vehicle device obtains the position information (i.e. the longitude 120.5361317 degrees and the latitude 24.09120167 degrees) and the vehicle speed information (i.e. the speed 39 km/h) of the vehicle device at 06:00:30 through the positioning module, and the vehicle device obtains the vehicle state information (which is a door switch information, the door switch information is 0, and represents that the door switch is normal) through the on-board diagnosis system, and in addition, the vehicle device can obtain the temperature information (which is 18 degrees) through the temperature sensor, the vehicle device calls the REST APIs of the data analysis server through the middleware module to transmit the vehicle device information to the data analysis server, and the REST time of the vehicle device information can be obtained by analogy.
The following are table nineteen:
with reference to fig. 7, the data analysis server apparatus 2 includes a communication module 20, a middleware module 22, and a performance evaluation module 24; in this embodiment, the data analysis server device 2 may support Linux operating system, microsoft Windows operating system, etc., and may build a web service server on the operating system; the communication module 20 can support wired network transmission to establish communication between the vehicle device 1, the database device 3 and the data analysis server device 2; the middleware module 22 is implemented by a Tomcat web service server to establish a plurality of REST APIs for interfacing with the vehicle device 1, and is capable of receiving the vehicle device information transmitted by the vehicle device 1 via the http, and storing the received vehicle device information and the energy consumption information in the database device 3, wherein the vehicle device information may include a vehicle number, a vehicle model, a driver number, time information, location information, vehicle speed information, and energy consumption information; the performance evaluation module 24 executes a performance evaluation algorithm, collects vehicle equipment information transmitted by each vehicle equipment, analyzes the number of violation event information of each driver, and calculates the violation degree performance and ranking of each driver.
Similarly, the database device 3 includes a communication module 30, an operation module 32 and a storage module 34; in this embodiment, the database device 3 is implemented by using a microsoft Structured Query Language (SQL) server, MySQL, PostgreSQL, an oracle database server, a MongoDB server, an HBase server, and the like; the communication module 30 can support wired network transmission to establish communication between the database device 3 and the data analysis server device 2; the operation module 32 can receive the request transmitted by the data analysis server device 3 through the communication module 30 to access the storage module 34; the storage module 34 interfaces with the operation module 32 to provide operations of adding, modifying, deleting, querying, etc., and in addition, the storage module 34 can store a schedule data table, which records the station information of the goods to be sent and received and the scheduled arrival time information, the station information includes a latitude coordinate (as shown in the twenty-below example), and the storage module 34 can also store the vehicle equipment information (as shown in the nineteenth above).
Table twenty is as follows:
when the data analysis server equipment receives the information of each piece of vehicle equipment, the longitude and the latitude of the information of the vehicle equipment are judged and analyzed, the longitude and the latitude of the station number in the schedule data table are compared, and when the distance between coordinates of the two longitudes and the latitude is within a distance threshold value, the vehicle is judged to reach the corresponding station number; for example, in this embodiment, the distance threshold is 50 meters, the data analysis server device receives vehicle device information transmitted from the first vehicle number at 2015/01/0106: 00:00, the vehicle device information includes the first vehicle number (vehicle number), the first vehicle model (vehicle model), the first driver (driver number), 2015/01/0106: 00:00 (time), 120.5423383 (longitude), 24.09490167 (latitude), 44 (vehicle speed), 1 (door switch information), 22 (temperature information), the data analysis server device compares the longitude and latitude coordinates (i.e., longitude 120.5423383 and 24.09490167) with the longitude and latitude coordinates of each station of the first vehicle number in the schedule data table, and it can be obtained that the distance between the current longitude and latitude and the longitude coordinates (i.e., longitude 120.5423383 and latitude 24.09490167) of station 1 is lower than the distance threshold, the schedule data table may be modified to incorporate the actual arrival time information for the first vehicle numbered vehicle as shown in the twenty-first example below.
Table twenty one is:
wherein the data analysis server device is to analyze INAn index factor, in this embodiment, INIs 4, representing the event information containing 4 pointer factors, respectively: for example, the data analysis server apparatus may calculate the event information of the index factors of the previous day every morning at 01:00:00 a day, analyze 2015/01/01 the vehicle equipment information (an example is shown in the nineteen table above) at 2015/01/0201: 00:00 a day, and then generate the event information of the index factors.
