CN110322016A - Analysis server apparatus and its optimal combination analysis method - Google Patents
Analysis server apparatus and its optimal combination analysis method Download PDFInfo
- Publication number
- CN110322016A CN110322016A CN201810480525.8A CN201810480525A CN110322016A CN 110322016 A CN110322016 A CN 110322016A CN 201810480525 A CN201810480525 A CN 201810480525A CN 110322016 A CN110322016 A CN 110322016A
- Authority
- CN
- China
- Prior art keywords
- information
- target function
- gene order
- function type
- optimal combination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 173
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 194
- 238000004891 communication Methods 0.000 claims description 38
- 210000000349 chromosome Anatomy 0.000 claims description 26
- 230000035772 mutation Effects 0.000 claims description 24
- 230000013011 mating Effects 0.000 claims description 18
- 230000033764 rhythmic process Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 230000002045 lasting effect Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000452 restraining effect Effects 0.000 claims 1
- 238000005265 energy consumption Methods 0.000 abstract description 34
- 230000006399 behavior Effects 0.000 description 75
- 230000006870 function Effects 0.000 description 75
- 238000004422 calculation algorithm Methods 0.000 description 37
- 230000002123 temporal effect Effects 0.000 description 23
- 238000000034 method Methods 0.000 description 22
- 239000000446 fuel Substances 0.000 description 14
- 101150012509 sub gene Proteins 0.000 description 13
- 230000005540 biological transmission Effects 0.000 description 11
- 238000012546 transfer Methods 0.000 description 11
- 230000002068 genetic effect Effects 0.000 description 10
- 239000000463 material Substances 0.000 description 9
- 230000004048 modification Effects 0.000 description 8
- 238000012986 modification Methods 0.000 description 8
- 239000008186 active pharmaceutical agent Substances 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 239000002828 fuel tank Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 206010016256 fatigue Diseases 0.000 description 2
- 239000003502 gasoline Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000035479 physiological effects, processes and functions Effects 0.000 description 2
- 101150082072 14 gene Proteins 0.000 description 1
- 101150079123 Bad gene Proteins 0.000 description 1
- 241000270708 Testudinidae Species 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000003585 interneuronal effect Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/123—DNA computing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Traffic Control Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Genetics & Genomics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of analysis server apparatus and its optimal combination analysis method, the optimal combination analysis method first establish several gene orders in initial phase, then with these gene orders are mated, are mutated etc. and calculated, to generate best gene order.And the optimal combination analysis method can be applied to energy consumption estimation, traffic information estimation, physiologic information estimation.
Description
Technical field
The present invention relates to a kind of relevant analysis technology of driving behavior, and in particular to a kind of analysis server
Equipment and its optimal combination analysis method.
Background technique
The report of researching and analysing of TaiWan, China research institute for economics is pointed out, in the cost knot of road haulage industry and Bus Transportation industry
In structure ratio, fuel material cost accounts for 24% ~ 29% in each year statistics.It follows that fuel material cost is the main of vehicle
On road haulage industry, fuel material cost is higher than wages and fringe benefit cost, and position for one of cost factor, especially reaction
Occupy the first place in cost structure.Therefore, if a kind of system and method that can monitor fuel material consumption, Jiang Nengyou can be developed
Cope with this problem in effect ground.
In the prior art, although having the vehicle class using historical summary, oil meter voltage, running speed to obtain and school
The technology of positive oil mass value also has and utilizes detecting battery voltage and the technology to calculate vehicle oil consumption, or time of diagnosis fuel tank
Present the technology etc. of oil mass data.However, these prior arts respectively lack effective feedback method, or road network can not be passed through
Traffic state, driver's difference etc. is because of fuel material cost needed for usually Synthesize estimation carrying trade, it appears respectively have missing, still
It needs to be improved.
Summary of the invention
The present invention provides a kind of analysis server apparatus and its optimal combination analysis method, comprehensively considers driving behavior
Traffic information or physiologic information, to provide optimal assessment information.
Optimal combination analysis method of the invention, suitable for analyzing the information of driving behavior reaction.This optimal combination point
Analysis method includes the following steps.Gene order is generated, each gene order includes several chromosomes, and these chromosomes and driving are gone
It is related for the statistical magnitude of the assessment information caused by different time points, and each statistical magnitude is that letter is assessed under different time points
Breath meets the quantity of numerical intervals.Traffic information or physiologic information that driving behavior is reacted are input to fitness function formula, with
The score of these gene orders is calculated, and these gene orders are the weighted values as fitness function formula.By these gene orders
Option program, mating program and mutation program are carried out, and generates best base because of sequence when the convergence of the score of these gene orders
Column, and this best gene order is the assessment information aggregate of driving behavior.
On the other hand, analysis server apparatus of the invention, including communication module group, reservoir and processor.Communication
Mould group receives the traffic information or physiologic information that driving behavior is reacted.Reservoir recording traffic information or physiologic information and number
A mould group.Processor couples communication module group and reservoir, and those of access and execute stored by reservoir mould group.And those moulds
Group includes optimal combination analysis module.The optimal combination analysis module executes the following steps.Generate gene order, each gene order
Comprising several chromosomes, and the statistical magnitude phase of these chromosomes and assessment information caused by driving behavior in different time points
It closes, and each statistical magnitude is the quantity assessed information under different time points and meet numerical intervals.The friendship that driving behavior is reacted
Communication breath or physiologic information are input to fitness function formula, and to calculate the score of these gene orders, and these gene orders are to make
For the weighted value of fitness function formula.These gene orders are subjected to option program, mating program and mutation program, and work as these bases
Because generating best gene order when the score of sequence is restrained, and this best gene order is the assessment information collection of driving behavior
It closes.
Based on above content, the embodiment of the present invention can improve simple genetic algorithms, first establish in initial phase multiple excellent
Good gene order, then the calculating such as with multiple gene order mated, be mutated generate most suitable gene order.And this
The simple genetic algorithms of improvement is planted in combination with the fitness function formula of neural network.The embodiment of the present invention can be applied to traffic information and life
Information estimation is managed, and using gene order as the weighted value of fitness function formula, to obtain best gene order.
In order to which features described above and advantage of the invention can be clearer and more comprehensible, embodiment is hereafter especially enumerated, and combine attached
Figure is described in detail as follows.
Detailed description of the invention
Fig. 1 is the system architecture diagram of an embodiment according to the present invention.
Fig. 2 is the flow chart of the optimal combination analysis method of an embodiment according to the present invention.
Fig. 3 is the schematic diagram of the fitness function formula of an embodiment according to the present invention.
Fig. 4 is the schematic diagram of the fitness function formula of another embodiment according to the present invention.
Fig. 5 is that the gene order of an embodiment according to the present invention generates the flow chart of algorithm.
Fig. 6 is the flow chart of the assessment algorithm of the traffic information related evaluation information of an embodiment according to the present invention.
Fig. 7 is the schematic diagram of the relevant fitness function formula of traffic information of an embodiment according to the present invention.
Fig. 8 is the flow chart of the assessment algorithm of the physiologic information related evaluation information of an embodiment according to the present invention.
Fig. 9 is the timing statistical chart of the rhythm of the heart value of an embodiment according to the present invention.
Figure 10 is the schematic diagram of the relevant fitness function formula of physiologic information of an embodiment according to the present invention.
Symbol description:
1: vehicle arrangement;
10,20,30,40: communication module group;
12,22,32: middleware mould group;
14: positioning module;
20: user equipment;
24: user interface;
34: optimal combination analysis module;
40: library apparatus;
42: operation mould group;
44: storage mould group;
S210 ~ S220, S510 ~ S515, S610 ~ S612, S810 ~ S812: step;
~: driving behavior quantity;
、w 1 ~w n : gene order;
: total energy quantity consumed;
~、~、~、~: chromosome;
~: traffic information;
t 0 ~t n : time factor.
Specific embodiment
Fig. 1 is the system architecture diagram of an embodiment according to the present invention, please refers to Fig. 1, this system includes at least several vehicles
Equipment 1, several user equipmenies 2, analysis server apparatus 3 and library apparatus 4.
Vehicle arrangement 1 can be automobile, locomotive, bus or train.In the present embodiment, vehicle arrangement 1 includes at least fixed
Position mould group 14, middleware mould group 12 and communication module group 10.
Positioning module 14 can support global positioning system (for example, GPS, the Big Dipper, GALILEO positioning system etc.) or wireless
Network signal positioning (for example, base station positioning, Wi-Fi positioning etc.) method, and obtain location information and vehicle speed information.At this
In embodiment, positioning module 14 can support global positioning system, can obtain the latitude and longitude coordinates of vehicle arrangement by satellite signals
And vehicle speed information.
Communication module group 10 can support wireless network transmissions, and can establish user equipment 2 and analysis server apparatus 3 it
Between communication.In this embodiment, communication module group 10 can support 4G(Long Term Evolution (Long Term Evolution,
LTE it)) communicates, to connect 4G network, and establishes the communication connection between analysis server apparatus 3.
