TW201824024A - Performance evaluation system and method - Google Patents

Abstract

The invention relates to a performance evaluation system and method, mainly through a data analysis server device, receiving vehicle equipment information from vehicle equipment information of a plurality of vehicle equipments, including energy consumption or risk factors, etc. The performance evaluation algorithm calculates the performance represented by the driver's driving behavior and can better sort the performance of all drivers.

Description

   Performance evaluation system and method   

The invention relates to a performance evaluation system and method, in particular to collecting energy consumption information or risk factors of multiple vehicle equipment and user equipment, and comprehensively considering to understand the impact of various driving behaviors on performance.

Fuel oil cost is one of the major cost factors for the automobile freight industry, which needs to be paid special attention. In addition, the illegal driving behavior of drivers in the freight industry not only affects the company's reputation, but also has a considerable impact on operations. In view of this, if we can develop a technology that can understand the performance of the freight industry in responding to different drivers ’energy consumption and driving violations, it will be able to effectively respond to this problem.

In the prior art, although there are technologies that use historical data of vehicle type, fuel gauge voltage, and driving speed to obtain and correct fuel value, there are also technologies that detect battery voltage and calculate vehicle fuel consumption, or diagnose fuel tanks. Techniques for returning fuel quantity data, etc .; however, each of them lacks effective feedback methods, or cannot comprehensively estimate the fuel cost required by the freight industry through factors such as road network traffic conditions, driver differences, and so on. It has its shortcomings and needs to be improved.

In the prior art, there are systems and methods for uploading the work status of employees to a cloud server through a work record unit and a target analysis request unit included in a plurality of mobile devices, and then comparing the work status with the work target to analyze the target completion ratio. However, although this technology can calculate the proportion of work completed and understand the work correlation between employees, it cannot compare the performance differences between employees, or find out the offending employees to the company's managers, which obviously has its shortcomings. , Still to be improved.

The invention collects energy consumption information and violation information through a plurality of vehicle equipment and user equipment, and comprehensively calculates various driving behaviors and ranks performance according to various factors, which is an extremely effective performance estimation technology.

In order to solve the impact of various factors on driving performance that cannot be considered in the prior art, the present invention provides a performance evaluation system that includes at least a plurality of vehicle equipment, a data analysis server equipment, and a database equipment.

Wherein, each of the vehicle equipments of the present invention can transmit vehicle equipment information to the data analysis server equipment, and the data analysis server equipment can store the transmitted data to the database equipment, and then be calculated by the data analysis server equipment The driving performance of each vehicle equipment is ranked.

Each of the vehicle equipment includes at least a driver identification device, a positioning module, an intermediary software module, and a communication module. Among them, the communication module can support wireless network transmission to establish each of the Communication between vehicle equipment and the data analysis server equipment.

The positioning module supports positioning methods such as Global Positioning System (GPS) or wireless network signal positioning, so that each vehicle device can obtain position information and speed information through this module.

The intermediary software module can support at least one of transmission protocols such as HyperText Transfer Protocol (HTTP), Message Queuing Telemetry Transport (MQTT), or Constrained Application Protocol (CoAP). , So that each of the vehicle equipment can interface with the data analysis server device through its own intermediary software module and then the communication module to transmit vehicle equipment information to the data analysis server device.

The driver identification device can read the driver's identification certificate to obtain the driver's number.

So far, the vehicle equipment information transmitted by each vehicle equipment through the intermediary software module and the communication module includes vehicle number, vehicle model, driver number, time information, location information, speed information, and the like.

Each of the vehicle equipment may optionally further include an energy detection device, and the energy detection device may detect energy consumption information of the vehicle equipment, and the energy consumption information may be fuel consumption information, power consumption information, or natural gas information, etc. The energy consumption information is also included in the vehicle equipment information and transmitted to the data analysis server equipment.

Each of the vehicle equipment may optionally further include an azimuth sensor, the azimuth sensor is used to detect azimuth information of each vehicle equipment during driving, and the azimuth information is used to judge an overspeed event, Incident information such as a sudden acceleration event, a sudden braking event, or a sharp turn event, and the event information will be included in the vehicle equipment information and transmitted to the data analysis server equipment.

Each of the vehicle equipment may optionally further include a concentration detection device, which is a wear-through brain wave detection device that is worn on the driver's head to detect the driver Brainwave to obtain concentration information. The concentration information is used to determine event information such as the God event, and the event information will be included in the vehicle equipment information and transmitted to the data analysis server device.

Each of the vehicle equipment may optionally further include a front vehicle distance detection device and a lane shift detection device. The front vehicle distance detection device detects the forward distance between each vehicle device and the vehicle in front when driving. Vehicle distance information, and the lane departure detection device detects deviation lane information of each vehicle device when the vehicle is not turned on, and the preceding vehicle distance information and the deviation lane information are used to determine that a safe distance has not been maintained. Event information such as an event or a lane shift event, and the event information will be included in the vehicle equipment information and transmitted to the data analysis server equipment.

Each of the vehicle equipment may optionally further include an on-board diagnostic system and a temperature sensor. The on-board diagnostic system detects vehicle state information of the vehicle provided by each of the vehicle equipment, and the temperature sensor detects Measure the temperature information of the refrigerator of each vehicle equipment set vehicle, vehicle state information and temperature information will be included in the vehicle equipment information and transmitted to the data analysis server equipment.

So far, the vehicle equipment information transmitted by each vehicle equipment through the intermediary software module and the communication module includes vehicle number, vehicle model, driver number, time information, location information, speed information, energy consumption information, event information, vehicle Status information and temperature information, etc., among which, the event information may be an overspeed event, a sharp acceleration event, a sharp braking event, a sharp turn event, a godsend event, an unsafe distance event, or a lane shift event.

Wherein, the database device of the present invention can store a schedule data table, the schedule data table is used to record the station information and scheduled arrival time information of each vehicle equipment receipt and delivery, when the data analysis server After the device receives the vehicle equipment information, it can generate door abnormal events, temperature abnormal events, insufficient pre-cooling events, or abnormal arrival time events based on the vehicle status information and temperature information in the vehicle equipment information. Latitude and longitude coordinates.

The data analysis server device of the present invention receives vehicle equipment information from each of the vehicle equipment, calculates a driver's performance while driving through a performance evaluation algorithm, and enables the driver's performance to be ranked.

Wherein, the performance evaluation algorithm executed by the data analysis server equipment corresponds to the steps of the performance evaluation method of the present invention, which includes at least the following steps: 1. Collect and analyze information of each vehicle equipment, and Each vehicle equipment reports vehicle equipment information to the data analysis server equipment, and the data analysis server equipment analyzes the vehicle equipment information of each vehicle equipment in a time interval, and stores the vehicle equipment information to a database equipment; 2 . Select at least one characteristic element, obtain vehicle equipment number, vehicle model, driver and other characteristic elements from the vehicle equipment information to select at least one characteristic element for performance evaluation; 3. Construct a hierarchical structure and set each according to each selected characteristic element The correlation structure of the upper and lower layers of the feature element; 4. Execute a pairwise comparison matrix generation algorithm to generate a pairwise comparison matrix for each feature element set at each level; 5. Calculate the eigenvalue and eigenvector, use Numerical analysis calculates a feature vector matrix of feature elements in each level; 6. Choose to solve After the case, to generate a plurality of scores by the solution of the eigenvector matrix wherein each element of each hierarchy, and then selected a best solution.

In the performance evaluation method of the present invention, the pairwise comparison matrix generation algorithm can be achieved in the following ways:

1. Count the value of each characteristic feature set in each hierarchy, and generate a pairwise comparison matrix according to the ratio of the values.

2. The distance function or the similarity function is used to calculate the value of each characteristic element set in each hierarchical structure, and a pairwise comparison matrix is generated according to the value.

3. The pairwise comparison matrix generation algorithm uses a fuzzy attribution function to calculate the value of each of the feature elements set in each hierarchical structure, and generates a pairwise comparison matrix according to the value.

In addition, in the step of selecting a solution for the data analysis server device, after the score of each solution is generated, the best solution will be selected according to the best score in each solution, or the decision will be applied. Tree information monetization method to select the best solution.

In the performance evaluation method of the present invention, when selecting each of the characteristic elements, the energy consumption information of each vehicle equipment may be selected so that the best solution is to evaluate the performance of energy-saving driving; or, each vehicle is selected. Event information such as overspeed events, rapid acceleration events, sudden braking events, sharp cornering events, stun events, unsafe distance events, or lane shift events, so that the best solution is to evaluate dangerous driving performance; or Select the event information such as abnormal door closing events, temperature abnormal events, insufficient pre-cooling events, or abnormal arrival time events of each vehicle equipment, so that the best solution is to evaluate the performance of logistics professionals.

When comparing the performance evaluation system and method of the present invention with other conventional technologies, it has the following advantages:

1. The driver's information and vehicle information are reported by the vehicle equipment, and the performance and ranking of the driver are calculated by the data analysis server equipment, which can automatically generate performance evaluation results.

2. The performance evaluation method proposed by the present invention, combined with the fuzzy attribution function to generate a pairwise comparison matrix, can strengthen the analysis of differences between data and avoid infinite or meaningless values.

3. The performance evaluation method proposed by the present invention combines the distance function or the similarity function to generate a pairwise comparison matrix, which can find the data with the greatest degree of difference.

4. The performance evaluation method proposed by the present invention can be applied to the estimation of energy consumption, to consider the amount of energy consumed by different drivers, different vehicle equipment and different driving behaviors, and select the solution with the lowest energy consumption to provide to the enterprise Manager's reference.