The first index factor is abnormal door closing, the performance evaluation module can obtain vehicle equipment information from the database equipment and analyze the door opening and closing information of each item of data, when the value of the door opening and closing information is 1, the door opening and closing information represents that the door is abnormal, namely a door closing abnormal event is generated, and the performance evaluation module further transmits a vehicle number, a driver number, time and corresponding event information corresponding to the door closing abnormal event to the database equipment and stores the vehicle number, the driver number, the time and the corresponding event information into an event information table (as shown in the twenty-two examples in the following table); for example, when the first driver drives the vehicle with the first vehicle number at 2015/01/0106: 00:00, the door opening and closing information is 1, and the performance evaluation module analyzes and judges the event information that the door closing abnormality occurs.
The second pointer factor is a temperature anomaly, the performance evaluation module can set a first temperature threshold and a second temperature threshold, wherein the first temperature threshold is lower than the second temperature threshold, the performance evaluation module obtains the vehicle equipment information from the database equipment (as shown in the nineteenth example in the table above) and analyzes the temperature information of each data, when the temperature information is smaller than the first temperature threshold or larger than the second temperature threshold, the temperature anomaly is represented, the performance evaluation module generates a temperature anomaly event, and transmits the vehicle number, the driver number, the time and the corresponding event information corresponding to the temperature anomaly event to the database equipment for storage in the event information table (as shown in the twenty-two examples in the table below); for example, the first temperature threshold is 16 degrees, the second temperature threshold is 20 degrees, when the first driver drives the vehicle with the first vehicle number at 2015/01/0106: 01:30, the temperature information is 15 degrees, the temperature information is less than the first temperature threshold, and the performance evaluation module analyzes and judges to generate the event information of the temperature abnormality.
The third indicator factor is precooling deficiency, the performance evaluation module can set a first temperature threshold and a second temperature threshold, wherein the first temperature threshold is lower than the second temperature threshold, the performance evaluation module can obtain vehicle equipment information (shown in the nineteenth example in the table above) and a modified shift table data table (shown in the twenty-first example in the table above) from the database equipment, analyze temperature information when the station 1 is reached, when the temperature information is smaller than the first temperature threshold or the temperature information is greater than the second temperature threshold, the precooling deficiency is represented, the performance evaluation module generates a precooling deficiency event, and transmits the vehicle number, the driver number, the time and the event information corresponding to the precooling deficiency event to the database equipment to be stored in the event information table (shown in the twenty-two examples in the table below); for example, the first temperature threshold is 16 degrees, the second temperature threshold is 20 degrees, the first driver drives the vehicle with the first vehicle number to arrive at the station 1 at 2015/01/0106: 00:00, the temperature information is 22 degrees, the temperature information is greater than the second temperature threshold, and the performance evaluation module analyzes and judges the information to generate the event information of insufficient precooling.
The fourth index factor is an arrival time anomaly, the performance evaluation module can set an arrival time threshold value, the database device can obtain the modified schedule data table (as shown in the twenty-one table above), and analyze the scheduled arrival time information and the real arrival time information of each data, when the value obtained after subtracting the real arrival time information from the scheduled arrival time information is higher than the arrival time threshold value, the arrival time anomaly is represented, the performance evaluation module generates an arrival time anomaly event, and transmits the vehicle number, the driver number, the time and the event information corresponding to the arrival time anomaly to the database device, and stores the vehicle number, the driver number, the time and the event information in an event information table (as shown in the twenty-two examples above); for example, the arrival time threshold is 20 minutes, DNThe individual driver drives CNVehicle of individual vehicle number, at station ZNThe scheduled arrival time information is 2015/01/3122: 00:00, the real arrival time information is 2015/01/3122: 30:00, at this time, the value obtained by subtracting the real arrival time information from the scheduled arrival time information and then taking the absolute value is 30 (minutes), the value is higher than the arrival time threshold value, and the event information with the abnormal arrival time is generated after the analysis and judgment of the performance evaluation module.