Middleware mould group 12 be stored in the reservoir (for example, hard disk, memory, buffer etc.) of vehicle arrangement 1 and by
Reason device (for example, CPU, chip, microprocessor etc.) executes after being loaded into, and supports hypertext transfer protocol (HyperText
Transfer Protocol, HTTP) or message sequence telemetering transmission (Message Queuing Telemetry
Transport, MQTT) or the transport protocols such as limited applications agreement.Vehicle arrangement 1 can pass through communication mould with middleware mould group 12
Group 10 is connect with analysis server apparatus 3, to transmit vehicle facility information, traffic information and/or physiologic information to data
Analysis server equipment 3.Vehicle arrangement information may include car number, vehicle model, driver's number, temporal information, position
Information, vehicle speed information etc..Traffic information can be hourage, vehicle flowrate, speed etc..Physiologic information can be rhythm of the heart value, the heart
Restrain variate-value etc..In this embodiment, middleware mould group 12 can support hypertext transfer protocol and tool as state transfer
(Representational State Transfer, REST), and middleware mould group 12 can call analysis server and set
Standby 3 Application Program Interface (Application Program Interfaces, APIs), and pass through communication module group 10 for vehicle
Facility information, traffic information and/or physiologic information are sent to analysis server in a manner of periodically or non-periodically
Equipment 3.
In this embodiment, vehicle arrangement 1 has car number, vehicle model and driver's number.Assuming that in system
Shared CNPlatform vehicle arrangement, TNKind vehicle model, DNPosition driver, vehicle arrangement 1 can be every the vehicle arrangement letters of transmission in 30 seconds
Breath, traffic information and/or physiologic information to analysis server apparatus 3, and each vehicle arrangement 1 is needed comprising identification
Its identification documents can be inserted into identity recognition device by the driver of device, each vehicle arrangement 1, to obtain driver's identity letter
Breath.
As shown in Table (1).Such as: the vehicle arrangement 1 that driver 1 drives car number 1 in 2015/01/01, vehicle arrangement
1 vehicle model is vehicle model 1, and vehicle arrangement 1 can obtain vehicle arrangement 1 in 06:00:00 by positioning module 14
Location information (that is, longitude 102.5423383 degree and 24.09490167 degree of latitude) and vehicle speed information (i.e. 44 kilometers of speed per hour/small
When), and the REST APIs of analysis server 3 can be called by middleware mould group 12, and vehicle arrangement information is sent to
Analysis server 3.
Table (1) vehicle arrangement information
。
User equipment 2 can be the equipment such as smart phone, tablet computer, host computer, laptop.User equipment 2
Including at least user interface 24, middleware mould group 22 and communication module group 20.
User interface 24 can be presented by display (for example, LCD, LED, OLED display etc.), to be supplied to user behaviour
Make user equipment 2, and obtains car number, temporal information, energy information and other assessment information of user's input, energy information
It can be oil mass information or information about power, and can be to 3 query analysis of analysis server apparatus as a result, and needing to connect in user
Mouth 24 shows this analysis result.
Communication module group 20 can support any kind of wireless network transmissions or cable-network transmission, and can establish user equipment
Communication between 2 and analysis server apparatus 3.In this embodiment, communication module group can support 4G to communicate, user equipment
2 can connect 4G network by communication module group 20, and establish the communication connection between analysis server apparatus 3.
Middleware mould group 22 be stored in reservoir (for example, hard disk, memory, buffer etc.) and by processor (for example,
CPU, chip, microprocessor etc.) be loaded into after execute, and support hypertext transfer protocol or message sequence telemetering to transmit, or limited
The transport protocols such as application protocol, and can be connect by communication module group 20 with analysis server apparatus 3, to transmit vehicle volume
Number, temporal information and energy information to analysis server apparatus 3.Energy information needs to believe comprising oil mass information or electricity
Breath.And middleware mould group 22 can receive the analysis result of analysis server apparatus 3.In this embodiment, middleware
Mould group 22 can support hypertext transfer protocol and tool as state transfer, and user equipment 2 can call data by middleware mould group 22
The REST APIs of Analysis server equipment 3, and car number, temporal information and the energy that user is inputted in user interface 24
Information is sent to analysis server apparatus 3 by communication module group 20.It follows that user's equipment 2 can use to obtain user institute
The energy information of input and other assessment information, and it is sent to analysis server apparatus 3.
In this embodiment, user equipment 2 is for the operation of user's aperiodicity, and obtains user by user interface 24
Car number, temporal information and the oil mass information of input, then car number, temporal information and energy are transmitted by communication module group 20
Information (i.e. oil mass information) to analysis server apparatus 3 and its energy consumption estimates mould group, as shown in Table (2):
Table (2) fuel consumption information
。
In this embodiment, the vehicle arrangement 1 of car number 1 is public in 2015/01/05 18:51:00 oiling 43.04
It rises, user can operate user equipment 2 according to oiling invoice information, input car number (i.e. car number by user interface 24
1), temporal information (i.e. 2015/01/05 18:51:00) and oil mass information (i.e. 43.04 liters), and middleware mould group 22 can exhale
The REST APIs for being analysis server apparatus 3, by the car number, temporal information and energy information of input, (i.e. oil mass is believed
Breath) it is sent to analysis server apparatus 3.
In this embodiment, user equipment 2 receives input vehicle by user interface 24 for the operation of user's aperiodicity
Number, temporal information and information about power, then car number, temporal information and energy information are transmitted by middleware mould group 22
(i.e. information about power) to analysis server apparatus 3, as shown in Table (3):
Table (3) electric quantity consumption information
。
In this embodiment, the vehicle arrangement 1 of car number 2 charges 17.22 degree in 2015/01/05 12:50:00
(kilowatt-hour (1kWh)), user operate user equipment 2 according to charge information, input car number (i.e. by user interface 24
Car number 2), temporal information (i.e. 2015/01/05 12:50:00) and information about power (i.e. 17.22 degree), and middleware mould group
22 can call the REST APIs of analysis server apparatus 3, car number, temporal information and the energy information that will be inputted
(i.e. information about power) is sent to analysis server apparatus 3.
Analysis server apparatus 3 includes at least middleware mould group 32, communication module group 30 and optimal combination and analyzes mould
Group 34.In this embodiment, analysis server apparatus 3 needs support (SuSE) Linux OS, Microsoft Windows operation
System etc., and all types of servers such as web service servers can be built in its operating system.
Middleware mould group 32 be stored in reservoir (for example, hard disk, memory, buffer etc.) and by processor (for example,
CPU, chip, microprocessor etc.) be loaded into after execute, and support hypertext transfer protocol, message sequence telemetering transmission or limited answer
With transport protocols such as agreements.And analysis server apparatus 3 can pass through communication module group 30 and vehicle by middleware mould group 32
Equipment 1 and user's equipment 2 connect, to receive vehicle arrangement information, traffic information and/or the physiology of the transmission of vehicle arrangement 1
Information simultaneously receives the car number of the transmission of user equipment 2, temporal information, energy information, and transmittable message to vehicle arrangement 1 or
User's equipment 2, and need to store the vehicle arrangement information and energy information that receive to library apparatus 4.In this implementation
In example, middleware mould group 32 needs to operate using Tomcat web service servers, and can build several REST APIs for vehicle
Equipment 1 and user equipment 2 connect, and need to receive by hypertext transfer protocol vehicle arrangement information that vehicle arrangement 1 transmits,
Traffic information and/or physiologic information simultaneously receive the car number of the transmission of user equipment 2, temporal information, energy information, and transmittable
Message is to vehicle arrangement 1 or user's equipment 2, moreover it is possible to store the vehicle arrangement information and energy information that receive to data bank
Equipment 4.
Communication module group 30 can be supported any kind of cable-network transmission (for example, Ethernet, fiber optic network etc.), establish
Vehicle arrangement 1 and analysis server apparatus 3, user equipment 2 and analysis server apparatus 3 and library apparatus 4
With the communication transfer between analysis server apparatus 3.
Optimal combination analysis module 34 is stored in reservoir (for example, hard disk, memory, buffer etc.) and by processor
(for example, CPU, chip, microprocessor etc.) executes after being loaded into, and executable optimal combination of embodiment of the present invention analysis method (to
Subsequent embodiment is described in detail), collect vehicle arrangement information, traffic information and/or physiologic information that vehicle arrangement 1 is transmitted, user
Car number, temporal information and the energy information that equipment 2 is transmitted, and analyze each driving behavior consumption energy quantity and
Other assessment information.Driving behavior can be vehicle speed information, and optimal combination analysis module 34 can consume each driving behavior
Energy quantity store to library apparatus 4, and generate driving behavior energy consumption estimated information set.Alternatively, best group
Closing analysis module 34 may be based on the traffic information or physiologic information that driving behavior is reacted, and estimate corresponding assessment information
(for example, traffic congestion degree, driver's degree tired out etc.) is described in detail to subsequent embodiment.