5. The performance evaluation method proposed by the present invention can be applied to the evaluation of dangerous driving. It can consider the degree of risk generated by different drivers, different vehicle equipment and different driving behaviors, and select the solution with the lowest degree of risk to provide to the enterprise. Manager's reference.

6. The performance evaluation method proposed by the present invention can be applied to the evaluation of logistics professionals, which can consider the degree of violations caused by different drivers, different vehicle equipment and different driving behaviors, and select the solution with the lowest degree of violation to provide to the enterprise. Manager's reference.

1‧‧‧Vehicle equipment

100‧‧‧ communication module

101‧‧‧Intermediary software module

102‧‧‧ Positioning Module

103‧‧‧Driver identification device

104‧‧‧energy detection device

105‧‧‧Azimuth sensor

106‧‧‧ Attention detection equipment

107‧‧‧Front vehicle distance detection equipment

108‧‧‧Lane shift detection equipment

109‧‧‧Onboard diagnostic system

110‧‧‧Temperature sensor

2‧‧‧Data Analysis Server Equipment

20‧‧‧Communication Module

22‧‧‧ Intermediate Software Module

24‧‧‧Performance Evaluation Module

3‧‧‧Database Equipment

30‧‧‧Communication Module

32‧‧‧ Computing Module

34‧‧‧Storage Module

4‧‧‧ External Information Equipment

S201 ~ S206‧‧‧step flow

FIG. 1 is a system architecture diagram of an embodiment of a performance evaluation system of the present invention.

FIG. 2 is a flowchart of steps in an embodiment of a performance evaluation method of the present invention.

FIG. 3 is a schematic diagram of a hierarchical structure of an embodiment of a performance evaluation method of the present invention.

FIG. 4 is a schematic diagram of a hierarchical structure of an embodiment of a performance evaluation method of the present invention.

FIG. 5 is a system architecture diagram of an embodiment of the performance evaluation system of the present invention.

FIG. 6 is a schematic diagram of a hierarchical structure of an embodiment of a performance evaluation method of the present invention.

FIG. 7 is a system architecture diagram of an embodiment of the performance evaluation system of the present invention.

FIG. 8 is a schematic diagram of a hierarchical structure of an embodiment of a performance evaluation method of the present invention.

In order to make the objectives, technical solutions, and advantages of the present invention clearer, 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 here are only used to explain the present invention, but It is not intended to limit the invention.

Please refer to FIG. 1, which is a system architecture diagram of a first embodiment of the performance evaluation system of the present invention, wherein the system includes a plurality of vehicle equipment 1 (to avoid complicated drawings, only one of which is shown in the figure), a data analysis server Device device 2 and a database device 3.

The vehicle equipment 1 can transmit information about the vehicle equipment on which the vehicle is installed to the data analysis server device 2, and the data analysis server device 2 can store data to the database device 3, and the data analysis server device 2 executes the invention Performance evaluation algorithms to calculate the performance and ranking of each driver.

In this embodiment, the vehicle device 1 includes a communication module 100, an intermediary software module 101, a positioning module 102, a driver identification device 103, and an energy detection device 104. Among them, the communication module 100 can support 4G (Long Term Evolution, LTE) communication technology, so that the vehicle device 1 can connect to the 4G network through the communication module 100 and establish communication with the data analysis server device 2; the intermediary software module The group 101 can support Hypertext Transfer Protocol and Representational State Transfer (REST). The vehicle device 1 can call the application program interfaces (APIs) of the data analysis server device 2 through the intermediary software module 101. And transmit vehicle equipment information to the data analysis server device 2 in a periodic or aperiodic manner. The vehicle equipment information may include vehicle number, vehicle model, driver number, time information, location information or speed information, etc. ; And the positioning module 102 can support a global positioning system, so that the vehicle equipment 1 obtains position information and vehicle speed data via satellite signals The driver identification device 103 is a radio frequency identification (RFID) card reader, and the driver ’s identification document owned by the driver is an RFID tag, which can be stored. A driver's number, and when approaching the driver's identification device 103, the driver's identification device 103 can obtain the driver's number; the energy detection device 104 is a fuel detection device, which can detect the fuel tank of the vehicle To obtain the energy consumption information by calculating the difference in gasoline quantity, and provide the energy consumption information to the vehicle equipment 1, so the vehicle equipment information transmitted by the vehicle equipment 1 includes the vehicle number, vehicle model, driver number, time information, location Information, speed information, and energy consumption information.

30 seconds and the vehicle device transmitting information to a data analysis server apparatus 2, in this embodiment in the following table, the total equipment vehicles C _N, T _N kinds of vehicle models, D _N-bit driver, the vehicle device may be every 1 An example is shown in the example; for example, the first driver drives the vehicle with the first vehicle number on 2015/01/01, and the vehicle model of the vehicle equipment set in the vehicle is the first vehicle model, and the vehicle equipment uses the driver identification device Obtain the driver ’s identity as the first driver ’s number, and the vehicle equipment may obtain the location information of the vehicle equipment (that is, longitude 102.5423383 degrees and latitude 24.09490167 degrees) and vehicle speed information (real-time) via its positioning module at 06:00. (Speed 44 km / h), and the vehicle equipment consumes 0.037 liters of fuel within 30 seconds (2015/01/01 05: 59: 30-2015 / 01/01 06: 00: 00) obtained by the energy detection device (Ie, energy consumption information), and then call the REST APIs of the data analysis server through the mediation software module to transmit vehicle equipment information to the data analysis server.

The following is Table 1:

Please continue to refer to FIG. 1, wherein the data analysis server device 2 includes a communication module 20, an intermediary software module 22, and a performance evaluation module 24; in this embodiment, the data analysis server device 2 can support Linux operating system, Microsoft Windows operating system, etc., and a network service server can be built on the operating system to which it belongs; the communication module 20 can support wired network transmission to establish vehicle equipment 1, database equipment 3, and data analysis The communication between the server devices 2; and the intermediary software module 22 is implemented using the Tomcat web service server to build a plurality of REST APIs for the vehicle device 1 to interface with, and it can receive the vehicle via the hypertext transfer protocol Vehicle equipment information transmitted by equipment 1, and the received vehicle equipment information and energy consumption information are stored in database equipment 3, where the vehicle equipment information may include vehicle number, vehicle model, driver number, time information, location information, Vehicle speed information and energy consumption information; and the performance evaluation module 24 performs a performance evaluation algorithm to collect vehicle settings transmitted by each vehicle device. Information and analysis of the amount of energy they consume drivers to calculate the energy consumption of each driver's performance and ranking.

Please continue to refer 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 uses Microsoft Structured Query Language (Structural (Query Language, SQL) server, MySQL, PostgreSQL, Oracle database server, MongoDB server, HBase server, etc .; and the communication module 30 can support wired network transmission to create database equipment 3 and The communication between 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; and the storage module 34 is connected with The computing module 32 interfaces to provide operations such as adding, modifying, deleting, and querying. The storage module 34 can store vehicle equipment information (as shown in Table 1 above).

Please refer to FIG. 2 again, which is a flowchart of the steps of the performance evaluation method of the present invention. The performance evaluation method is the performance evaluation algorithm performed by the performance evaluation module in the data analysis server device. The steps include at least: 1. Steps S201 collects and analyzes vehicle equipment information. Each vehicle equipment reports vehicle equipment information to the data analysis server equipment, and then the data analysis server equipment analyzes vehicle equipment information, especially vehicle equipment information within a time interval. And store the vehicle equipment information to the database equipment; 2. Step S202 selects the characteristic elements, including the vehicle equipment, the vehicle model, and the driver, etc., and can select multiple characteristic elements for performance evaluation; 3. Step S203 construction Hierarchical structure, set the upper and lower correlation structure according to the selected feature elements; 4. Step S204 generates a pairwise comparison matrix algorithm, generates a pairwise comparison matrix according to the feature elements set at each level; 5. Step S205 calculates the eigenvalues and features Vector, using numerical analysis to calculate the feature vector matrix of feature elements at each level; 6. Step S206 Selecting a solution can generate a score for each solution according to the feature vector matrix of each level of feature elements, and then select the best solution corresponding to an optimal score.

According to the above performance evaluation method, in this embodiment, the collection and analysis of vehicle equipment information in step S201 is to query and analyze the vehicle equipment information within a time interval by the performance evaluation module from the database equipment. The time interval is here The example is one year; taking the i-th vehicle model as an example, the performance evaluation module queries the database equipment and statistics the energy consumption information of the i-th vehicle model throughout 2015 . Energy In this embodiment, a total of T _N kinds of vehicle models, the statistics of all types of vehicles consume information

Step S202 selects the characteristic elements to analyze using the vehicle model and the driver's two characteristic elements, and then proceeds to step S203 to establish a hierarchical structure, with the optimal solution as the first layer, the vehicle model as the second layer, and the driver as the second layer. Three levels, the schematic diagram of the hierarchy is shown in Figure 3.