The following table is twenty-two:
the data analysis server device may interface with an external information device through the communication module by the middleware module, and obtain information such as average loss amount of each pointer factor from the external information device, and store the information of the average loss amount in the database device, as an example, see twenty-third table below;
referring to fig. 2, a flow chart of steps of the performance evaluation method of the present embodiment includes the steps of: step S201 collects and analyzes vehicle equipment information; step S202, selecting characteristic elements; step S203, constructing a hierarchical structure; step S204, generating an algorithm by a pair comparison matrix; step S205, calculating a characteristic value and a characteristic vector; step S206 selects solutions to screen out the best solution corresponding to a best score.
According to the performance evaluation method, in this embodiment, in step S201, vehicle equipment information is collected and analyzed, the data analysis server device can interface with an external information device through the middleware module via the communication module to obtain average loss amounts of each pointer factor from the external information device, and store information of the average loss amounts into the database device, please refer to twenty-three examples above, and the performance evaluation module queries the database device to obtain the average loss amounts.
Wherein, the performance evaluation module inquires and analyzes vehicle equipment information in one day from the database equipment; taking the ith index factor of the jth driver as an example, the performance evaluation module queries and counts the number of event information of the ith index factor of the jth driver at 2015/01/01 from the database device
And has a total of INThe index factors can count the number of pointer factor event information of the jth driver
In this embodiment, step S202 selects a feature element, and analyzes the feature element by using the pointer factor and the driver, and then step S203 is performed to establish a hierarchical structure, in which the best solution is used as the first layer, the pointer factor is used as the second layer, and the driver is used as the third layer, and the schematic diagram of the hierarchical structure is shown in fig. 8.
In step S204, the pair-wise comparison matrix generation algorithm may count the values of the feature elements set at each level, and generate the pair-wise comparison matrix according to the ratio of the values.
In this embodiment, the index factors of the second layer may correspond to a comparison matrix, and the pair of comparison matrices may be generated in such a way that the pair of comparison matrices compares and analyzes the average loss amount of each index factor, and calculates the feature vector matrix of each level of feature elements by using a numerical analysis method;
wherein, the initialization of the index factor is as follows:
normalization of the index factor to the comparison matrix:
the feature element feature vector matrix of the second layer, namely the influence factor weight matrix of each index factor:
in this embodiment, each index factor of the third layer driver may correspond to a pair comparison matrix, the pair comparison matrix may be generated in the following manner, and in order to avoid the case that the denominator is 0, the number of the index factor event information may be increased by one, and the pair comparison matrix may compare and analyze the number of the index factor event information of each driver; in the following, the number of event messages generated by the occurrence of the first index factor for each driver is taken as an example:
driver initialization of the first index factor occurs as a pair comparison matrix:
the driver generates a normalized pair-wise comparison matrix of the first index factor:
the driver generates an influence factor weight matrix of a first index factor:
according to the calculation mode, the x index factors generated by each driver at the third layer can correspond to a pair comparison matrix, the pair comparison matrix can be generated in the following mode, and the x index factor event information quantity of each driver can be compared and analyzed through the pair comparison matrix;
wherein, the driver generates the initialized pairwise comparison matrix of the x index factors:
wherein the driver generates a normalized pairwise comparison matrix of the x index factors:
wherein, the driver generates the weight matrix of the influence factors of the x index factors:
by analogy, R can be generated at the third layerNIndividual pairwise comparison matrices, i.e.
And can establish the feature vector matrix W of the feature element of the third layer2：
After step S205, step S206 selects a solution, generates a score for each solution according to the feature vector matrix of each level feature element, and then screens out an optimal solution, where the optimal solution corresponds to an optimal score; in this embodiment, the score for each solution may be generated by matrix multiplication (as shown below), with the score for each solution being represented as its proportion, upsilon, of the average lost amount compared to the other drivers1Score (i.e., the score of the first driver), upsilon, representing solution 12Score representing solution 2 (i.e. second driver's score), …, upsilonDNRepresentative solution DNFraction of (i.e. D th)NThe score of the driver);
in this embodiment, the lower the average loss amount, the better, that is, the score of each solution is compared, and the solution with the lowest score is obtained, and the driver corresponding to the solution represents the best driver; suppose the lowest score is υ1Then the first driver is superior to the other drivers, and the first driver can obtain the least average loss amount under each index factor.