Analysis server apparatus 3 needs to pass through communication module group 30 and external geography information by middleware mould group 32
Server connection inquires external geographic information server with REST APIs to obtain vehicle arrangement information and vehicle location letter
The corresponding road type of breath, and road type and vehicle arrangement information are merged into modification rear vehicle facility information, and will repair
Change rear vehicle facility information to store to library apparatus 4.This external geographic information server can be Google Map server
Or Hinet GeoWeb map server, as shown in Table (4):
Table (4) is stored to the modification rear vehicle facility information of library apparatus 4
。
Library apparatus 4 includes at least storage mould group 44, operation mould group 42 and communication module group 40.In this embodiment,
Library apparatus 4 need using Microsoft's structured query language (Structural Query Language, SQL) server,
The operation such as MySQL, PostgreSQL, inscriptions on bones or tortoise shells data bank server, MongoDB server, HBase server, and can pass through
Communication module group 40 receives and the data for the Analysis server equipment 3 that stores data.
Communication module group 40 can support any kind of cable-network transmission, establish library apparatus 4 and analysis service
Communication connection between device equipment 3.
Operation mould group 42(is for example, all types of processors or chip) analysis server can be received by communication module group 40
The requirement that equipment 3 is transmitted, and storage mould group 44 is accessed according to the requirement of acquirement.
Store mould group 44(for example, hard disk, memory or memory card etc.) can couple with operation mould group 42, and provide outside for
It stores data and the operation newly such as is increased, modified, deleted, inquired.In this embodiment, storage mould group 44 will store car number
(such as with the vehicle model table of comparisons (as shown in Table (5)), modification rear vehicle facility information (as shown in Table (4)), fuel consumption information
Shown in table (2)), electric quantity consumption information etc. (as shown in Table (3)), traffic information and physiologic information etc..
When wanting newly-increased vehicle arrangement 1, can be logged in by system operator the newly-increased corresponding car number of vehicle arrangement 1 and
Vehicle model is to car number and the vehicle model table of comparisons, and car number and the vehicle model table of comparisons can provide analysis clothes
Device equipment 3 of being engaged in establishes modification rear vehicle facility information after inquiring.
Table (5) car number and the vehicle model table of comparisons
。
In one embodiment, vehicle arrangement 1 also may include energy arrangement for detecting (not shown), energy detecting dress
Set can detecting vehicle equipment 1 energy information, energy information can be oil mass information or information about power, and energy information needs include
In vehicle arrangement information, and need vehicle arrangement information being sent to analysis by middleware mould group and communication module group
Server apparatus 3.
In addition, energy arrangement for detecting needs the oil mass information of periodically or non-periodically detecting vehicle equipment 1, and record vehicle
Car number, temporal information and the oil mass information of equipment 1, then car number, temporal information are transmitted by middleware mould group 12
With energy information (i.e. oil mass information) to analysis server apparatus 3, as shown in Table (6):
Table (6) fuel consumption information
。
In this embodiment, before 2015/01/01 06:00:00, the energy of the vehicle arrangement 1 of car number 3 is detectd
Surveying device and detecting the remaining fuel of fuel tank of vehicle arrangement 1 is 4 liters, and detects vehicle in 2015/01/01 06:00:00
The remaining fuel of fuel tank of equipment 1 is 3.973 liters, and the oil mass information that consumption can be calculated by energy arrangement for detecting is
0.027 liter, as shown in Table (6), and car number, temporal information and oil mass information can be sent to by middleware mould group 12
Analysis server apparatus 3.
And as shown in Table (7), in 2015/01/01 06:00:00, the energy of the vehicle arrangement 1 of car number 4 is detected
Device detects vehicle arrangement 1 and consumes in total between 2015/01/01 05:59:30 to 2015/01/01 06:00:00
0.013 degree (kilowatt-hour (1kWh)), the information about power that can record consumption is 0.013 degree, as shown in Table (7), and can be by vehicle
Number, temporal information and information about power are sent to analysis server apparatus 3 by middleware mould group 12.
Table (7) electric quantity consumption information
。
In this embodiment, user can not need to input car number, temporal information and oil by user interface 24
Information is measured, then car number, temporal information and energy information are transmitted to analysis server apparatus by middleware mould group 12
3。
In addition, 3 middleware mould group 32 of analysis server apparatus needs to receive vehicle arrangement 1 by communication module group 30
The car number of vehicle arrangement information, traffic information and/or physiologic information and vehicle arrangement 1, temporal information and energy information, and
Information those of will be received to store to library apparatus 4.The optimal combination analysis module 34 of analysis server apparatus 3 can
Optimal combination analysis method is executed, vehicle arrangement information, traffic information, physiologic information, vehicle that vehicle arrangement 1 is transmitted are collected
Number, temporal information and energy information, and analyze the energy quantity of each driving behavior consumption.The driving behavior can be vehicle
Fast information, analysis server apparatus 3 can simultaneously store the energy quantity that each driving behavior consumes to library apparatus 4.
And the analysis server apparatus 3 can also store data to library apparatus 4, then be held by analysis server apparatus 3
Row energy consumption estimation method calculates the energy quantity of each driving behavior consumption.
Based on above system framework, the present invention described further below applies several implementations of optimal combination analysis method
Example, to help to understand spirit of the invention.
One embodiment of the present of invention be applied to energy consumption estimation method, analysis server apparatus 3 it is best
Step performed by combinatory analysis mould group 34, which includes at least, collects driving behavior program, collects energy information program and optimal combination
Analyze program.
In collecting driving behavior program, vehicle arrangement information, traffic information and/or physiology are returned by vehicle arrangement 1 and believed
Breath to analysis server apparatus 3, then by analysis server apparatus 3 analyze vehicle arrangement information, traffic information and/or
Physiologic information, and vehicle arrangement information, traffic information and/or physiologic information are stored to library apparatus 4.Analysis service
Device equipment 3 can calculate every vehicle arrangement, each vehicle model, each road type and every driver in one section of period section
Various driving behavior quantity.
In collecting energy information program, energy information or other assessment information are returned to analysis by user equipment 2
Server apparatus 3 or by returning energy information after vehicle arrangement energy arrangement for detecting detected energy information to analysis server
Equipment 3, then store by 3 analysing energy information of analysis server apparatus, and by energy information and/or assessment information to data
Library facilities 4, and every vehicle arrangement 1, each vehicle type in one section of period section can be calculated by analysis server apparatus 3
Number, each road type, every driver energy consumption quantity and/or assess the statistical magnitude of information (for example, certain a road section
Vehicle number, the cumulative frequency of waking state etc.).
And in optimal combination analysis program, driving behavior quantity and energy consumption number are obtained by optimal combination analysis module 34
Amount, and simple genetic algorithms is executed by optimal combination analysis module 34 and analyzes the energy consumption quantity of each driving behavior, and is exported
Driving behavior energy consumption estimated information set or the assessment information aggregate of other driving behaviors.
It is worth noting that, vehicle arrangement 1, which also can be performed, collects driving behavior program, to obtain modification rear vehicle equipment letter
It ceases (as shown in Table (4)), and needs to count each according to the information such as vehicle arrangement, vehicle model, driver, road type and drive
Sail behavior quantity.The driving behavior can be vehicle speed information, and vehicle speed information is defined as v.In this embodiment, by speed per hour section
The statistical magnitude separated using 10 kilometers is limited as driving behavior, but not with 10 kilometers.
The each driving behavior quantity for modifying each vehicle arrangements 1 in 2015 of rear vehicle facility information statistics, such as table (8)
It is shown.Car number 1 amounts in the data stroke count that the vehicle speed information of return in 2015 is 0 kilometer/hour to be hadPen, speed letter
Ceasing between 0 ~ 10 kilometer/hour of data stroke count is total hasPen ... vehicle speed information is greater than 120 kilometers/hour of data pen
Number is total to be hadPen.The rest may be inferred, vehicle arrangementC N The data pen for being 0 kilometer/hour in the vehicle speed information of return in 2015
Number is total to be hadData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.
Table (8) counts each driving behavior quantity according to car number 1
。
The each driving behavior quantity for modifying various vehicle models in 2015 of rear vehicle facility information statistics, such as table (9)
It is shown.Vehicle model 1 amounts in the data stroke count that the vehicle speed information of return in 2015 is 0 kilometer/hour to be hadPen, speed letter
Ceasing between 0 ~ 10 kilometer/hour of data stroke count is total hasPen ... vehicle speed information is greater than 120 kilometers/hour of data pen
Number is total to be hadPen.The rest may be inferred, vehicle model TNThe data pen for being 0 kilometer/hour in the vehicle speed information of return in 2015
Number is total to be hadData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.
Table (9) counts each driving behavior quantity according to vehicle model
。
The each driving behavior quantity for modifying each drivers in 2015 of rear vehicle facility information statistics, such as table (10) institute
Show.Driver 1 amounts in the data stroke count that the vehicle speed information of return in 2015 is 0 kilometer/hour to be hadPen, vehicle speed information are situated between
Amounting in 0 ~ 10 kilometer/hour of data stroke count hasData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total
In respect ofPen.The rest may be inferred, driver DNAmounting in the data stroke count that the vehicle speed information of return in 2015 is 0 kilometer/hour hasPen, vehicle speed information have between 0 ~ 10 kilometer/hour of data stroke count is totalPen ... vehicle speed information be greater than 120 kilometers/
The data stroke count of hour is total to be hadPen.