Step S204 generates a pairwise comparison matrix algorithm. The system calculates 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 models of the second layer may correspond to a pairwise comparison matrix. The pairwise comparison matrix may be generated in the following manner. The pairwise comparison matrix may be used to compare and analyze the energy consumption of each vehicle model, and Use the numerical analysis method to calculate the feature vector matrix of the feature elements in the hierarchy; the vehicle model is initialized into a pair comparison matrix: Normalized pairwise comparison matrix for vehicle models: The feature vector matrix of the second layer of feature elements is the weighting factor matrix of each vehicle model:

In this embodiment, the drivers of each vehicle model on the third layer can correspond to a pairwise comparison matrix. The pairwise comparison matrix can be generated in the following manner, and the driver of each vehicle model can be performed by the pairwise comparison matrix. Comparison and analysis of energy consumption; if the energy consumption generated by each driver driving the first vehicle model is taken as an example: the driver of the first vehicle model initializes the pairwise comparison matrix: The normalized pairwise comparison matrix for drivers of the first vehicle model: Weighting matrix of influencing factors for each driver of the first vehicle model:

According to the above calculation method, the driver of the x- th vehicle model on the third layer can correspond to a pairwise comparison matrix. The pairwise comparison matrix can be generated in the following manner. The pairwise comparison matrix can be used to drive each vehicle model. Comparison and Analysis of Human Energy Consumption; Initialized Pairwise Comparison Matrix for Drivers of Vehicle Type x : Normalized pairwise comparison matrix for drivers of vehicle type x : Weighting matrix of influencing factors for each driver of vehicle type x :

By analogy, T _N pairwise comparison matrices can be generated in the third layer, that is, W _2,1 , W _2,2 , ..., , And the feature vector matrix W ₂ of the feature elements of the third layer can be established accordingly:

Following on, after calculating the eigenvalues and eigenvectors in step S205. That is, it proceeds to step S206 to select a solution, and generates a score of each solution according to the feature vector matrix of each level of features, and then selects the best solution. In this embodiment, the score of each solution is multiplied by a matrix. Method (as shown in the following formula), the score of each solution represents the energy consumption ratio of this solution compared to other drivers, and υ ₁ represents the score of solution 1 (that is, the score of the first driver) , Υ ₂ represents the score of solution 2 (that is, the score of the second driver), ..., The score representing the solution D _N (ie the score of the D _N driver);

In this embodiment, the lower the energy consumption, the better, so compare the scores of each solution to get the lowest score solution, then the driver corresponding to this solution is the best driver; that is, assuming the lowest A score of υ ₁ indicates that the first driver is superior to other drivers. The first driver will get the least energy consumption when driving various vehicle models.

According to the above calculation method, it is assumed that T _N is 3, the energy consumption amount of the first vehicle model is 1.011 times the energy consumption amount of the second vehicle model, and the energy consumption amount of the first vehicle model is that of the third vehicle model. 1.022 times the amount of energy consumption, the vehicle model is initialized into a pair comparison matrix, as shown in the example in Table 2 below: Then calculate the normalized pairwise comparison matrix of the vehicle model based on the initialized pairwise comparison matrix of the vehicle model, as shown in the example in Table 3 below: Then calculate the feature vector matrix of the feature elements in the second layer according to the normalized pairwise comparison matrix of the vehicle model, as shown in the example in Table 4 below:

According to the above calculation method, assuming D _N is 3, the amount of energy consumed by the first driver driving the first vehicle model is 0.981 times the amount of energy consumed by the second driver driving the first vehicle model, and the first driver is driving The amount of energy consumed by a person driving the first vehicle model is 0.972 times the amount of energy consumed by a third driver driving the first vehicle model. The driver of the first vehicle model is initialized into a pair comparison matrix, as shown in the example in Table 5 below. As shown: Based on the pairwise comparison matrix initialized by the driver of the first vehicle model, the normalized pairwise comparison matrix of the driver of the first vehicle model is calculated, as shown in the example in Table 6 below: Then, based on the normalized pairwise comparison matrix of the driver of the first vehicle model, the influence factor weight matrix of the driver of the first vehicle model is calculated, as shown in the example in Table 7 below:

According to the above calculation method, it is assumed that the amount of energy consumed by the first driver driving the second vehicle model is 0.941 times the amount of energy consumed by the second driver driving the second vehicle model, and the first driver driving the second vehicle model. The vehicle model consumes 0.974 times the amount of energy consumed by the third driver driving the second vehicle model. The driver of the second vehicle model initializes the pairwise comparison matrix, as shown in the example in Table 8 below: The normalized pairwise comparison matrix for the driver of the second vehicle model can be calculated based on the initialized pairwise comparison matrix for the driver of the second vehicle model, as shown in the example in Table 9 below: The influence factor weight matrix for each driver of the second vehicle model can be calculated based on the normalized pairwise comparison matrix of the driver of the second vehicle model, as shown in the example in Table 10 below:

According to the above calculation method, it is assumed that the amount of energy consumed by the first driver driving the third vehicle model is 0.998 times the amount of energy consumed by the second driver driving the third vehicle model, and the first driver driving the third vehicle model. The amount of energy consumed by a vehicle model is 0.999 times the amount of energy consumed by a third driver driving a third vehicle model. The driver of the third vehicle model initializes a pairwise comparison matrix, as shown in the example in Table 11 below: The normalized pairwise comparison matrix for the driver of the third vehicle model can be calculated based on the initialized pairwise comparison matrix for the driver of the third vehicle model, as shown in the example in Table 12 below: The weighting matrix of influencing factors for each driver of the third vehicle model can be calculated based on the normalized pairwise comparison matrix of the driver of the third vehicle model, as shown in the example in Table 13 below:

The feature layer feature vector matrix of the third layer combines 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 each driver of the third vehicle model. The human influence factor weight matrix is shown in the example in Table 14 below:

The scores of each solution can be obtained by matrix multiplication, that is, the results of the matrix multiplication in Table 4 and Table 14, the results are shown in the example in Table 15 below.

Among them, the first solution (that is, the first driver) has the lowest score, that is, the least energy consumption, which means that the first driver can be calculated as the best solution by the method of the present invention.

Yet another embodiment of the present invention is a performance evaluation system and method, which can be used for energy-saving driving performance evaluation, and a performance evaluation algorithm performed by the performance evaluation system to collect and analyze the energy consumption of a plurality of drivers driving a vehicle. To select the least expensive solution.

The performance evaluation system in this embodiment is the same as that shown in FIG. 1. The vehicle device 1 includes a communication module 100, an intermediary software module 101, a positioning module 102, a driver identification device 103, and energy. Detection device 104, wherein the communication module 100 can support 4G (Long Term Evolution, LTE) communication technology, so that the vehicle equipment 1 can connect to a 4G network through the communication module 100, and establish and analyze data The communication of the server device 2; the intermediary software module 101 can support Hypertext Transfer Protocol and Representational State Transfer (REST), and the vehicle device 1 can call the data analysis server device 2 through the intermediary software module 101 Application Program Interfaces (APIs), and transmits vehicle equipment information to the data analysis server device 2 periodically or aperiodically. The vehicle equipment information may include vehicle number, vehicle model, and driver number , Time information, location information or speed information, etc .; and the positioning module 102 can support a global positioning system to enable vehicle equipment 1 Location information and speed information are obtained via satellite signals; the driver identification device 103 is a radio frequency identification (RFID) card reader, and the driver ’s identification document owned by the driver is an RFID tag ( tag), the RFID tag 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 detection device 104 is a fuel detection device The measuring device can detect the amount of gasoline in the fuel tank of the vehicle, calculate the difference in the amount of gasoline to obtain the energy consumption information, and provide the energy consumption information to the vehicle equipment 1. Therefore, the vehicle equipment information transmitted by the vehicle equipment 1 includes the vehicle number, vehicle model, Driver ID, time information, location information, speed information, and energy consumption information.

In the present embodiment, a total of C _N vehicles devices, T _N kinds of vehicle models, D _N-bit driver, the vehicle device is transmitted once every 30 seconds, the vehicle information device to the data analysis server apparatus, the following table sixteen For example: The first driver drove the vehicle with the first vehicle number on 2015/01/01, and the vehicle model of the vehicle equipment was the first vehicle model. The vehicle equipment obtained the driver ’s Identifies the number of the first driver, and the vehicle equipment can obtain the location information of the vehicle equipment (that is, longitude 102.5423383 degrees and latitude 24.09490167 degrees) and vehicle speed information (real-time speed 44 km / Hours), and the vehicle equipment uses the energy detection device within 30 seconds (2015/01/01 05: 59: 30-2015 / 01/01 06: 00: 00) to consume 0.019 kWh (kWh (1kWh ) (That is, energy consumption information), and then call the REST APIs of the data analysis server through the mediation software module to transmit vehicle equipment information to the data analysis server.

The examples in Table 16 are as follows:

Please refer to FIG. 1 for the system architecture of this embodiment. The data analysis server device 2 includes a communication module 20, an intermediary software module 22, and a performance evaluation module 24. In this embodiment, the data analysis The server device 2 can support Linux operating system, Microsoft Windows operating system, etc., and a network service server can be built on the operating system to which it belongs; the communication module 20 can support wired network transmission to establish vehicle equipment 1, data The communication between the library device 3 and the data analysis server device 2; and the intermediary software module 22 is implemented using the Tomcat network service server to build a plurality of REST APIs for the vehicle device 1 to access, which can be accessed via Hypertext transfer protocol receives vehicle equipment information transmitted by vehicle equipment 1 and stores the received vehicle equipment information and energy consumption information to database equipment 3, where the vehicle equipment information may include vehicle number, vehicle model, driver number, Time information, location information, vehicle speed information, and energy consumption information; and the performance evaluation module 24 performs a performance evaluation algorithm to collect each vehicle Vehicle equipment information transmitted by the preparation and analysis of the energy consumption of the number of drivers you calculate the energy consumption of each driver's performance and ranking.