The sixth embodiment of the present invention is also a performance evaluation system and method for dangerous driving performance evaluation, and the sixth embodiment may be based on the fifth embodiment, in which the paired comparison matrix generation algorithm in the performance evaluation method (i.e., the performance evaluation algorithm executed by the performance evaluation module) is based on the above embodiment, but the fuzzy attribution function is used to calculate the value of the feature element set at each level, and the paired comparison matrix is generated according to the value.
In this embodiment, the index factor of the second layer (i.e., the vehicle device) corresponds to a pair of comparison matrices, the pair of comparison matrices may be generated by using a fuzzy attribution function, the fuzzy attribution function is a modified S-type function (e.g., a modified Sigmoid function), the modified S-type function may generate S-type by subtracting a modified reference value from the input value to be equal to 0, and the comparison and analysis of the average loss amount of the pointer factors of each level are performed by using the pair of comparison matrices, and then, a normalized pair comparison matrix of the vehicle model and a feature element feature vector matrix of the second layer are calculated respectively;
wherein, the initialization of the vehicle model is a pairwise comparison matrix:
in this embodiment, each driver in each index factor of the third layer may correspond to a comparison matrix, which may be generated by the fuzzy membership function method as described above, i.e. a modified sigmoid function,
calculating a normalized paired comparison matrix of the xth index factor of the driver and a feature element feature vector matrix of a third layer by using the initialized paired comparison matrix of the xth index factor of the driver:
it should be understood that the detailed description and specific examples, while indicating the possible embodiments of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention, which is to be construed as limiting the equivalent embodiments or modifications without departing from the spirit of the present invention.
In summary, the present invention is an innovation in technical idea, has many functions which are not achieved by the prior art, and fully meets the legal invention patent essentials of novelty and progress, and accordingly, the present invention is made by the following patent applications.
Claims (16)
1. A performance evaluation system, comprising:
the vehicle equipment is used for collecting the vehicle equipment information of energy consumption information, azimuth information, concentration information and positioning information of each driver in real time when the drivers drive;
the data analysis server equipment receives the vehicle equipment information from each vehicle equipment, calculates the performance of each driver during driving through a performance evaluation algorithm and ranks the performance of the plurality of drivers; and
a database device linked with the data analysis server device for storing the vehicle device information of each vehicle device and the performance of each driver and the ranking of the performance of the plurality of drivers;
wherein each of the vehicle devices further includes an energy detection device, the energy detection device detects the energy consumption information of the vehicle installed in each of the vehicle devices, including oil amount, electricity amount, or natural gas amount, the energy consumption information is also included in the vehicle device information and transmitted to the data analysis server device, wherein the data analysis server device is further configured to:
collecting energy consumption information for each vehicle model of the plurality of vehicle devices;
establishing a first initialized pairwise comparison matrix based on the energy consumption information of each vehicle model;
establishing a first normalized pairwise comparison matrix based on the first initialized pairwise comparison matrix;
a first eigenvector matrix established for the comparison matrix based on the first normalization;
establishing a second initialized pairwise comparison matrix of the driver of each vehicle model based on the energy consumption information of each vehicle model;
establishing a second normalized pairwise comparison matrix for the driver of each of the vehicle models based on the second initialized pairwise comparison matrix for each of the vehicle models;
establishing an influencing factor weight matrix of the driver of each vehicle model based on the second normalized pairing comparison matrix of each vehicle model;
establishing a second eigenvector matrix of the vehicle models according to the weight of the influence factor of each vehicle model;
multiplying the first eigenvector matrix and the second eigenvector matrix to obtain the score of each driver as the performance of each driver.
2. The performance evaluation system of claim 1, wherein each of said vehicle devices comprises a driver identity recognition device, a positioning module, an middleware module, a performance evaluation module, and a communication module;
the positioning module supports a global positioning system or a wireless network signal positioning function, each vehicle device obtains position information and vehicle speed information in the vehicle device information through the positioning module to which the vehicle device belongs, and the vehicle speed information is used for judging event information of an overspeed event, a rapid acceleration event and a rapid braking event;
the communication module supports wireless network transmission to establish communication between the vehicle equipment and the data analysis server equipment;
the middleware module supports at least one transmission protocol of a hypertext transmission protocol, a message sequence telemetry transmission or a limited application protocol, and the vehicle equipment interfaces with the data analysis server equipment through the middleware module and the communication module so as to transmit the vehicle equipment information to the data analysis server equipment;
the performance evaluation module calculates the performance of each driver when driving through the performance evaluation algorithm and can sequence the performance of the plurality of drivers; and
the driver identity recognition device is used for reading the identity recognition certificate of each driver to obtain a driver number, and the driver number is also contained in the vehicle equipment information and is transmitted to the data analysis server equipment.