Table (10) counts each driving behavior quantity according to driver
。
The each driving behavior quantity for modifying different kinds of roads types in 2015 of rear vehicle facility information statistics, such as table (11)
It is shown.Road type 1 amounts in the data stroke count that the vehicle speed information of return in 2015 is 0 kilometer/hour to be hadPen, speed letter
Ceasing between 0 ~ 10 kilometer/hour of data stroke count is total hasPen ... vehicle speed information is greater than 120 kilometers/hour of data pen
Number is total to be hadPen.The rest may be inferred, road type RNThe data stroke count for being 0 kilometer/hour in the vehicle speed information of return in 2015
It is total to haveData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.
Table (11) counts each driving behavior quantity according to road type
。
Modify each driving behavior of each vehicle arrangement 1 and each driver in 2015 of rear vehicle facility information statistics
Quantity, as shown in table (12).Driver 1 drives the money that vehicle arrangement 1 is 0 kilometer/hour in the vehicle speed information of return in 2015
Material stroke count is total to be hadPen, vehicle speed information have between 0 ~ 10 kilometer/hour of data stroke count is totalPen ... vehicle speed information
Data stroke count greater than 120 kilometers/hour, which amounts to, to be hadPen.Driver 2 drives car number 1 in the speed of return in 2015
The data stroke count that information is 0 kilometer/hour is total to be hadPen, vehicle speed information are total between 0 ~ 10 kilometer/hour of data stroke count
HaveData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.Driver 1 drives car number
The data stroke count that 2 vehicle speed informations returned in 2015 are 0 kilometer/hour is total to be hadPen, vehicle speed information are between 0 ~ 10 public affairs
In/the data stroke count of hour is total hasData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be had
Pen.The rest may be inferred, driverD N Drive car numberC N The data stroke count for being 0 kilometer/hour in the vehicle speed information of return in 2015
It is total to haveData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.
Table (12) counts each driving behavior quantity according to vehicle arrangement and driver
。
Modify various vehicle models in 2015 of rear vehicle facility information statistics and each driving behavior of each driver
Quantity, as shown in table (13).Driver 1 drives the money that vehicle model 1 is 0 kilometer/hour in the vehicle speed information of return in 2015
Material stroke count is total to be hadPen, vehicle speed information have between 0 ~ 10 kilometer/hour of data stroke count is totalPen ... speed letter
Data stroke count of the breath greater than 120 kilometers/hour is total to be hadPen.Driver 2 drives vehicle model 1 in the vehicle of return in 2015
The data stroke count that fast information is 0 kilometer/hour is total to be hadPen, vehicle speed information are between 0 ~ 10 kilometer/hour of data stroke count
It is total to haveData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.Driver 1 drives
Vehicle model 2 amounts in the data stroke count that the vehicle speed information of return in 2015 is 0 kilometer/hour to be hadPen, vehicle speed information are situated between
Amounting in 0 ~ 10 kilometer/hour of data stroke count hasPen ... vehicle speed information is greater than 120 kilometers/hour of data stroke count
It is total to havePen.The rest may be inferred, driver DNDrive vehicle model TNIn 2015 return vehicle speed information be 0 kilometer/it is small
When data stroke count total haveData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be had
Pen.
Table (13) counts each driving behavior quantity according to vehicle model and driver
。
Modify each driving behavior that rear vehicle facility information counts each vehicle arrangement 1 and different kinds of roads type in 2015
Quantity, as shown in table (14).The money that vehicle arrangement 1 is 0 kilometer/hour in the vehicle speed information of return in 2015 in road type 1
Material stroke count is total to be hadPen, vehicle speed information have between 0 ~ 10 kilometer/hour of data stroke count is totalPen ... speed letter
Data stroke count of the breath greater than 120 kilometers/hour is total to be hadPen.Car number 1 is in road type 2 in the vehicle of return in 2015
The data stroke count that fast information is 0 kilometer/hour is total to be hadPen, vehicle speed information are between 0 ~ 10 kilometer/hour of data stroke count
It is total to haveData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.Car number 2 is in road
Road Class1 amounts in the data stroke count that the vehicle speed information of return in 2015 is 0 kilometer/hour to be hadPen, vehicle speed information are between 0
~ 10 kilometers/hour of data stroke count is total to be hadData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total
HavePen.The rest may be inferred, vehicle arrangement CNIn road type RNIn the vehicle speed information of return in 2015 be 0 kilometer/hour
Data stroke count is total to be hadData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.
Table (14) counts each driving behavior quantity according to vehicle arrangement and road type
。
Modify each drivers in 2015 of rear vehicle facility information statistics and each driving behavior of different kinds of roads type
Quantity, as shown in table (15).Driver 1 drives those vehicle arrangements 1 in road type 1
0 kilometer/hour of data stroke count is total to be hadPen, vehicle speed information have between 0 ~ 10 kilometer/hour of data stroke count is totalData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.Driver 1 drives those vehicles
Equipment 1, which amounts in road type 2 in the data stroke count that the vehicle speed information of return in 2015 is 0 kilometer/hour, to be hadPen, speed
Information has between 0 ~ 10 kilometer/hour of data stroke count is totalPen ... vehicle speed information is greater than 120 kilometers/hour of data
Stroke count is total to be hadPen.Driver 2 drives those vehicle arrangements 1 in road type 1
0 kilometer/hour of data stroke count is total to be hadPen, vehicle speed information have between 0 ~ 10 kilometer/hour of data stroke count is totalData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.The rest may be inferred, driverD N It drives
Those vehicle arrangements 1 are sailed in road typeR N Amounting in the data stroke count that the vehicle speed information of return in 2015 is 0 kilometer/hour hasData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen.
Table (15) counts each driving behavior quantity according to driver and road type
。
It should be noted that statistics modification rear vehicle facility information generates each driving behavior quantity, it is not limited to using year
Part, need to be counted using period section, time interval need comprising year, season, the moon, week, day, when, minute, second etc..
By taking month as an example: the data stroke count that the vehicle speed information that car number 1 is returned in January, 2015 is 0 kilometer/hour is total
In respect ofThe data stroke count that the vehicle speed information that pen, car number 1 were returned in the M month in 2015 is 0 kilometer/hour is total to be had
The summation in pen and each month in year is equal to year whole year summation (i.e.), and so on;Vehicle model 1 is in 2015
The data stroke count that the vehicle speed information of return in January in year is 0 kilometer/hour is total to be hadPen, vehicle model 1 were returned in the M month in 2015
The data stroke count that the vehicle speed information of report is 0 kilometer/hour is total to be hadThe summation in pen and each month in year is equal to year whole year
Summation is (i.e.), and so on;The vehicle speed information that driver 1 returns in January, 2015 is 0 kilometer/hour
Data stroke count is total to be hadThe data stroke count that the vehicle speed information that pen, driver 1 returned in the M month in 2015 is 0 kilometer/hour is total
In respect ofThe summation in pen and each month in year is equal to year whole year summation (i.e.), and so on;Road class
The data stroke count that the vehicle speed information that type 1 is returned in January, 2015 is 0 kilometer/hour is total to be hadPen, road type 1 in
The data stroke count that the vehicle speed information that the M month in 2015 is returned is 0 kilometer/hour is total to be hadThe summation etc. in pen and each month in year
In year whole year summation (i.e.), and so on;Driver 1 drives what car number 1 was returned in January, 2015
The data stroke count that vehicle speed information is 0 kilometer/hour is total to be hadPen, driver 1 drive car number 1 and return in the M month in 2015
The data stroke count that the vehicle speed information of report is 0 kilometer/hour is total to be hadIt is annual that the summation in pen and each month in year is equal to year
Spend summation (i.e.), and so on;Driver 1 drives the speed letter that vehicle model 1 is returned in January, 2015
The data stroke count that breath is 0 kilometer/hour is total to be hadPen, driver 1 drive the vehicle that vehicle model 1 was returned in the M month in 2015
The data stroke count that fast information is 0 kilometer/hour is total to be hadThe summation in pen and each month in year is equal to year whole year summation
(i.e.), and so on;Car number 1 is 0 in the vehicle speed information that road type 1 is returned in January, 2015
Kilometer/hour data stroke count total haveThe vehicle speed information that pen, car number 1 are returned in road type 1 in the M month in 2015
Have for 0 kilometer/hour of data stroke count is totalThe summation in pen and each month in year is equal to year whole year summation (i.e.), and so on;Driver 1 drives what those vehicle arrangements 1 were returned in road type 1 in January, 2015
The data stroke count that vehicle speed information is 0 kilometer/hour is total to be hadPen, driver 1 drive those vehicle arrangements 1 in road class
The data stroke count that the vehicle speed information that type 1 was returned in the M month in 2015 is 0 kilometer/hour is total to be hadPen and each month in year
Summation be equal to year whole year summation (i.e.), and so on.