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 uses a Microsoft Structured Query Language (SQL) server. Server, MySQL, PostgreSQL, Oracle database server, MongoDB server, HBase server, etc .; and the communication module 30 can support wired network transmission to create database device 3 and data analysis server device 2 Communication between the computing module 32 and the communication module 30 can receive the request transmitted by the data analysis server device 3 to access the storage module 34; and the storage module 34 is interfaced with the computing module 32 To provide operations such as adding, modifying, deleting, and querying, the storage module 34 will store vehicle equipment information (as shown in Table 16 above).

The step flow chart of the performance evaluation method of this embodiment is also the same as that of the first embodiment described above. Please refer to FIG. 2. The steps include: step S201 collecting and analyzing vehicle equipment information; step S202 selecting feature elements; step S203 constructing a hierarchy Structure; step S204 generates a pairwise comparison matrix algorithm; step S205 calculates eigenvalues and eigenvectors; step S206 selects a solution to screen out the best solution corresponding to an optimal score.

In this embodiment, the step S201 collects and analyzes the vehicle equipment information. The performance evaluation module queries and analyzes the database equipment information within a year from the database equipment, and can calculate the average energy consumption information of different speed zones. Here, In the embodiment, there are a total of fourteen hourly speed zones, including: the first hourly speed zone is 0 km / h, the second hourly speed zone is greater than 0 kilometers per hour and less than or equal to 10 kilometers per hour, and the third hourly speed zone is greater than 10 kilometers. / Hour and less than 20 km / h, 4th speed range greater than 20 km / h and 30 km / h or less, 5th speed range greater than 30 km / h and 40 km / h or less, 6th speed range Greater than 40 km / h and less than or equal to 50 km / h, 7th speed range greater than 50 km / h and less than or equal to 60 km / h, 8th speed range greater than 60 km / h and less than or equal to 70 km / h, The 9th speed range is greater than 70 km / h and 80 km / h or less, the 10th speed range is greater than 80 km / h and 90 km / h or less, and the 11th speed range is At 90 km / h and 100 km / h or less, at 12 km / h and greater than 100 km / h and at 110 km / h, at 13 km per hour and greater than 110 km / h and at 120 km / h, and The 14th speed range is greater than 120 km / h.

Taking the i- th vehicle equipment as an example, the performance evaluation module queries and analyzes the energy consumption information of the i-th vehicle equipment in each speed zone in 2015: the energy consumption of the i- th vehicle equipment in the first speed zone Information Degrees, energy consumption information for the i- th vehicle equipment in the second speed range Degrees, energy consumption information for the i- th vehicle equipment in the third speed range Degrees, energy consumption information for the 4th speed zone of the i- th vehicle equipment Degrees, energy consumption information for the i- th vehicle equipment in the 5th speed range Degrees, energy consumption information for the 6th speed zone of the i- th vehicle equipment Degrees, energy consumption information for the 7th speed zone of the i- th vehicle equipment Degree, energy consumption information of the i- th vehicle equipment in the 8th speed range Degrees, energy consumption information for the 9th speed zone of the i- th vehicle equipment Degrees, energy consumption information for the i- th vehicle equipment in the 10th speed range Degrees, energy consumption information for the 11th speed zone of the i- th vehicle equipment Degree, energy consumption information of the i- th vehicle equipment at the 12th speed zone Degrees, energy consumption information for the 13th speed zone of the i- th vehicle equipment Degree, energy consumption information of the 14th speed zone of the i- th vehicle equipment degree.

According to the above performance evaluation method, taking the i- th driver driving the x- th vehicle equipment as an example, the performance evaluation module queries and analyzes the database equipment for the x- th vehicle equipment driven by the i- th driver in 2015. Energy consumption information of each hour speed zone in the year: The energy consumption information of the i-th driver driving the xth vehicle equipment in the first hour speed zone is Degrees, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the second speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the third speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the fourth speed zone is Degrees, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 5th speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 6th speed range is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 7th speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 8th speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 9th speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 10th speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 11th speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 12th speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 13th speed zone is Degree, the energy consumption information of the i-th driver driving the x-th vehicle equipment in the 14th speed zone is degree.

In this embodiment, the feature elements are selected in step S202, and the two feature elements of the vehicle equipment and the driver are used for analysis, and step S203 is performed to establish a hierarchical structure, and the optimal solution is used as the first layer and the vehicle equipment as The second floor and the driver are the third floor. Please refer to Figure 4 for the schematic diagram of the hierarchical structure.

The pairwise comparison matrix generation algorithm in step S204 can calculate a value of a feature element set at each level by using a distance function or a similarity function, and generate a pairwise comparison matrix according to the value.

In this embodiment, the vehicle equipment of the second layer may correspond to a pairwise comparison matrix, and the pairwise comparison matrix may be generated by the Cosine Similarity method, and may be used to calculate the normalized pairing of the vehicle equipment separately. Comparison matrix and feature vector matrix of feature elements of the second layer; initialization of vehicle equipment is a pairwise comparison matrix: Normalized pairwise comparison matrix for vehicle equipment: The feature vector matrix of feature elements in the second layer is the weighting matrix of influencing factors of each vehicle equipment:

In this embodiment, the driver of each vehicle equipment in the third layer can correspond to a pairwise comparison matrix, and the pairwise comparison matrix can be generated by the cosine similarity method, and each pair of comparison matrix can be used for each comparison and analysis of each of the driver's vehicle energy consumption of the device to the i-th x-th driving vehicle equipment, for example, may be through x-th driver of a vehicle device initialization pairwise comparison matrix, and then calculate the x-th The normalized pairwise comparison matrix of the driver of the vehicle equipment and the feature vector feature vector matrix of the third layer; among them, the initialization of the pairwise comparison matrix of the driver of the xth vehicle equipment: Among them, the normalized pairwise comparison matrix of the driver of the x- th vehicle equipment: Driver influence factor weight matrix for the xth vehicle equipment:

And so on, can be produced in the third layer C _N pairwise comparison matrix, i.e. line W _2,1, W _2,2, ..., , And the feature element feature vector matrix W _{2 of the} third layer can be established accordingly:

Following on, after calculating the eigenvalues and eigenvectors in step S205. That is, the method proceeds to step S206 to select a solution. In this embodiment, the score of each solution can be obtained by multiplying the feature vector matrix (as shown below). The score of each solution represents the energy of the solution compared to other drivers. Consumption ratio, υ ₁ represents the score of solution 1 (that is, the score of the first driver), υ ₂ represents the score of solution 2 (that is, the score of the second driver), ..., The score representing the solution D _N (ie the score of the D _N driver);

Cosine similarity can be used to calculate the similarity of each solution, and the solution with the lowest score can be found accordingly, which means that this solution has the largest difference from other solutions, and is used to find the driver with the largest difference in energy consumption.

There is still another embodiment of the present invention, which is a performance evaluation system and method, which can be used for the performance evaluation of dangerous driving. The performance evaluation module executes performance evaluation algorithms to collect and analyze the number of drivers driving the vehicle Event information. The event information is the speeding event, sharp acceleration event, sudden braking event, sharp turn event, stun event, unsafe distance event, lane shift event, etc. to select the least dangerous solution.

For a system architecture diagram of the performance evaluation system of this embodiment, please refer to FIG. 5. The system includes a plurality of vehicle devices 1 (to avoid complicated drawings, only one of which is shown in the figure), a data analysis server device 2 and a database device. 3.

The vehicle equipment 1 can transmit information about the vehicle equipment on which the vehicle is installed to the data analysis server device 2, and the data analysis server device 2 can store data to the database device 3, and the data analysis server device 2 executes the invention Performance evaluation algorithms to calculate the performance and ranking of each driver.

In this embodiment, the vehicle device 1 includes a communication module 100, an intermediary software module 101, a positioning module 102, a driver identification device 103, an azimuth sensor 105, and a focus detection Measurement device 106, a distance detection device 107 in front of the vehicle, and a lane departure detection device 108; among them, the communication module 100 can support 4G (Long Term Evolution, LTE) communication technology, making the vehicle device 1 The communication module 100 can be connected to the 4G network and establish communication with the data analysis server device 2. The intermediary software module 101 can support Hypertext Transfer Protocol and Representational State Transfer (REST). The vehicle The device 1 can call the application program interfaces (APIs) of the data analysis server device 2 through the intermediary software module 101, and send vehicle equipment information to the data analysis server in a periodic or aperiodic manner. Device 2. Vehicle equipment information may include vehicle number, vehicle model, driver number, time information, location information or speed information, etc .; and the positioning module 102 Support global positioning system, so that vehicle equipment 1 obtains position information and speed information via satellite signals, and judges speeding events, rapid acceleration events, emergency braking events and other event information through the vehicle speed information; the driver identification device 103 is a wireless radio frequency Identification system (Radio Frequency Identification, RFID) card readers, and the driver ’s identification document owned by the driver is an RFID tag (tag), which can store a driver ’s number and approach the driver ’s identity When the device 103 is installed, the driver identification device 103 can obtain the driver ID therein.

Among them, the azimuth sensor 105 is a gyroscope, which can detect the azimuth information of the vehicle so that the vehicle equipment 1 can obtain the azimuth information, and the azimuth information is a value between 0 and 360, which is available. To determine whether the vehicle has a sharp turn event and other event information; and the concentration detection device 106 is a wear-through brain wave detection device that can be worn on the driver ’s head to detect the driver ’s brain wave information. Device 1 can obtain brain wave information through brain wave detection device 106 to generate concentration information. In this embodiment, a NeuroSky MindWave wearable brain wave detection device can be used, which has a built-in software to detect brain waves. After that, the concentration information is output. Among them, the concentration information is a value between 0 and 100, which can be used to determine whether the driver has event information such as a god event.