3. The performance evaluation system of claim 2, wherein each of the vehicle devices further comprises an azimuth sensor for detecting the azimuth information of each of the vehicle devices in driving, the azimuth information being used to determine event information of a sharp turn event, and the event information being included in the vehicle device information and transmitted to the data analysis server device.
4. The performance evaluation system of claim 2, wherein each of the vehicle devices further comprises a concentration detection device, the concentration detection device is a wearable brain wave detection device for being worn on the head of each of the drivers to detect the brain waves of each of the drivers to obtain the concentration information, the concentration information is used to determine event information of an absentism event, and the event information is transmitted to the data analysis server device to be included in the vehicle device information.
5. The performance evaluation system of claim 2, wherein each of the vehicle devices further comprises a preceding vehicle distance detection device and a lane deviation detection device, the preceding vehicle distance detection device detects preceding vehicle distance information between each of the vehicle devices and a preceding vehicle when the vehicle device is traveling, the lane deviation detection device detects deviation lane information that each of the vehicle devices does not turn on a turn signal when the vehicle device is traveling, the preceding vehicle distance information and the deviation lane information are respectively used for determining event information of an event that a safety distance is not kept or a lane deviation is not kept, and the event information is included in the vehicle device information and transmitted to the data analysis server device.
6. The performance evaluation system of claim 2, wherein each of the vehicle devices further comprises an on-board diagnostic system and a temperature sensor, the on-board diagnostic system detects vehicle status information of each of the vehicle devices in which the vehicle is installed, and the temperature sensor detects temperature information of a refrigerator of each of the vehicle devices in which the vehicle status information and the temperature information are to be included in the vehicle device information and transmitted to the data analysis server device.
7. The performance evaluation system of claim 6, wherein the database device stores a schedule data table for recording station information and scheduled arrival time information of each of the vehicle devices, and the data analysis server device generates a door closing abnormal event, a temperature abnormal event, a pre-cooling insufficient event or an arrival time abnormal event according to the vehicle state information and the temperature information in the vehicle device information after receiving the vehicle device information.
8. A performance evaluation method is suitable for a performance evaluation system, the performance evaluation system comprises a data analysis server device, the data analysis server device receives vehicle device information from each vehicle device in a plurality of vehicle devices, calculates the performance of each driver when driving through a performance evaluation algorithm and sorts the performance of a plurality of drivers, the data analysis server device at least comprises the following steps:
collecting and analyzing vehicle equipment information, reporting the vehicle equipment information to the data analysis server equipment by a plurality of vehicle equipment arranged on a vehicle, analyzing the vehicle equipment information of each vehicle equipment in a time interval by the data analysis server equipment, and storing the vehicle equipment information to a database equipment;
selecting at least one characteristic element, and selecting at least one characteristic element from the vehicle equipment number, the vehicle model and the characteristic elements of each driver from the vehicle equipment information to carry out performance evaluation;
constructing a hierarchical structure, and setting an upper-layer and a lower-layer associated structure of each feature element according to each selected feature element;
executing a comparison matrix generation algorithm to generate a comparison matrix according to each characteristic element set by each level;
calculating characteristic values and characteristic vectors, and calculating a characteristic vector matrix of characteristic elements in each level by using numerical analysis; and
selecting a solution, generating scores of a plurality of solutions according to the eigenvector matrix of each characteristic element in each level, and screening out an optimal solution;
wherein each of the vehicle devices further includes an energy detection device, the energy detection device detects the energy consumption information of the vehicle installed in each of the vehicle devices, including oil amount, electricity amount, or natural gas amount, the energy consumption information is also included in the vehicle device information and transmitted to the data analysis server device, wherein the method further includes:
collecting energy consumption information for each vehicle model of the plurality of vehicle devices;
establishing a first initialized pairwise comparison matrix based on the energy consumption information of each vehicle model;
establishing a first normalized pairwise comparison matrix based on the first initialized pairwise comparison matrix;
a first eigenvector matrix established for the comparison matrix based on the first normalization;
establishing a second initialized pairwise comparison matrix of the driver of each vehicle model based on the energy consumption information of each vehicle model;
establishing a second normalized pairwise comparison matrix for the driver of each of the vehicle models based on the second initialized pairwise comparison matrix for each of the vehicle models;
establishing an influencing factor weight matrix of the driver of each vehicle model based on the second normalized pairing comparison matrix of each vehicle model;
establishing a second eigenvector matrix of the vehicle models according to the weight of the influence factor of each vehicle model;
multiplying the first eigenvector matrix and the second eigenvector matrix to obtain the score of each driver as the performance of each driver.