It is executed by vehicle arrangement 1 and collects energy information program, need to obtain fuel consumption information (such as table to user equipment 2
(2) shown in) or electric quantity consumption information (as shown in Table (3)), and obtain and combine car number and the vehicle model table of comparisons (such as table (5)
It is shown) and modification rear vehicle facility information (as shown in Table (4)) need to use according to car number, vehicle model, driver etc.
Period section carries out statistics energy consumption quantity, time interval need comprising year, season, the moon, week, day, when, minute, second etc..
Alternatively, needing when executing collection energy information program by analysis server apparatus 3 to vehicle arrangement 1
Energy arrangement for detecting obtains fuel consumption information (as shown in Table (6)) or electric quantity consumption information (as shown in Table (7)), and needs to tie
Close car number and the vehicle model table of comparisons (as shown in Table (5)) and modification rear vehicle facility information (as shown in Table (4)).Data
Analysis server equipment 3 can be according to information such as car number, vehicle model, drivers, and one section of period section can be used and carry out
Count energy consumption quantity, and the time interval may include year, season, the moon, week, day, when, minute, second etc..
The available time is time interval, and energy consumption information can be fuel consumption information or electric quantity consumption information.Money
Material Analysis server equipment 3 simultaneously can be counted according to car number, vehicle model, driver respectively and can be obtained:
Vehicle arrangement 1 is in whole year total energy quantity consumed in 2015, vehicle arrangement N is in whole year total energy in 2015
Quantity consumed is, and so on;
Vehicle model 1 is in whole year total energy quantity consumed in 2015, vehicle model N is in whole year total energy in 2015
Quantity consumed is, and so on;
In the energy consumption quantity for calculating vehicle model, analysis server apparatus 3 can be according to car number and vehicle model
The table of comparisons takes out the car number (i.e. vehicle arrangement) of same vehicle model, by those vehicle arrangements 1 corresponding to the time interval
Energy consumption quantity aggregation become vehicle model energy consumption quantity.
Driver 1 is in whole year total energy quantity consumed in 2015, driver N is in whole year total energy in 2015
Quantity consumed is, and so on;
Driver 1 drives vehicle arrangement 1 in whole year total energy quantity consumed in 2015, driver N1Drive vehicle
Equipment N2It is in whole year total energy quantity consumed in 2015, and so on;
Driver 1 drives vehicle model 1 in whole year total energy quantity consumed in 2015, driver N1Drive vehicle
Model N2It is in whole year total energy quantity consumed in 2015, and so on.
Analysis server apparatus 3 can be time interval with month, count energy consumption information, energy consumption information can
To be fuel consumption information or electric quantity consumption information, and it is respectively necessary for being united according to car number, vehicle model, driver
Meter:
Vehicle arrangement 1 is in January, 2015 total energy quantity consumed, vehicle arrangement N in M month total energy in 2015 consume number
Amount isAnd the summation in each month in year is equal to year whole year summation (i.e.), and so on;
Vehicle model 1 is in January, 2015 total energy quantity consumed, vehicle model N in M month total energy in 2015 consume number
Amount isAnd the summation in each month in year is equal to year whole year summation (i.e.), and so on;
Driver 1 is in January, 2015 total energy quantity consumed, driver N in M month total energy quantity consumed in 2015 beAnd the summation in each month in year is equal to year whole year summation (i.e.), and so on;
Driver 1 drive vehicle arrangement 1 in January, 2015 total energy quantity consumed be, driver N1Drive vehicle arrangement
N2It is in M month total energy quantity consumed in 2015And the summation in each month in year is equal to year whole year summation (i.e.), and so on;
Driver 1 drive vehicle model 1 in January, 2015 total energy quantity consumed be, driverN 1Drive vehicle modelN 2In 2015MMonth total energy quantity consumed isAnd the summation in each month in year is equal to year whole year summation (i.e.), and so on.
After obtaining driving behavior quantity and energy consumption quantity, optimal combination point is can be performed in optimal combination analysis module 34
Analysis method, referring to Fig. 2, Fig. 2 is the flow chart of optimal combination analysis method.
Optimal combination analysis module 34 establishes baseline file (step S210), the baseline file include driving behavior quantity,
Energy consumption quantity, female group's gene order quantity, evolution number, repeatedly band number, mating rate、
Mutation rate.Evolution numberInitial value is 0, and every simple genetic algorithms of execution (may include selection, mate and dash forward
Become program), then the number that develops adds one, until evolution numberEqual to repeatedly band number。
Optimal combination analysis module 34 then executes fitness function formula and generates algorithm (step S211), to generate fitness function
Formula, this fitness function formula is used to calculate the score of gene order, and each gene order includes several chromosomes.These chromosomes
With the system of assessment information caused by driving behavior in different time points (for example, consumption energy, vehicle fleet size, degree tired out etc.)
Count number is related, and each statistical magnitude is the quantity assessed information under different time points and meet numerical intervals.
Optimal combination analysis module 34 then executes gene order and generates algorithm (step S212), according to fitness function formula
Required chromosome quantitative generates gene order, and can be according to female group's gene order quantityGenerate several genes of female group
Sequence.
Optimal combination analysis module 34 then executes gene order score computational algorithm (step S213), by gene order
And vehicle speed information, traffic information or the physiologic information that driving behavior is reacted are input to fitness function formula, and calculate gene order
Score, and those gene orders are then used as the weighted value of fitness function formula.
Then whether discriminant function formula restrains (step S214) to optimal combination analysis module 34, when evolution numberDeng
In repeatedly band numberWhen, optimal combination analysis module 34 exports best gene order, this best gene order is to drive
Sail behavior energy consumption estimated information set or the assessment information aggregate of other driving behaviors.On the other hand, when evolution numberLess than repeatedly band numberWhen, optimal combination analysis module 34 will develop numberIn addition one.
Optimal combination analysis module 34 replicates those gene sequences followed by gene order selection algorithm (that is, option program)
Two groups of gene orders (step S216) in column, to form two groups of mother's gene orders.
Optimal combination analysis module 34 then executes gene order mating algorithm (step S217, i.e. mating program), according to
Mating rate, two groups of mother's gene orders are mated, two groups of sub- gene orders of the first generation are generated.
Optimal combination analysis module 34 then executes gene order mutation algorithm (step S218, i.e. mutation program), with according to
According to mutation rate, and two groups of sub- gene orders of the first generation are executed into mutation, to form the sub- gene order of two second generations.
And optimal combination analysis module 34 those of replaces the sub- gene order of newly generated two groups of second generations in female group
Two groups of gene orders in gene order, and those substituted gene orders correspond to two most bad score (steps
S219).
Optimal combination analysis module 34 can also obtain two groups of new gene sequences (step S220) again, and with gene order point
Number calculates algorithm and calculates the score of those new gene sequences, then executes a simple genetic algorithms.
As an example it is assumed that female group's gene order quantity in baseline fileIt is set as 14, evolution numberInitial value is 0, repeatedly with numberFor 1000, mating rateFor 100%, mutation rateIt is 7%.
Driving behavior quantity, which can be, counts each driving behavior quantity (as shown in Table (8)) according to vehicle arrangement, according to
Vehicle model counts each driving behavior quantity (as shown in Table (9)), counts each driving behavior quantity (such as table according to driver
(10) shown in), each driving behavior quantity (such as shown in table (11)) is counted according to road type, according to vehicle arrangement and driver
Each driving behavior quantity (such as shown in table (12)) is counted, each driving behavior quantity is counted according to vehicle model and driver
(such as shown in table (13)) counts each driving behavior quantity (such as shown in table (14)) according to vehicle arrangement and road type, according to,
Or count each driving behavior quantity according to driver and road type (such as shown in table (15)).
Energy consumption quantity can be vehicle arrangement energy consumption quantity, vehicle model energy consumption quantity, vehicle model
Energy consumption quantity, driver's energy consumption quantity, vehicle arrangement and driver's energy consumption quantity or vehicle model and driving
People's energy consumption quantity.
In this embodiment, driving behavior quantity is each driving behavior number counted according to vehicle arrangement and driver
Amount (such as shown in table (12)), and energy consumption quantity is vehicle arrangement and driver's energy consumption quantity.
By taking driver i drives vehicle arrangement j as an example: driver i drives vehicle arrangement j in the vehicle speed information of return in 2015
Have for 0 kilometer/hour of data stroke count is totalPen, vehicle speed information have between 0 ~ 10 kilometer/hour of data stroke count is totalData stroke count of pen ... the vehicle speed information greater than 120 kilometers/hour is total to be hadPen;Driver i drives vehicle and sets
The data stroke count that the vehicle speed information that standby j is returned in January, 2015 is 0 kilometer/hour is total to be hadPen is returned for 2 months 2015
Vehicle speed information be 0 kilometer/hour data stroke count total haveThe vehicle speed information of pen ... in December, 2015 return is 0
Kilometer/hour data stroke count total haveThe summation in pen and each month in year is equal to year whole year summation (i.e.);Driver i drives vehicle arrangement j in whole year total energy quantity consumed in 2015, drive
People i drive vehicle arrangement j in January, 2015 total energy quantity consumed be, vehicle arrangement j was in 2015 for driver i driving
M month total energy quantity consumed isAnd the summation in each month in year is equal to year whole year summation (i.e.