The preceding vehicle distance detection device 107 can detect the preceding vehicle distance information between the vehicle and the vehicle in front, so that the vehicle device 1 can obtain the preceding vehicle distance information through the preceding vehicle distance detection device 107. The preceding vehicle distance information is A value that can be used to determine whether the vehicle has event information such as an event that does not maintain a safe distance; and the lane departure detection device 108 can detect the state of the vehicle deviating from the lane without turning on the lights, so that the vehicle device 1 can pass The lane departure detection device 108 obtains the lane offset information. The lane offset information is a value of 0 or 1. 0 is a lane without an offset and 1 is a lane with an offset. There is event information such as a lane departure event.

In summary, the vehicle equipment information transmitted by the vehicle equipment 1 in this embodiment includes a vehicle number, a driver number, time information, and event information. The event information may be an overspeed event, a sharp acceleration event, a sharp braking event, a sharp turn event, God event, unsafe distance event, lane shift event.

In the present embodiment, a total of C _N vehicles equipment, D _N-bit drivers, R _N of the risk factors elite event information, wherein, the apparatus 1 may be every second vehicle to the positioning module 102, the orientation The angle sensor 105, the concentration detection device 106, the preceding vehicle distance detection device 107, and the lane departure detection device 108 respectively obtain position information, speed information, azimuth information, concentration information, and front vehicle Distance information and lane offset information, and the vehicle equipment 1 analyzes the information to determine whether it meets the risk factor. If there is a risk factor, when the vehicle equipment information is transmitted to the data analysis server equipment 2, the vehicle equipment information includes the compliance Event information for risk factors.

In this embodiment, the risk factor type R _N is 7, which represents event information including a total of seven risk factors, which are: speeding event, rapid acceleration event, sudden braking event, sharp turning event, stunning event, not maintained. Safety distance event or lane departure event.

The first risk factor is overspeed. The vehicle device 1 can obtain information from the positioning module 102 every one second to determine vehicle speed information, and the vehicle device 1 can pass the intermediary software module 101 and then the communication module. 100 is interfaced with an external information device 4 to obtain road information on the road where the vehicle is located from the external information device 4, such as the speed limit, and then compare the speed information and the speed limit; when the speed information is greater than the speed limit, the vehicle The device 1 interfaces with the data analysis server device 2 through the communication module 100 to transmit vehicle equipment information to the data analysis server device 2. The vehicle equipment information includes at least a vehicle number, a driver number, time information, and event information. Information is a speeding event.

The second risk factor is rapid acceleration. The vehicle equipment can obtain vehicle speed information from the positioning module 102 every one second. Moreover, the vehicle equipment 1 can record the vehicle speed information of the previous second and set the first acceleration threshold. When the vehicle speed When the difference between the information minus the vehicle speed information of the previous second is greater than the first acceleration threshold, the vehicle equipment 1 interfaces with the data analysis server equipment 2 through the communication module 100 to transmit the vehicle equipment information to the data analysis servo Device 2, the vehicle equipment information includes at least a vehicle number, a driver number, time information, and event information. The event information is a rapid acceleration event.

The third risk factor is an emergency brake. The vehicle equipment 1 can obtain the speed information from the positioning module 102 every one second. Moreover, the vehicle equipment 1 can record the speed information of the previous second and set the second acceleration threshold. When the difference between the speed information reduction in seconds and the speed information reduction is greater than the second acceleration threshold, the vehicle device 1 interfaces with the data analysis server device 2 through the communication module 100 and transmits the vehicle device information to the data analysis server Device 2. The vehicle equipment information includes at least the vehicle number, driver number, time information, and event information. The event information is an emergency braking event. The fourth risk factor is a sharp turn. Vehicle equipment 1 can turn to the direction every one second. The angle sensor 105 obtains azimuth information, and the vehicle device 1 can record the azimuth information of the previous second and set a first azimuth threshold value and a second azimuth threshold value, where the first azimuth threshold value is less than the first Two azimuth thresholds. When the difference between the azimuth information minus the previous azimuth information and the absolute value is greater than the first acceleration threshold and the difference is less than the second When the angle threshold value is reached, the vehicle equipment 1 interfaces to the data analysis server equipment 2 via the communication module 100 to transmit the vehicle equipment information to the data analysis server equipment 2. The vehicle equipment information includes at least a vehicle number, a driver number, Time information and event information, which is a sharp turn event.

The fifth risk factor is driving gods, vehicle equipment 1 can obtain the concentration information from the concentration detection device 106 every one second, and vehicle equipment 1 can set a concentration threshold when the concentration information is less than Attention threshold, the vehicle equipment 1 interfaces to the data analysis server equipment 2 via the communication module 100 to transmit vehicle equipment information to the data analysis server equipment 2. The vehicle equipment information includes at least a vehicle number, a driver number, Time information and event information, the event information is a God event.

The sixth risk factor is that the safety distance is not maintained. The vehicle equipment 1 can obtain the vehicle speed information from the positioning module 102 every one second, and obtain the preceding vehicle distance information from the forward vehicle distance detection device 107, and the vehicle equipment 1 can Calculate the value of the vehicle speed information (unit: km / h) minus 20 to determine whether the value is greater than the distance information of the preceding vehicle. When the value is greater than the distance information of the preceding vehicle, the vehicle equipment 1 analyzes the data through the communication module 100 The server device 2 is interfaced to transmit vehicle equipment information to the data analysis server device 2. The vehicle equipment information includes at least a vehicle number, a driver number, time information, and event information. The event information is an event that does not maintain a safe distance.

The seventh risk factor is lane departure. Vehicle equipment 1 can obtain lane departure information from the lane departure detection device 108 every one second and determine whether the value is 1. When the lane departure information value is 1, then The vehicle equipment 1 is interfaced to the data analysis server equipment 2 via the communication module 100 to transmit vehicle equipment information to the data analysis server equipment 2. The vehicle equipment information includes at least a vehicle number, a driver number, time information, and event information. , The event information is a lane departure information event.

Please continue to refer to FIG. 5, where the data analysis server device 2 includes a communication module 20, an intermediary software module 22, and a performance evaluation module 24; in this embodiment, the data analysis server device 2 can support Linux operating system, Microsoft Windows operating system, etc., and a network service server can be built on the operating system to which it belongs; the communication module 20 can support wired network transmission to establish vehicle equipment 1, database equipment 3, and data analysis The communication between the server devices 2; and the intermediary software module 22 is implemented using the Tomcat web service server to build a plurality of REST APIs for the vehicle device 1 to interface with, and it can receive the vehicle via the hypertext transfer protocol Vehicle equipment information transmitted by equipment 1, and the received vehicle equipment information and energy consumption information are stored in database equipment 3, where the vehicle equipment information may include vehicle number, vehicle model, driver number, time information, location information, The speed information and event information are shown in the example in Table 17 below; and the performance evaluation module 24 executes a performance evaluation algorithm to collect each vehicle equipment The vehicle equipment information transmitted, and the dangerous driving factors of each driver are analyzed to calculate the performance and ranking of each driver.

Table 17 is:

The data analysis server device 2 can interface with the external information device 4 through the communication module 20 through the intermediary software module 22, and obtain the probability of a traffic accident for each risk factor from the external information device 4, and a traffic accident will occur. Probability is stored to database device 3, as shown in the example in Table 18 below:

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 uses Microsoft Structured Query Language (SQL). Server, MySQL, PostgreSQL, Oracle database server, MongoDB server, HBase server, etc .; and the communication module 30 can support wired network transmission to create database device 3 and data analysis server device Communication between 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; and the storage module 34 is interposed with the operation module 32 Then, to provide operations such as adding, modifying, deleting, and querying, the storage module 34 can store vehicle equipment information (as shown in Table 17 above).

For the steps of the performance evaluation method of this embodiment, please also refer to the flowchart of FIG. 2. The steps include: collecting and analyzing vehicle equipment information in step S201; selecting feature elements in step S202; constructing a hierarchical structure in step S203; pairing in step S204 A comparison matrix generation algorithm; step S205 calculates eigenvalues and eigenvectors; step S206 selects a solution to screen out the best solution corresponding to an optimal score.

In this embodiment, the vehicle equipment information collected and analyzed in step S201 may be queried and analyzed by the performance evaluation module from the database equipment for each vehicle equipment information within one month.

The number of events information to the driver of the j-th occurrence of the i th risk factor, for example, performance evaluation module i-th occurrence of risk factors in January 2015 to a database query and statistical device j-th driver ; In this embodiment, there are a total of R _N types of risk factors, and a total of the number of event information on the occurrence of various risk factors by the jth driver can be counted { , , ..., }.

In this embodiment, the feature elements selected in step S202 are analyzed using the risk factor and the driver's two feature elements, and step S203 is performed to establish a hierarchical structure according to this. The optimal solution is used as the first layer, and the risk factor is used as the second. As the third floor, the floor and driver are shown in Figure 6 for a schematic diagram of the hierarchical structure.

The pairwise comparison matrix generation algorithm in step S204 can count the values of the feature elements set at each level, and generate a pairwise comparison matrix according to the ratio of the values.