9. The performance evaluation method according to claim 8, wherein the pair-wise comparison matrix generation algorithm system counts values of the feature elements set for each hierarchical structure and generates the pair-wise comparison matrix in proportion to the values.
10. The performance assessment method of claim 8, wherein the pair-wise comparison matrix generation algorithm calculates the value of each feature element configured for each hierarchical structure by using a distance function or a similarity function, and generates the pair-wise comparison matrix according to the value.
11. The performance assessment method of claim 8, wherein the pair-wise comparison matrix generation algorithm calculates the value of each feature element configured for each hierarchical structure using a fuzzy membership function and generates the pair-wise comparison matrix according to the value.
12. The performance evaluation method as claimed in claim 8, wherein the selected solution of the data analysis server device, after generating a score for each of the solutions, screens out the best solution according to a score-best one among the solutions.
13. The performance assessment method of claim 8, wherein the selected solutions of the data analysis server device, after generating a score for each of the solutions, uses decision tree information profitability to screen out the best solution.
14. The performance evaluation method of claim 8, wherein in selecting each of the characteristic elements, energy consumption information of each of the vehicle equipments is further selected so that the optimal solution evaluates energy saving driving performance.
15. The performance evaluation method according to claim 8, wherein at least one of event information of an overspeed event, or a rapid acceleration event, a rapid braking event, a sharp turning event, a absenteeism event, a non-maintained safety distance event, or a lane deviation event of each of the vehicle equipments is further selected in selecting each of the characteristic elements so that the optimal solution evaluates dangerous driving performance.
16. The performance evaluation method according to claim 8, wherein at least one of event information of a door closing abnormal event, a temperature abnormal event, a precooling insufficient event or an arrival time abnormal event of each of the vehicle equipments is further selected in selecting each of the characteristic elements so that the optimal solution evaluates the performance of the logistic.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW105141530 | 2016-12-15 | ||
| TW105141530A TWI604324B (en) | 2016-12-15 | 2016-12-15 | Performance evaluation system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107633339A CN107633339A (en) | 2018-01-26 |
| CN107633339B true CN107633339B (en) | 2021-05-28 |
Family
ID=61023396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710176941.4A Active CN107633339B (en) | 2016-12-15 | 2017-03-22 | Performance evaluation system and method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107633339B (en) |
| TW (1) | TWI604324B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI658954B (en) * | 2018-03-09 | 2019-05-11 | 世環國際股份有限公司 | Method and module for determining improper vehicle lane departure, and system thereof |
| CN110909966A (en) * | 2018-09-14 | 2020-03-24 | 北京京东尚科信息技术有限公司 | Efficiency evaluation method and efficiency evaluation system |
| TWI712523B (en) * | 2019-08-23 | 2020-12-11 | 啓碁科技股份有限公司 | Method and system for predicting dangerous vehicles |
| TWI722647B (en) * | 2019-11-11 | 2021-03-21 | 中華電信股份有限公司 | System for driver estimation and method thereof |
| CN112182081A (en) * | 2020-09-23 | 2021-01-05 | 金现代信息产业股份有限公司 | Commuting passenger vehicle performance analysis method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102829980A (en) * | 2012-03-29 | 2012-12-19 | 中国科学院自动化研究所 | Intelligent degree evaluation method of intelligent vehicle |
| CN104750753A (en) * | 2013-12-31 | 2015-07-01 | 中国移动通信集团公司 | Method and equipment for generating driving behavior reports |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6604084B1 (en) * | 1998-05-08 | 2003-08-05 | E-Talk Corporation | System and method for generating an evaluation in a performance evaluation system |