).
The all-year driving behavior quantity that driver 1 drives vehicle arrangement 1 in this embodiment is one group of set, and driver 1 drives the annual vapour of vehicle arrangement 1
Oil consumption quantity is 10921.364 liters.
And generated in algorithm in fitness function formula, optimal combination analysis module 34 can produce a multiple linear functional expression
As fitness function formula, and this fitness function formula can be used to calculate gene order score s.In this embodiment, with driver i
For driving vehicle arrangement j, referring to Fig. 3, fitness function formula are as follows:, wherein gene
The lower sequence score s the better in this embodiment, i.e., optimum solution is。
Gene order is one group of set, gene order include 14 chromosomes (i.e.
Cardinality of a set), wherein the 1st chromosome is, chromosome can be floating-point encoding, and can be considered and drive
It sails people i and drives energy consumption quantity corresponding to the idling (vehicle speed information is 0 kilometer/hour) of vehicle arrangement j.
In addition, generating in algorithm in gene order, optimal combination analysis module 34 can be according to needed for fitness function formula
Chromosome quantitative generates gene order, and can be according to female group's gene order quantityGenerate multiple gene orders of female group.
Female group's gene order quantity by taking driver i drives vehicle arrangement j as an example, in this exampleIt is 14,
And chromosome quantitative is 14, gene order, which generates algorithm, will be randomly generated 14 gene orders.These gene orders include
14 chromosomes, and optimal combination analysis module 34 is using those gene orders as female group's gene order.
In addition, those gene orders are stated in this embodiment so that driver i drives vehicle arrangement j as an example are as follows:
Gene order 1 is;
Gene order 2 is, and so on;
Gene order 14 is。
Table (16) mother's group's gene order
。
In this embodiment, female group's gene order is randomly generated, and those chromosomes are the numerical value of floating-point encoding.With
For driver 1 drives vehicle arrangement 1, as shown in table (17), those gene orders are stated in this embodiment are as follows:
Gene order 1 is;
Gene order 2 is, and so on;
Gene order 14 is。
Female group's gene order of 17 driver 1 of table driving vehicle arrangement 1
。
And calculated in algorithm in gene order score, optimal combination analysis module 34 can will be each in female group's gene order
Gene order is input to fitness function formula, and calculates gene order score.With driveri
Drive vehicle arrangementjFor, gene order score corresponding to gene order 1 is、
Gene orderhCorresponding gene order score is。
By taking driver 1 drives vehicle arrangement 1 as an example, gene order corresponding to each gene order of female group's gene order
Score:
;
;
The rest may be inferred,
。
After optimal combination analysis module 34 has executed gene order score computational algorithm, evolution number is judgedIt is
It is no to be equal to repeatedly band number.If evolution numberEqual to repeatedly band number, then optimal combination analysis module
The 34 best gene orders of output, this best gene order is wherein one group of gene order of female group's gene order, and this
The best gene order score of gene order corresponding (having), best gene order is driving behavior energy consumption estimated information collection
It closes.On the other hand, when evolution numberLess than repeatedly band numberWhen, optimal combination analysis module 34 will develop numberIn addition one.
It include gene order selection algorithm (or option program), gene order mating during said gene algorithm
Algorithm (or mating program) and gene order mutation algorithm (or mutation program).
In this embodiment, gene order selection algorithm is wheel disc method (roulette wheel selection), most
Good combinatory analysis mould group 34 can replicate two groups in female group's gene order using wheel disc method, and form two groups of mother's gene orders.With
Driver 1 drive vehicle arrangement 1 for, optimal combination analysis module 34 select gene order 1 () and gene order 2 (), and replicated as first generation mother gene sequence
Column, as shown in table (18):
(18) first godmother's gene order of table
。
In this embodiment, optimal combination analysis module 34, can root during executing gene order mating algorithm
According to mating rateAnd single-point mating (1-point crossover) is carried out, and assume to mate point (crossover point)With
Machine is produced as 2, and after carrying out two groups of gene order mating process, first godmother's gene order changes into first generation subbase because of sequence respectively
Column (such as shown in table (19)):
The sub- gene order 1 of the first generation、
The sub- gene order 2 of the first generation。
The sub- gene order of table (19) first generation
。
In this embodiment, optimal combination analysis module 34, can during executing gene order mutation algorithm
According to mutation rateBinary vector (binary vector) is randomly generated, to execute two gene sequences
Column mutation process.Assuming that, then the numerical value of n-th of chromosome can become another number of non-script numerical value in gene order
Value, and another numerical value needs are randomly generated.For example, the first generation subbase changed by above-mentioned first godmother gene order because
Sequence is assumed as second godmother's gene order (such as shown in table (20)), then
It is changed into the sub- gene order of the second generation after the second mutated process of godmother's gene order, as shown in table (21).
(20) second godmother's gene order of table
。
The sub- gene order of table (21) second generation
。
Optimal combination analysis module 34 those of then replaces the sub- gene order of newly generated two groups of second generations in female group
Two groups of gene orders in gene order, and those substituted gene orders correspond to two in most bad score.At this
In a embodiment, by taking driver 1 drives female group's gene order of vehicle arrangement 1 as an example, the corresponding gene order of gene order 2
Score is that the corresponding gene order score of 1062.54674, gene order 14 is 1009.53678, and two gene orders are in female group
The most bad gene order of score.Optimal combination analysis module 34 will be replaced in female group with the sub- gene order of two groups of second generations
Wherein two groups of those gene orders, after substitution shown in result such as table (22).
Driver 1 after table (22) evolution bout drives female group's gene order of vehicle arrangement 1
。
Optimal combination analysis module 34 can also calculate algorithm with gene order score and calculate other those gene orders
Score, and judge evolution numberWhether repeatedly band number is equal to.If evolution numberEqual to repeatedly band
Number, then optimal combination analysis module 34 exports best gene order.And if evolution numberLess than repeatedly band
Number, then optimal combination analysis module 34 will develop numberIn addition one, then execute a simple genetic algorithms.
In this embodiment, after optimal combination analysis module 34 will execute gene order score calculating algorithm calculating evolution bout
Driver 1 drive vehicle arrangement 1 female group's gene order two newly-increased gene order (i.e. gene order 2 and gene orders
14) the corresponding gene order score of two newly-increased gene orders can, be obtained:
;
。
When evolution numberEqual to repeatedly band numberWhen, optimal combination analysis module 34 exports best base because of sequence
Column, this best gene order is one of gene order of female group's gene order and gene order corresponds to best gene order point
Number, and best gene order is driving behavior energy consumption estimated information set or the estimated information of other driving behaviors.
In this embodiment, by taking driver 1 drives vehicle arrangement 1 as an example, gene order 14 will be exportedFor most
Good gene order, i.e. driver 1 drives 1 idling of vehicle arrangement (vehicle speed information be 0 kilometer/hour), 30 seconds gasoline of traveling
Quantity consumed is 0.012500034 liter, driver 1 drives 1 vehicle speed information of vehicle arrangement and is 0 ~ 10 kilometer/hour and travels 30 seconds
Gasoline consumption quantity be 0.018487159 liter, and so on:
。
In this embodiment, optimal combination analysis module 34 can be performed during executing gene order mutation algorithm
Dynamic method corrects chromosome, which substitutes into the resulting score of fitness function formula calculating with reference to gene order and be modified.With
For driver 1 drives vehicle arrangement 1, optimal combination analysis module 34 can root during executing gene order mutation method
According to mutation rateBinary vector (binary vector) is randomly generated, to execute two gene orders
Mutation process.Assuming that, then the numerical value of n-th of chromosome will substitute into fitness function formula with reference to gene order in gene order
Resulting score is calculated to be modified.
For example, second godmother's gene order (as shown in table 19) can be mutated with gene order mutation method,
And assume, second godmother's gene order 1Chromosome 1, its second godmother gene order 2Chromosome 1It can be mutated with following calculation, then
It is changed into the sub- gene order of the second generation after the second mutated process of godmother's gene order.
。
In said gene series jump algorithm, optimal combination analysis module 34 can also set upper limit value upper_bound
With lower limit value lower_bound, the resulting score of fitness function formula calculating is substituted into referring again to gene order and is modified.Citing comes
It says, with above-mentioned mutation example, optimal combination analysis module 34 can be mutated with following equation, then second godmother's gene order
The sub- gene order of the second generation is translated into after mutated process.
。
Referring to figure 4., Fig. 4 is the fitness function formula production method of another embodiment, and this method can make neural network
For fitness function formula, and this fitness function formula can be used to calculate gene order score s.In this embodiment, it is driven with driver i
For sailing vehicle arrangement j, neural network has hidden layer, and hidden layer hasA neuron, then fitness function formula are as follows:, wherein gene order score s.In this embodiment, divide
The lower number the better, i.e., optimum solution is, gene order is one
Group set, this group of base
Because sequence includesA chromosome is (that is, cardinality of a set), wherein first
A chromosome is, chromosome can be floating-point encoding.Optimal combination analysis module 34 can be obtained using simple genetic algorithms
To one group of best gene order, and this organizes best gene order and corresponds to best gene order score s(score the lowest),
And best gene order is in combination with driving behavior quantityEstimated energy quantity consumed.