In this embodiment, the risk factor of the second layer may correspond to a pairwise comparison matrix. The pairwise comparison matrix may be generated in the following manner, and the pairwise comparison matrix may be used to compare Analysis, and then use numerical analysis to calculate the feature vector matrix of each level of feature elements; among them, the risk factor initialization is a pairwise comparison matrix: Normalized pairwise comparison matrix for risk factors: The feature vector matrix of the feature elements in the second layer is the influence factor weight matrix of each risk factor:

In this embodiment, each risk factor of the driver of the third layer can correspond to a pairwise comparison matrix. The pairwise comparison matrix can be generated in the following manner, and in order to avoid the situation where the denominator is 0, the risk factor is Increasing the number of event information by one, the pairwise comparison matrix can be used to compare and analyze the amount of event information of each driver's risk factors; the following is an example of the amount of event information generated by each driver when the first risk factor occurs: Among them, driving The initial pairwise comparison matrix for the first occurrence of human risk factors:

Among them, the normalized pairwise comparison matrix of the first risk factor for drivers:

Among them, the driver's occurrence of the first risk factor weight matrix:

According to the same calculation method, the occurrence of the xth risk factor for each driver in the third layer can correspond to a pairwise comparison matrix. The pairwise comparison matrix can be generated in the following manner, and the driver's Comparison and analysis of the quantity of this risk factor event information; among them, the driver initiates the pairwise comparison matrix of the xth risk factor: Among them, the normalized pairwise comparison matrix of the driver's xth risk factor: Among them, the driver's occurrence of the x- th risk factor weighting factor matrix:

By analogy, R _N pairwise comparison matrices can be generated in the third layer, that is, W _2,1 , W _2,2 , ..., , And the feature element feature vector matrix W _{2 of the} third layer can be established accordingly:

In this embodiment, in step S206, a solution is selected, and a score of each solution can be generated according to a feature vector matrix of each level of feature elements, and then the best solution corresponding to an optimal score is selected; The score can be generated by matrix multiplication (as shown below). The score of each solution represents the ratio of the possibility of a traffic accident compared to other drivers, and υ ₁ represents the score of solution 1 (that is, the first The score of one driver), υ ₂ represents the score of solution 2 (that is, the score of the second driver), ..., The score representing the solution D _N (ie the score of the D _N driver);

In this embodiment, the lower the probability of a traffic accident, the better, so compare the scores of each solution to get the lowest score solution. The driver corresponding to the best solution is the best driver. It will get the least risk of traffic accidents under various risk factors.

Another embodiment disclosed is also a performance evaluation system and method for the performance evaluation of dangerous driving. Based on the third embodiment described above, the performance evaluation module executes a performance evaluation algorithm. When solving a solution, the score of each solution is generated according to the feature vector matrix of the feature elements of each level, and then the best solution is selected by the decision tree information profit method. Among them, the decision tree information profit method includes the following steps: There are calculations of the score vector matrix of the normalization solution, calculation of the degree of confusion of the score after the normalization of each risk factor of each driver, and calculation of the degree of confusion to obtain information for profit.

As the above-described third embodiment, the elements made of the features of the second layer and the fraction of vector matrix W ₂ wherein _a third layer of the eigenvector matrix W of each element solution Then, the performance evaluation module uses the following calculation methods to generate a normalized solution score vector matrix ω , where, The score representing the j- th driver who has normalized the i- th risk factor:

According to the above calculation method, the performance evaluation module uses the entropy formula to calculate the chaos degree of the normalized scores of each risk factor for each driver, and uses the j- th driver to normalize the scores of various risk factors. The degree of confusion E _{j is taken} as an example, and the calculation method is as follows:

According to the above calculation, performance evaluation module using the entropy formula for the degree of chaos after scores of each driver's individual risk factors to calculate normalized, then the one minus the clutter to get information to profit, with the first j As an example, the information profit of a driver G _j is calculated as follows: G _j = 1- E _j .

In conclusion, assuming that R _N is 3 and D _N is 3, a normalized solution score vector matrix can be calculated, as shown below: among them, The score for the first risk factor representing the first driver was 0.7976, The third risk factor of the third driver is a normalized score of 0.4225, and the rest can be deduced by analogy.

According to the above calculation method, the performance evaluation module uses the entropy formula to calculate the chaos degree of the scores after the normalization of each risk factor of each driver; among them, the chaos degree of the scores after the normalization of each risk factor of the first driver E ₁ : Among them, the degree of confusion of the score of the second driver after the normalization of each risk factor E ₂ : Among them, the degree of chaos E ₃ of the score after the normalization of each risk factor of the third driver:

According to the above calculation method, the performance evaluation module uses the entropy formula to calculate the degree of chaos of the score after the normalization of each risk factor of each driver, and then uses one to reduce the degree of chaos to obtain information for profit; One driver's information profit G ₁ = 1- E ₁ = 1-0.586 = 0.414; the second driver's information profit G ₂ = 1- E ₂ = 1-0.868 = 0.132; the third driver Information profit G ₃ = 1- E ₃ = 1-0.853 = 0.147.

After completing the information profit of each driver, the performance evaluation module sorts the information profit and selects the solution with the highest information profit, which is the best solution and represents the corresponding driver in the the next risk factor or complex, there is significant abnormal performance than other drivers; in this embodiment, the first driver of the information highest profit G _1, the first driver selected by the record performance evaluation module The first driver was an abnormal driver.

Furthermore, the present invention has another embodiment, which is a performance evaluation system and method, which can be used for logistics performance evaluation purposes, and the performance evaluation system performs a performance evaluation algorithm to collect and analyze a plurality of logistics drivers driving vehicles. Incident information to select the solution with the least violations.

The system architecture diagram of the performance evaluation system of the fifth embodiment is shown in FIG. 7. The system includes a plurality of vehicle devices 1 (to avoid complicated drawings, only one of which is shown in the figure), and a data analysis server. Device 2 and a database device 3.

The vehicle equipment 1 can transmit information about the vehicle equipment on which the vehicle is installed to the data analysis server device 2, and the data analysis server device 2 can store data to the database device 3, and the data analysis server device 2 executes the invention Performance evaluation algorithms to calculate the performance and ranking of each driver.

In this embodiment, the vehicle device 1 includes a communication module 100, an intermediary software module 101, a positioning module 102, a driver identification device 103, an on-board diagnostic system 109, and a temperature sensor. 110, the vehicle equipment 1 has a vehicle number and a vehicle model; wherein the functions of the communication module 100, the intermediary software module 101, the positioning module 102, and the driver identification device 103 are the same as those of the previous embodiment; The difference is that the on-board diagnostic system 109 can detect the vehicle status information of the vehicle, so that the vehicle equipment 1 can 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 The sensor 110 can detect freezer temperature information in the vehicle, so that the vehicle device 1 can obtain the temperature information through the temperature sensor 110; therefore, in this embodiment, the vehicle device information transmitted by the vehicle device 1 includes Vehicle number, vehicle model, driver number, time information, location information, speed information, door switch information, temperature information, etc.

30 seconds and the vehicle device transmitting information to a data analysis server apparatus 2, in this embodiment in the following table, the total equipment vehicles C _N, T _N kinds of vehicle models, D _N-bit driver, the vehicle device may be every 1 A nineteen example is shown; among them: the first driver drives the vehicle with the first vehicle number on 2015/01/01, and the vehicle model of the vehicle equipment set is the first vehicle model, and the vehicle equipment is identified by the driver's identity The device obtains the driver ’s identity as the first driver ’s number, and the vehicle equipment may obtain the location information of the vehicle equipment (that is, longitude 102.5423383 degrees and latitude 24.09490167 degrees) and vehicle speed information ( Real-time speed 44 km / h), and the vehicle equipment obtains vehicle status information through the on-board diagnostic system (the information is a door switch information, the value of the door switch information is 1, which indicates that the door switch is abnormal), and the vehicle equipment then passes the intermediary software The module calls the REST APIs of the data analysis server to send vehicle equipment information to the data analysis server.

Subsequently, the vehicle equipment obtains the location information of the vehicle equipment (that is, longitude 120.5361317 degrees and latitude 24.09120167 degrees) and vehicle speed information (real-time speed of 39 km / h) through the positioning module at 06:00:30, and the vehicle equipment passes the vehicle. Get the vehicle status information from the diagnostic system (the door switch information is 0, which indicates that the door switch is normal). In addition, the vehicle equipment can obtain temperature information (18 degrees) through the temperature sensor. The REST APIs of the data analysis server are called through the mediation software module to transmit the vehicle equipment information to the data analysis server. The rest of the vehicle equipment information can be obtained by analogy.

The following is Table 19:

Please continue to refer to FIG. 7, where the data analysis server device 2 includes a communication module 20, an intermediary software module 22, and a performance evaluation module 24; in this embodiment, the data analysis server device 2 can support Linux operating system, Microsoft Windows operating system, etc., and a network service server can be built on the operating system to which it belongs; the communication module 20 can support wired network transmission to establish vehicle equipment 1, database equipment 3, and data analysis The communication between the server devices 2; and the intermediary software module 22 is implemented using the Tomcat web service server to build a plurality of REST APIs for the vehicle device 1 to interface with, and it can receive the vehicle via the hypertext transfer protocol Vehicle equipment information transmitted by equipment 1, and the received vehicle equipment information and energy consumption information are stored in database equipment 3, where the vehicle equipment information may include vehicle number, vehicle model, driver number, time information, location information, Vehicle speed information and energy consumption information; and the performance evaluation module 24 performs a performance evaluation algorithm to collect vehicle settings transmitted by each vehicle device. Information and analyze the information you the number of violations the driver, the driver is calculated for each violation and the degree of performance rankings.