| JP4002046B2 (en) * | 2000-01-20 | 2007-10-31 | 株式会社小糸製作所 | Method for evaluating reflecting performance of reflecting mirror, evaluation system for evaluating reflecting performance of reflecting mirror, and computer-readable recording medium storing a program for causing a computer to execute reflecting performance evaluation of reflecting mirror |
| US7326060B2 (en) * | 2002-05-09 | 2008-02-05 | Barry Seiller | Visual performance evaluation and training system |
| TW200811742A (en) * | 2006-08-25 | 2008-03-01 | Folion Financial Technology Co Ltd | Appraisal system for asset allocation and investment portfolio performance |
| TW200945224A (en) * | 2008-04-30 | 2009-11-01 | Univ Ching Yun | Performance evaluation system for enterprise resource planning adopting fuzzy theory and its performance evaluation method |
| TWI426457B (en) * | 2011-01-21 | 2014-02-11 | Chi Mei Foundation Hospital | Automated performance evaluation methods and systems |
| CN103247091B (en) * | 2012-02-07 | 2016-01-20 | 厦门金龙联合汽车工业有限公司 | A kind of driving evaluation system and method |
| TWI550531B (en) * | 2013-01-25 | 2016-09-21 | Univ Southern Taiwan Sci & Tec | Enterprise resource planning performance evaluation system and method |
| TWI534726B (en) * | 2015-02-25 | 2016-05-21 | wen-yuan Cai | Performance evaluation management system |
-
2016
- 2016-12-15 TW TW105141530A patent/TWI604324B/en active
-
2017
- 2017-03-22 CN CN201710176941.4A patent/CN107633339B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102829980A (en) * | 2012-03-29 | 2012-12-19 | 中国科学院自动化研究所 | Intelligent degree evaluation method of intelligent vehicle |
| CN104750753A (en) * | 2013-12-31 | 2015-07-01 | 中国移动通信集团公司 | Method and equipment for generating driving behavior reports |
Also Published As
| Publication number | Publication date |
|---|---|
| TW201824024A (en) | 2018-07-01 |
| TWI604324B (en) | 2017-11-01 |
| CN107633339A (en) | 2018-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107633339B (en) | Performance evaluation system and method | |
| US11842404B2 (en) | Enhancement using analytics based on vehicle kinematic data | |
| US11514276B2 (en) | System and method for detecting and classifying recurrent stops of a vehicle fleet | |
| US20210049548A1 (en) | Multi-phase consolidation optimization tool | |
| US11530961B2 (en) | Vehicle vocation system | |
| CN110807930B (en) | Dangerous vehicle early warning method and device | |
| CN102132132B (en) | Local decision policies about the sharing of sensed data that enhance privacy and lower communication costs for services that aggregate data from personal devices | |
| US11407410B2 (en) | Method and system for estimating an accident risk of an autonomous vehicle | |
| CN110268454B (en) | Determining a customized safe speed for a vehicle | |
| US20130041521A1 (en) | Vehicle monitoring system with automatic driver identification | |
| CN108475358A (en) | Method and system for the stroke performance for evaluating driver | |
| EP3578433B1 (en) | Method for estimating an accident risk of an autonomous vehicle | |
| CN115239127B (en) | Ecological vulnerability assessment method, computer device, storage medium, and verification method | |
| CN108431837A (en) | Method and system for the stroke performance for evaluating driver | |
| CN107918826B (en) | Driver evaluation and scheduling method for driving environment perception | |
| US10061833B2 (en) | Data insight and intuition system for tank storage | |
| Akter | Truck activity pattern classification using anonymous mobile sensor data | |
| EP3819838A1 (en) | Method for classifying trade industry of a vehicle | |
| US20100262366A1 (en) | System and method for distance estimation | |
| Kryzhanovsky et al. | Information, Modeling and Measurement of Uncertainty in the Vehicle | |
| Yang et al. | Anomaly Detection and Performance Visualization of Truck Parking Information and Management Systems | |
| CN118014271A (en) | Intelligent truck dispatching terminal based on Linux system | |
| Nicheporchuk et al. | Integrated emergency monitoring system in Krasnoyarsk region | |
| CN117216615A (en) | Method, system, medium and electronic equipment for identifying channeling behavior | |
| CN116665342A (en) | New energy automobile driving behavior analysis method, system and equipment |
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 |