In this embodiment, with a neural network there is a hidden layer to be illustrated, but not limited to this, nerve net
Network is also required to have multiple hidden layers, and interneuronal weighted value can be used as chromosome.Multiple bases are generated with this above-mentioned hypothesis
One group of best gene order is obtained because of sequence, and using simple genetic algorithms.
It is please a kind of gene order production method of one embodiment of the present of invention referring next to Fig. 4, Fig. 4.Optimal combination
Analysis module 34 according to driving behavior statistical magnitude (for example, the statistical magnitude in special speed section, special traffic relevant information
Statistical magnitude or specific physiologic information relevant information statistical magnitude etc.) and assessment information statistics (for example, energy disappears
Consumption quantity etc.) establish multiple target function types (step S510);Each objective function is randomly generated in optimal combination analysis module 34
The multiple parameter values of formula, and those target function types are calculated, generate each target function type error amount (step S511);Optimal combination
Analysis module 34 corrects each target function type parameter value optimum solution (step S512) according to each target function type error amount;Best group
It closes analysis module 34 and exports each target function type parameter value optimum solution to those other target function types (step S513), and again
Calculate each target function type error amount;Optimal combination analysis module 34 judges whether each target function type error amount is lower than convergence threshold
It is worth (step S514 judges whether to restrain);And when each target function type error amount is lower than convergence threshold, optimal combination analysis
Mould group 34 is by the smallest combining parameter values (step S515) of output error;It is received, whereas if each target function type error amount is higher than
Threshold value is held back, then optimal combination analysis module 34 corrects each target function type parameter value optimum solution according to error amount, and exports each mesh
Offer of tender numerical expression parameter value optimum solution recalculates each target function type error amount to those other target function types, lasting to count
It calculates until convergence.
It should be noted that those described above target function type can be according to the driving behavior quantity and energy consumption in each month
Quantity is established.And in this embodiment, by taking driver i drives vehicle arrangement j as an example, optimal combination analysis module 34 can be with
Following manner generates multiple target function types:
First object functional expression:
Second target function type:
…
12nd target function type:
13rd target function type:
14th target function type:。
In this approach, optimal combination analysis module 34 can also set upper limit value upper_bound and lower limit value
Lower_bound, and those of first object functional expression parameterCan be used be randomly generated between
Numerical value between upper limit value upper_bound and lower limit value lower_bound.In addition, optimal combination analysis module 34 is random
After generating those numerical value, error amount and corrected parameter are calculated further according to target function typeInitial value:
。
According to above-mentioned calculation, those of the second target function type parameterIt needs to use
The numerical value between upper limit value upper_bound and lower limit value lower_bound is randomly generated, and optimal combination analyzes mould
Group 34 calculates error amount and corrected parameter after those numerical value are randomly generated, further according to target function typeInitial value:
。
According to above-mentioned calculation, and so on, those of the 14th target function type parameter
It needs to use the numerical value being randomly generated between upper limit value upper_bound and lower limit value lower_bound, and best group
Analysis module 34 is closed after those numerical value are randomly generated, calculates error amount and corrected parameter further according to target function type
Initial value:
。
Complete calculation of initial value after, the exportable each target function type parameter value optimum solution of optimal combination analysis module 34 to that
Other a little target function types, and recalculate each target function type error amount.By taking first object functional expression as an example, those parameters can
It is reset with following manner, and calculates error amount and corrected parameter further according to target function type:
。
According to above-mentioned calculation, by taking the second target function type as an example, those parameters can be reset with following manner,
And error amount and corrected parameter are calculated further according to target function type:
。
According to above-mentioned calculation, and so on, by taking the 14th target function type as an example, those parameters can use following side
Formula is reset, and calculates error amount and corrected parameter further according to target function type:
。
According to above-mentioned calculation, judge whether each target function type error amount is lower than convergence threshold.When each objective function
When formula error amount is lower than this convergence threshold, the smallest combining parameter values of 34 output error of optimal combination analysis module.And if each
Target function type error amount is higher than convergence threshold, then optimal combination analysis module 34 repeats parameters revision, according to error amount
Each target function type parameter value optimum solution is corrected, and exports each target function type parameter value optimum solution to those other objective functions
Formula, and each target function type error amount is recalculated, it is lasting to calculate until error amount is lower than convergence threshold.
Based on said gene algorithm, in addition the present invention proposes a kind of traffic information estimation method, as shown in Figure 6.Data
Analysis server equipment 3 collects n section in the traffic information (step S610) at t-th of time point.This traffic information can
To be hourage, vehicle flowrate or speed, such as: traffic information of the section 1 t-th of time point is, section 2 is in t
The traffic information at a time point is... traffic information of the section n t-th of time point be。
The traffic information in n section t-th of time point is reacted in driving behavior by optimal combination analysis module 34 again
It is input to optimal combination analysis method (step S611) described in Fig. 2.It is worth noting that, at this point, fitness function formula generation side
The formula of method is, as shown in Figure 7.Optimal combination analysis module 34 can then use optimal combination
Analysis method obtains weight setOptimal combination, and weighted value of the gene order as fitness function formula
(that is, the associated weighted value of traffic information between each section), and optimal combination is section Effects of Factors power
Weight (step S612).
In addition, the present invention provides a kind of physiologic information estimation method, as shown in figure 8, analysis server apparatus 3 can be received
Collection drives the physiologic information (step S810) at m time point, and physiologic information can be heart rate value or heart rate variability numerical value, such as schemes
Shown in 9.
Driving behavior is input to Fig. 2 institute in the physiologic information that m time point is reacted again by optimal combination analysis module 34
The optimal combination analysis method (step S811) stated, fitness function formula are then unitary n times equation, such as
Shown in Figure 10.
Optimal combination analysis module 34 obtains weight set with optimal combination analysis methodIt is best
Combination, this optimal combination are time factor (t) weighing factor (i.e. time series and the associated weighted value of heart rate variability) (step
Rapid S812).
It should be noted that optimal combination analysis module 34 can be then by those bases in the appraisal procedure shown in Fig. 6,8
Because sequence carries out option program, mating program and mutation program, and best base is generated in the convergence of the score of those gene orders
Because of sequence, and this best gene order is the assessment information aggregate of driving behavior.
In conclusion the optimal combination analysis method of the embodiment of the present invention, can improve simple genetic algorithms, in initial phase
First establish several excellent gene orders, then with these gene orders mated, be mutated etc. calculate with generate best base because
Sequence, and this improvement simple genetic algorithms is in combination with the fitness function formula of neural network.The embodiment of the present invention can be according to application person's
Demand and be applied to energy consumption estimation, traffic information estimation and physiologic information estimation, to obtain best gene order.
Although the present invention is disclosed by way of embodiment as above, it is not intended to make the present invention any limit
Fixed, the people in any technical field with common knowledge should can make without departing from the spirit and scope of the present invention
Some changes and retouching, therefore protection scope of the present invention should be subject to the scope defined in the appended claims.
Claims (10)
1. a kind of optimal combination analysis method, suitable for analyzing the information of driving behavior reaction, which is characterized in that described best group
Closing analysis method includes:
Generate multiple gene orders, wherein each described gene order include multiple chromosomes, and the multiple chromosome with
The statistical magnitude of assessment information caused by driving behavior in different time points is related, and each described statistical magnitude is different
The assessment information meets the quantity of numerical intervals under time point;
Traffic information or physiologic information that the driving behavior is reacted are input to fitness function formula, to calculate the multiple base
Because of the score of sequence, wherein weighted value of the multiple gene order as the fitness function formula;And
The multiple gene order is subjected to option program, mating program and mutation program, and works as the multiple gene order
Score convergence when generate best gene order, wherein the best base is because of the assessment information collection that sequence is the driving behavior
It closes.
2. optimal combination analysis method according to claim 1, which is characterized in that when point of the multiple gene order
Counting the step of generating the best gene order when restraining includes:
When evolution number is equal to repeatedly band number, the best gene order is exported, wherein the primary option program of every progress,
The mating program and the mutation program, then the evolution number adds one;And
When the evolution number is less than the repeatedly band number, the evolution number is added one.
3. optimal combination analysis method according to claim 1, which is characterized in that generate the multiple gene order packet
It includes:
Multiple target function types are established according to the traffic information or physiologic information of the driving behavior and the assessment information;
The multiple parameter values of each target function type are randomly generated, and calculate each described target function type to generate
The error amount of each target function type;
Each described parameter of each target function type is corrected according to the error amount of target function type described in each
The optimum solution of value;
Export the optimum solution of each target function type parameter value to other each described target function type, and count again
Calculate the error amount of each target function type;And
Judge whether the error amount of each target function type is lower than convergence threshold, wherein if the error of target function type
Value is lower than the convergency value, then the smallest combining parameter values of output error, if the error amount of target function type is higher than the receipts
Hold back threshold value, then each of each target function type is corrected according to the error amount of each target function type described in
The optimum solution of parameter value, and the optimum solution for exporting each parameter value of each target function type is each to other
A target function type and the error amount for recalculating each target function type are calculated with lasting until target letter
The error amount of numerical expression is lower than the convergence threshold.