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 uses the Microsoft Structured Query Language (Structural Query Language, SQL) server, MySQL, PostgreSQL, Oracle database server, MongoDB server, HBase server, etc .; and the communication module 30 can support wired network transmission to create database equipment 3 and data analysis server Communication between the 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; and the storage module 34 is connected to the operation module 32 interface to provide operations such as adding, modifying, deleting, querying, etc. In addition, the storage module 34 can store a shift table data table, which records the site information and scheduled arrivals of the goods received and delivered. Time information, site information includes a latitude and longitude coordinate (as shown in the example in Table 20 below), and the storage module 34 can also store vehicle equipment information (as shown in Table 19 above).

The following is Table 20:

Among them, the data analysis server equipment will judge and analyze the longitude and latitude of the vehicle equipment information when receiving each piece of vehicle equipment information, and compare the longitude and latitude of the station number in the schedule table data table. When it is within a distance threshold, it is judged that the vehicle arrives at the corresponding station number; for example, in this embodiment, the distance threshold is 50 meters, and the data analysis server equipment is at 2015/01/01 06: 00 0:00 received the vehicle equipment information from the first vehicle number. The vehicle equipment information is as follows, including the first vehicle number (vehicle number), the first vehicle model (vehicle model), and the first driver (driver). (Number), 2015/01/01 06: 00: 00 (time), 120.5423383 (longitude), 24.09490167 (latitude), 44 (vehicle speed), 1 (door opening and closing information), 22 (temperature information), the data analysis server The device compares the latitude and longitude coordinates (that is, longitude 120.5423383 and latitude 24.09490167) with the latitude and longitude coordinates of each station of the first vehicle number in the schedule table, and can obtain the current latitude and longitude with the latitude and longitude coordinate of station 1 (that is, longitude 120.542 3383 and latitude 24.09490167) The distance is lower than the distance threshold, so it can modify the schedule data table to add the real arrival time information of the vehicle with the first vehicle number. The modified schedule data table is shown in Table 21 below. Example As shown.

Table 21 is:

Among them, the data analysis server device will analyze I _N index factors. In this embodiment, I _N is 4, which represents event information including a total of 4 index factors, which are: door door abnormal events, temperature abnormal events, Insufficient pre-cooling event or abnormal arrival time, etc. In addition, the data analysis server device can calculate the index factor event information of the previous day at 01:00 AM every day. For example, the data analysis server device was in 2015 / 01/02 01: 00: 00 analyzes the vehicle equipment information of 2015/01/01 (for example, as shown in Table 19 above), and then generates event information of these index factors.

Among them, 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 switch information of each piece of data. When the value of the door switch information is 1, it represents the door. If the switch is abnormal, a door closing abnormal event is generated. The performance evaluation module further transmits the vehicle number, driver number, time, and corresponding event information corresponding to the door closing abnormal event to the database device and stores it in the event information table. (Shown in the example in Table 22 below); for example, when the first driver drives a vehicle with the first vehicle number at 2015/01/01 06: 00: 00, the door switch information is 1, and the performance evaluation module Analyze the event information that causes abnormal door closing.

The second index factor is temperature abnormality. The performance evaluation module can set the first temperature threshold and the second temperature threshold. Among them, the first temperature threshold is lower than the second temperature threshold, and the performance evaluation module reports to the data. The library equipment obtains the vehicle equipment information (as shown in the example in Table 19 above) and analyzes the temperature information of each piece of data. When the temperature information is less than the first temperature threshold or the temperature information is greater than the second temperature threshold, it represents the temperature Abnormal, the performance evaluation module generates a temperature abnormal event, and transmits the vehicle number, driver number, time, and corresponding event information corresponding to the temperature abnormal event to the database device for storage to the event information table (as follows) Table 22 shows an example); 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 on 2015/01/01 At 06:01:30, the temperature information is 15 degrees, and the temperature information is less than the first temperature threshold. The performance evaluation module analyzes and determines the event information of the temperature abnormality.

The third index factor is insufficient pre-cooling. The performance evaluation module can set a first temperature threshold and a second temperature threshold. The first temperature threshold is lower than the second temperature threshold. The database equipment obtains the vehicle equipment information (as shown in the example in Table 19 above) and the modified schedule data table (as shown in the example in Table 21 above), and analyzes the temperature information when arriving at station 1, when the temperature information is less than the first A temperature threshold value or temperature information greater than the second temperature threshold value indicates insufficient pre-cooling. The performance evaluation module generates an insufficient pre-cooling event, and the vehicle number, driver number, time, and The event information is transmitted to the database device and stored in the event information table (as shown in the example in Table 22 below); for example, the first temperature threshold is 16 degrees, the second temperature threshold is 20 degrees, and the first driver The first vehicle numbered by a person arrives at station 1 at 2015/01/01 06: 00: 00, the temperature information is 22 degrees, and the temperature information is greater than the second temperature threshold, which is analyzed and judged by the performance evaluation module After the event information is insufficient to produce the pre-cooling.

Among them, the fourth index factor is the abnormal arrival time. The performance evaluation module can set an arrival time threshold, and the database equipment can obtain the revised schedule data table (as shown in table 21 above). And analyze the scheduled arrival time information and real arrival time information of each piece of data. When the scheduled arrival time information minus the real arrival time information and the absolute value is higher than the arrival time threshold, it represents When the arrival time is abnormal, the performance evaluation module generates an arrival time abnormal event, and transmits the vehicle number, driver number, time, and event information corresponding to the arrival time abnormal event to the database device and stores it to a database device. Event information table (as shown in the example in table 22 above); for example, the arrival time threshold is 20 minutes, and the D _N driver drives the vehicle with the C _N vehicle number and is scheduled to arrive at the station Z _N Departure time information is 2015/01/31 22:00: 00, real arrival time information is 2015/01/31 22:30: 00, at this time, the scheduled arrival time information is subtracted from the real arrival time information. Value after absolute value The value is 30 (minutes). This value is higher than the arrival time threshold. After the performance evaluation module analyzes and judges, the event information of the abnormal arrival time is generated.

The following table is Table 22:

Among them, the data analysis server device can be connected with an external information device by an intermediary software module through a communication module, and obtain information such as the average loss amount of each index factor from the external information device, and store the information of the average loss amount. To the database device, please refer to the following table 23 for examples;

For the flowchart of the steps of the performance evaluation method of this embodiment, please also refer to FIG. 2. The steps include: step S201 collecting and analyzing vehicle equipment information; step S202 selecting feature elements; step S203 constructing a hierarchical structure; step S204 pairwise comparison matrix Generate an algorithm; step S205 calculates eigenvalues and eigenvectors; step S206 selects a solution to screen out the best solution corresponding to an optimal score.

According to the above performance evaluation method, in this embodiment, step S201 collects and analyzes vehicle equipment information. The data analysis server device can be interfaced by the intermediary software module with an external information device through a communication module to the The external information device obtains the average loss amount of each index factor, and stores the information of the average loss amount to the database device. Please refer to the example in the table 23 above, and then query the database device by the performance evaluation module. These average losses.

Among them, the performance evaluation module queries and analyzes the vehicle equipment information in one day from the database equipment; taking the j- th driver's i- th index factor as an example, the performance evaluation module queries the database equipment and Count the event information of the i- th index factor of the j- th driver in 2015/01/01 , And there are I _N kinds of index factors, which can count the number of index factor event information of the jth driver { , , ..., }.

In this embodiment, the feature elements are selected in step S202, and the two feature elements of the index factor and the driver are used for analysis, and step S203 is performed to establish a hierarchical structure, and the optimal solution is used as the first layer and the index factor as The second layer and the driver are the third layer. Please refer to Figure 8 for the schematic diagram of the hierarchical structure.

The algorithm for generating the pairwise comparison matrix in step S204 can count the values of the feature elements set at each level, and generate a pairwise comparison matrix according to the ratio of the values.

In this embodiment, the index factors of the second layer may correspond to a pairwise comparison matrix, and the pairwise comparison matrix may be generated in the following manner to compare and analyze the average loss amount of each index factor from the pairwise comparison matrix. , And use the numerical analysis method to calculate the feature vector matrix of each level of feature elements; among them, the index factor initialization is a pairwise comparison matrix: Normalized pairwise comparison matrix of indicator factors: The feature vector matrix of the feature elements in the second layer is the influence factor weight matrix of each index factor:

In this embodiment, each index factor of the driver of the third layer can correspond to a pairwise comparison matrix. The pairwise comparison matrix can be generated in the following manner, and in order to avoid the situation where the denominator is 0, the index factor event can be Increase the number of information by one, and use this pairwise comparison matrix to compare and analyze the amount of event information of each driver's index factors. Below, take the amount of event information generated by each driver as the first index factor as an example: Initialized pairwise comparison matrix for the first indicator factor: The normalized pairwise comparison matrix for the first index factor of driver occurrence: Weighting matrix of influencing factors for the first index factor of driver occurrence:

According to the above calculation method, the occurrence of the x- th index factor for each driver of the third layer can correspond to a pairwise comparison matrix. The pairwise comparison matrix can be generated in the following manner, and the driver's first Comparison and analysis of the amount of event information of the x index factors; among them, the initialization of the x- th index factor of the driver is a pairwise comparison matrix: Among them, the normalized pairwise comparison matrix of the x- th index factor of driver occurrence: Among them, the driver's occurrence of the x- th index factor influence factor weight matrix:

By analogy, R _N pairwise comparison matrices can be generated in the third layer, that is, W _2,1 , W _2,2 , ..., , And the feature element feature vector matrix W _{2 of the} third layer can be established accordingly:

After step S205, step S206 selects a solution, generates a score for each solution according to the feature vector matrix of each level of feature elements, and then selects the best solution, which corresponds to an optimal score; here In the embodiment, the score of each solution can be generated by matrix multiplication (as shown below), the score of each solution represents the ratio of its average loss compared to other drivers, υ ₁ represents the solution The score of scheme 1 (that is, the score of the first driver), υ ₂ represents the score of solution 2 (that is, the score of the second driver), ..., The score representing the solution D _N (ie the score of the D _N driver);

In this embodiment, the lower the average loss amount is, the better, that is, the score of each solution is compared to obtain the solution with the lowest score, and the driver corresponding to it is the best driver; assuming that the lowest score is υ ₁ , It means that the first driver is superior to other drivers, and the first driver will get the least average loss amount under various index factors.