4. optimal combination analysis method according to claim 1, which is characterized in that generate the multiple gene order packet
It includes:
The traffic information of different sections of highway in different time points is obtained, wherein the traffic information is hourage, vehicle flowrate or vehicle
Speed.
5. optimal combination analysis method according to claim 1, wherein generating the multiple gene order and including:
Physiologic information in different time points is obtained, wherein the physiologic information is rhythm of the heart value or rhythm of the heart variation value.
6. a kind of analysis server apparatus, which is characterized in that the analysis server apparatus includes:
Communication module group, the communication module group receive the traffic information or physiologic information that driving behavior is reacted;
Reservoir, the reservoir record the traffic information or the physiologic information and multiple mould groups;And
Processor, the processor couples the communication module group and the reservoir, and accesses and execute the reservoir institute
The multiple mould group of storage, the multiple mould group include:
Optimal combination analysis module, the optimal combination analysis module execute:
Generate multiple gene orders, wherein each described gene order include multiple chromosomes, and the multiple chromosome with
The statistical magnitude of assessment information caused by driving behavior in different time points is related, and each described statistical magnitude is different
The assessment information meets the quantity of numerical intervals under time point;
The traffic information of the driving behavior or physiologic information are input to fitness function formula, to calculate the multiple gene order
Score, wherein weighted value of the multiple gene order as the fitness function formula;And
The multiple gene order is subjected to option program, mating program and mutation program, and works as the multiple gene order
Score convergence when generate best gene order, wherein the best base is because of the assessment information collection that sequence is the driving behavior
It closes.
7. analysis server apparatus according to claim 6, which is characterized in that
When evolution number is equal to repeatedly band number, the optimal combination analysis module exports the best gene order, wherein often
The primary option program, the mating program and the mutation program are carried out, then the optimal combination analysis module is by institute
Evolution number is stated plus one;And
When the evolution number is less than the repeatedly band number, the optimal combination analysis module adds the evolution number
One.
8. analysis server apparatus according to claim 6, which is characterized in that the optimal combination analysis module according to
Plural target function type is established according to the traffic information or physiologic information of the driving behavior and the assessment information, is randomly generated every
The complex parameter value of one target function type, and each described target function type is calculated to generate each described target
The error amount of functional expression corrects each of each target function type according to the error amount of target function type described in each
The optimum solution of a parameter value, export the optimum solution of each target function type parameter value to other each described mesh
Offer of tender numerical expression, and the error amount of each target function type is recalculated, judge the mistake of each target function type
Whether difference is lower than convergence threshold, wherein output error is most if the error amount of target function type is lower than the convergence threshold
Small combining parameter values, if the error amount of target function type is higher than the convergence threshold, according to target letter described in each
The error amount of numerical expression corrects the optimum solution of each parameter value of each target function type, and exports each institute
It states the optimum solution of each parameter value of target function type and each described target function type and is recalculated every to other
The error amount of one target function type is calculated with lasting until the error amount of target function type is lower than the convergence threshold.
9. analysis server apparatus according to claim 6, which is characterized in that the optimal combination analysis module is logical
It crosses the communication module group and obtains the traffic information of different sections of highway in different time points, and the traffic information is hourage, vehicle
Flow or speed.
10. analysis server apparatus according to claim 6, which is characterized in that the optimal combination analysis module
Physiologic information in different time points is obtained by the communication module group, and the physiologic information is rhythm of the heart value or rhythm of the heart variation
Value.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107110666 | 2018-03-28 | ||
TW107110666A TWI661328B (en) | 2018-03-28 | 2018-03-28 | Data analysis server equipment and optimized combination method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110322016A true CN110322016A (en) | 2019-10-11 |
Family
ID=67764281
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810480525.8A Pending CN110322016A (en) | 2018-03-28 | 2018-05-18 | Analysis server apparatus and its optimal combination analysis method |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110322016A (en) |
TW (1) | TWI661328B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1410911A (en) * | 2001-09-26 | 2003-04-16 | 财团法人资讯工业策进会 | Calculation method for transportation vehicle controlled dispatch |
JP2009069867A (en) * | 2007-09-10 | 2009-04-02 | Mitsubishi Heavy Ind Ltd | Action route search device, method and program |
US9193442B1 (en) * | 2014-05-21 | 2015-11-24 | Rockwell Collins, Inc. | Predictable and required time of arrival compliant optimized profile descents with four dimensional flight management system and related method |
CN107194605A (en) * | 2016-12-19 | 2017-09-22 | 中华电信股份有限公司 | Energy consumption estimation system and method |
CN107822623A (en) * | 2017-10-11 | 2018-03-23 | 燕山大学 | A kind of driver fatigue and Expression and Action method based on multi-source physiologic information |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7246007B2 (en) * | 2004-03-24 | 2007-07-17 | General Motors Corporation | System and method of communicating traffic information |
US8024112B2 (en) * | 2005-09-29 | 2011-09-20 | Microsoft Corporation | Methods for predicting destinations from partial trajectories employing open-and closed-world modeling methods |
CN101325004B (en) * | 2008-08-01 | 2011-10-05 | 北京航空航天大学 | Method for compensating real time traffic information data |
CN101794507B (en) * | 2009-07-13 | 2012-03-28 | 北京工业大学 | Method for evaluating macroscopic road network traffic state based on floating car data |
TWI417817B (en) * | 2010-09-29 | 2013-12-01 | Ind Tech Res Inst | Traffic notification system and method with reduced communications requirements |
-
2018
- 2018-03-28 TW TW107110666A patent/TWI661328B/en active
- 2018-05-18 CN CN201810480525.8A patent/CN110322016A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1410911A (en) * | 2001-09-26 | 2003-04-16 | 财团法人资讯工业策进会 | Calculation method for transportation vehicle controlled dispatch |
JP2009069867A (en) * | 2007-09-10 | 2009-04-02 | Mitsubishi Heavy Ind Ltd | Action route search device, method and program |
US9193442B1 (en) * | 2014-05-21 | 2015-11-24 | Rockwell Collins, Inc. | Predictable and required time of arrival compliant optimized profile descents with four dimensional flight management system and related method |
CN107194605A (en) * | 2016-12-19 | 2017-09-22 | 中华电信股份有限公司 | Energy consumption estimation system and method |
CN107822623A (en) * | 2017-10-11 | 2018-03-23 | 燕山大学 | A kind of driver fatigue and Expression and Action method based on multi-source physiologic information |
Also Published As
Publication number | Publication date |
---|---|
TW201942911A (en) | 2019-11-01 |
TWI661328B (en) | 2019-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109118055B (en) | Driving behavior scoring method and device | |
EP3330917A1 (en) | Method and system for determining traffic service fees | |
US20220187087A1 (en) | Systems and methods for predicting fuel consumption efficiency | |
Oliveira et al. | Evaluation of two methods for identifying trip purpose in GPS-based household travel surveys | |
AU2018102202A4 (en) | Systems and methods for cheat examination | |
Jiménez et al. | Modelling the effect of driving events on electrical vehicle energy consumption using inertial sensors in smartphones | |
CN105444770A (en) | Intelligent mobile phone-based lane grade map generating and positioning system and method | |
CN109583926A (en) | A kind of used car pricing method apparatus and system | |
CN107194605A (en) | Energy consumption estimation system and method | |
US20180204252A1 (en) | System and method for representing the costs of commuting journeys | |
Montini et al. | Route and mode choice models using GPS data | |
JP7029022B2 (en) | Information generator, information generation method, program, and storage medium | |
CN108428001A (en) | Credit score prediction technique and device | |
Chamberlain et al. | Evaluating the barrier effects of charge point trauma on UK electric vehicle growth | |
CN111723835A (en) | Vehicle movement track distinguishing method and device and electronic equipment | |
US20230221134A1 (en) | Machine Learning Platform for Dynamic Device and Sensor Quality Evaluation | |
CN110322016A (en) | Analysis server apparatus and its optimal combination analysis method | |
Liu et al. | A data-driven approach for electric bus energy consumption estimation | |
Lu et al. | Data-mining approach to work trip mode choice analysis in Chicago, Illinois, area | |
Auld et al. | Results of the utracs internet-based prompted recall gps activity-travel survey for the Chicago region | |
US20220196413A1 (en) | Systems and methods for simulating transportation order bubbling behavior | |
Kumar | Driver Usage Risk Profiling by Analyzing Vehicle Driving Behavior using Machine Learning Model Based on Vehicular Cloud Telematics Data | |
CN113919893B (en) | Information pushing method and device, electronic equipment and readable medium | |
Pakeerathan et al. | Driving Behaviour Analysis using Low Sampling GPS Trajectories of Ride-hailing Services | |
Morgul et al. | Value of schedule delays by time of day: evidence from usage data from high-occupancy toll lanes on state road 167 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191011 |
|
WD01 | Invention patent application deemed withdrawn after publication |