The sixth embodiment of the present invention is also a performance evaluation system and method for performance evaluation of dangerous driving. The sixth embodiment can be based on the fifth embodiment, and the performance evaluation method (that is, the performance evaluation module is executed) The algorithm for generating a pairwise comparison matrix in the performance evaluation algorithm is based on the previous embodiment. However, the fuzzy attribute function is used to calculate the value of the feature elements set at each level, and a pairwise comparison matrix is generated according to the value.

In this embodiment, the index factor of the second layer (ie, the vehicle equipment) corresponds to a pairwise comparison matrix. The pairwise comparison matrix can be generated by a fuzzy attribution function. The fuzzy attribution function is a modified S-type. Function (such as a modified Sigmoid function), the modified S-type function can subtract the modified reference value from the input value to be 0 to generate the S-type, and the pairwise comparison matrix performs the average loss of each level of index factors The comparison and analysis of the amounts are as follows. The normalized pairwise comparison matrix of the vehicle model and the feature vector feature vector matrix of the second layer are calculated respectively. Among them, the initialization of the vehicle model is the pairwise comparison matrix:

In this embodiment, each driver in each index factor of the third layer can correspond to a pairwise comparison matrix, and the pairwise comparison matrix can be generated by using the fuzzy attribution function as described above, that is, the modified one. S-shaped function, wherein the normalized pairwise comparison matrix to the x-driver initialization pairwise comparison matrix index factor of the driver calculated in the x-th index factor, and wherein the third element of the eigenvector matrix layer:

It should be understood that the detailed descriptions above are specific descriptions of the feasible embodiments of the present invention, but each of the embodiments is not intended to limit the patent scope of the present invention, and any equivalent implementation or change without departing from the technical spirit of the present invention, All should be included in the patent scope of this case.

In summary, the present invention is technically innovative and has multiple effects that are inferior to the previous technology. It has fully met the novel and progressive statutory invention patent requirements. It has filed a patent application in accordance with the law and urges your office to approve this invention. The patent application encourages invention, and it is a matter of virtue.

Claims (17)

    A performance evaluation system includes at least: a plurality of vehicle equipment, each of which is used to collect vehicle equipment information such as energy consumption information, azimuth information, concentration information, and positioning information when driving while driving; a data analysis server The device receives the vehicle equipment information from each of the vehicle equipment, calculates the driver's performance while driving through a performance evaluation algorithm, and can better sort the driver's performance. A database device is connected to the data analysis server device, and is used to store vehicle equipment information of each vehicle equipment and driver performance and ranking.         The performance evaluation system according to item 1 of the scope of patent application, wherein each of the vehicle equipment includes a driver identification device, a positioning module, an intermediary software module, a performance evaluation module, and a communication module. The positioning module supports global positioning system or wireless network signal positioning function, and each vehicle device obtains the position information and speed information in the vehicle equipment information through the positioning module to which it belongs. Used to determine event information such as overspeed events, rapid acceleration events, emergency braking events, etc .; wherein the communication module supports wireless network transmission to establish communication between the vehicle equipment and the data analysis server equipment; and among them, The intermediary software module supports at least one transmission protocol of a hypertext transmission protocol, a message sequence telemetry transmission, or a restricted application protocol. The vehicle device is connected to the data analysis server device via the intermediary software module and the communication module. To transmit vehicle equipment information to the data analysis server equipment; and wherein the performance evaluation module passes the The performance evaluation algorithm calculates the driver's performance while driving, and can better sort the driver's performance. Among them, the driver identification device is used to read the driver's identification document to obtain the driver's number. The driver's number is also The information contained in the vehicle equipment is transmitted to the data analysis server equipment.         According to the performance evaluation system described in item 2 of the scope of the patent application, each of the vehicle equipment further includes an energy detection device, and the energy detection device detects the energy consumption information of the vehicle provided by each of the vehicle equipment. Including the amount of oil, electricity, or natural gas, energy consumption information is also included in the vehicle equipment information and transmitted to the data analysis server equipment.         The performance evaluation system according to item 2 of the scope of the patent application, wherein each of the vehicle equipment further includes an azimuth sensor, and the azimuth sensor is used to detect the azimuth of each vehicle equipment during driving. Information, azimuth information is used to determine event information such as sharp turning events, and the event information will be included in the vehicle equipment information and transmitted to the data analysis server equipment.         According to the performance evaluation system described in item 2 of the scope of patent application, each of the vehicle equipment further includes a concentration detection device, which is a wearable brain wave detection device for It is worn on the driver ’s head to detect the driver ’s brain waves to obtain concentration information. The concentration information is used to determine event information such as the God event, and the event information will be included in the vehicle equipment information and transmitted to The data analysis server equipment.         The performance evaluation system according to item 2 of the scope of patent application, wherein each of the vehicle equipment further includes a front vehicle distance detection device and a lane departure detection device, and the front vehicle distance detection device detects each Information about the distance between the vehicle equipment and the vehicle in front while driving, and the lane deviation detection device detects the information about the deviation lanes when the vehicle equipment is not turned on when driving. Lane shifting information is used to determine event information such as a non-maintained distance event or a lane shift event, and the event information will be included in the vehicle equipment information and transmitted to the data analysis server equipment.         The performance evaluation system according to item 2 of the scope of patent application, wherein each of the vehicle equipment further includes an on-vehicle diagnostic system and a temperature sensor, and the on-vehicle diagnostic system detects a vehicle equipped with a vehicle. Vehicle status information, and the temperature sensor detects the temperature information of the refrigerator of each vehicle equipment, and the vehicle status information and temperature information will be included in the vehicle equipment information and transmitted to the data analysis server equipment.         The performance evaluation system described in item 7 of the scope of patent application, wherein the database device can store a shift schedule data sheet, which is used to record the site information and reservations of each vehicle equipment receipt and delivery Arrival time information. After the data analysis server device receives vehicle equipment information, it can generate door closing abnormal events, temperature abnormal events, insufficient pre-cooling events, or arrivals based on vehicle status information and temperature information in the vehicle equipment information. Station time abnormal events, etc.         A performance evaluation method is performed by a data analysis server device including at least the following steps: collecting and analyzing vehicle device information, and reporting the vehicle device information from a plurality of vehicle devices provided on the vehicle to the data analysis server device. The data analysis server equipment analyzes the vehicle equipment information of each vehicle equipment in a time interval, and stores the vehicle equipment information in a database equipment; selects at least one characteristic element, and obtains the vehicle equipment number, vehicle model, and vehicle equipment information from the vehicle equipment information. Select at least one of the characteristic elements such as a driver for performance evaluation; construct a hierarchical structure, and set the upper and lower correlation structure of each characteristic element according to each selected characteristic element; execute a pairwise comparison matrix to generate an algorithm to Each pair of feature elements set at each level generates a pairwise comparison matrix; calculates the eigenvalues and feature vectors, and uses numerical analysis to calculate a feature vector matrix of feature elements at each level; selects a solution, according to each level in each level The feature vector matrix of the feature element generates a complex After scoring several solutions, the best solution is selected.         The performance evaluation method according to item 9 of the scope of the patent application, wherein the pairwise comparison matrix generation algorithm calculates the value of each characteristic element set by each hierarchical structure, and generates a pairwise comparison matrix according to the ratio of the values .         The performance evaluation method according to item 9 of the scope of the patent application, wherein the pairwise comparison matrix generation algorithm uses a distance function or a similarity function to calculate the value of each feature element set in each hierarchical structure, and Generate a pairwise comparison matrix.         The performance evaluation method according to item 9 of the scope of the patent application, wherein the pairwise comparison matrix generation algorithm uses a fuzzy attribution function to calculate the value of each characteristic element set in each hierarchical structure, and generates a pair according to the value Comparison matrix.         The performance evaluation method according to item 9 of the scope of the patent application, wherein the selection solution of the data analysis server equipment, after generating the score of each solution, is selected according to the best score in each solution. The best solution.         The performance evaluation method according to item 9 of the scope of patent application, wherein the selection solution of the data analysis server equipment generates a score for each solution, and then uses the decision tree information profit method to screen the best solution.         The performance evaluation method according to item 9 of the scope of patent application, wherein, when selecting each of the characteristic elements, the energy consumption information of each of the vehicle equipment can be selected so that the best solution is to evaluate the performance of energy-saving driving.         The performance evaluation method according to item 9 of the scope of the patent application, in which, when selecting each of the characteristic elements, it is more possible to select an overspeed event, a rapid acceleration event, a sudden braking event, a sharp turn event, and a god of death of each vehicle equipment. At least one of event information such as an event, an unsafe distance event, or a lane departure event, so that the best solution is to evaluate dangerous driving performance.         The performance evaluation method according to item 9 of the scope of the patent application, wherein when selecting each of the characteristic elements, it is more possible to select a door closing abnormal event, a temperature abnormal event, a pre-cooling insufficient event, or an abnormal arrival time abnormality of each vehicle equipment. At least one kind of event information such as events, so that the best solution is to evaluate the performance of logistics professionals.