CN115587678A - Intelligent map traveling method and system for commercial vehicle - Google Patents
Intelligent map traveling method and system for commercial vehicle Download PDFInfo
- Publication number
- CN115587678A CN115587678A CN202211073893.3A CN202211073893A CN115587678A CN 115587678 A CN115587678 A CN 115587678A CN 202211073893 A CN202211073893 A CN 202211073893A CN 115587678 A CN115587678 A CN 115587678A
- Authority
- CN
- China
- Prior art keywords
- travel
- route
- vehicle
- recommended
- consumption
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 230000006399 behavior Effects 0.000 claims description 43
- 230000005611 electricity Effects 0.000 claims description 12
- 239000002131 composite material Substances 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 10
- 239000000446 fuel Substances 0.000 description 7
- 238000013499 data model Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Navigation (AREA)
Abstract
The invention provides a method and a system for intelligent map travel of a commercial vehicle, which comprises the following steps: inputting a departure place and a destination; calculating a plurality of recommended planning routes and highway tolls corresponding to each recommended planning route through a map API; for the recommended planned route, firstly, slicing and segmenting according to road conditions to obtain each journey, and then, analyzing and determining the oil consumption or the power consumption of each journey according to the load category of a vehicle and the driving behavior of a driver in each journey, wherein the recommended planned route is a plurality of routes which are short in time and/or distance; and superposing the oil consumption and/or the power consumption of each journey, adding the total oil cost and/or the total power cost and the highway tolls to obtain the travel cost of each recommended and planned route, and planning the route based on the travel cost. The invention improves the calculation precision of the oil charge or the electric charge in the travel cost of the long-distance running of the vehicle, simultaneously carries out comprehensive consideration on the comprehensive travel cost of the travel, and can meet the long-distance route planning requirement of a commercial vehicle user.
Description
Technical Field
The invention belongs to the technical field of commercial vehicle navigation, and particularly relates to an intelligent map trip method and system for a commercial vehicle.
Background
The transport of goods by commercial vehicles is one of the main modes of modern transport and also one of the two basic modes of transport that constitute the transport of goods on land. It plays an important role in the whole transportation field and plays an increasingly important role.
At present, a commercial vehicle navigation long-distance path planning scheme on the market generally carries out route planning recommendation of unilateral factors according to 3 modes of shortest time, shortest mileage and lowest high-speed charge, the influence of increasing oil fee on travel cost is not considered, and accurate calculation and estimation are not carried out on oil consumption of a long-distance route, for a commercial vehicle running for a long distance, the comprehensive travel cost actually needs to consider the influence on the accurate travel cost including the oil consumption and the high-speed charge cost (particularly, the priority of the travel cost and the calculation accuracy requirement of the estimated travel cost for the commercial vehicle are higher), the influence of the running time and the mileage is also properly considered, so that the overall and comprehensive consideration is carried out on the travel cost in an actual angle, however, the existing travel and map route planning method does not fully consider the comprehensive travel cost in which the time, the distance and the travel cost are comprehensively considered in the vehicle running process, the single influence factor is usually taken into statistical consideration, and in addition, the actual calculation accuracy of the travel cost of the long-distance travel cost of the commercial vehicle is generally not accurate enough, so that a route planning scheme meeting the actual travel requirement of a user can not be provided.
Therefore, based on the above situations, it is urgently needed to design an intelligent map trip method and system for a commercial vehicle, so as to further improve the oil cost calculation precision of long-distance trip expenses, and comprehensively consider the comprehensive trip cost of trips, thereby making an optimized trip planning route which meets the actual needs of users of the commercial vehicle in all aspects.
Disclosure of Invention
Technical problem to be solved
The invention provides an intelligent map trip method and system for a commercial vehicle, which improve the calculation precision of oil charge in the trip cost of long-distance running of the vehicle and comprehensively consider the comprehensive trip cost of trip, thereby meeting the route planning requirements of commercial vehicle users such as trucks and the like.
(II) technical scheme
The invention also discloses a method for the trip of the intelligent map of the commercial vehicle, which comprises the following steps:
step 1: inputting a departure place and a destination;
step 2: calculating a plurality of recommended planned routes and a highway toll corresponding to each recommended planned route through a map API, wherein the recommended planned routes are the first plurality of routes with short time and/or short distance;
and step 3: for the recommended planned route, firstly, slicing and segmenting according to road conditions to obtain each journey, and then analyzing and determining the oil consumption and/or the power consumption of each journey according to the load category of the vehicle and the driving behavior of a driver in each journey; the road conditions comprise plain high speed, plain national road, hilly high speed, hilly national road, mountain high speed, mountain national road and plateau;
and 4, step 4: and superposing the oil consumption or the power consumption of each journey, outputting total oil charge and/or total power charge based on each recommended planning route by combining the oil price and/or the power price, adding the total oil charge and/or the total power charge and the highway tolls to obtain the travel cost of each recommended planning route, and planning the route based on the travel cost.
Preferably, the method further comprises the following step 5: after selecting a proper route, the user clicks and sends the route to the vehicle, and the vehicle-mounted map module automatically navigates to the destination.
Preferably, the step 1 is executed on a mobile phone remote terminal or a car machine local terminal.
Preferably, the load categories are specifically classified into the following 5 categories: no-load, light load, half load, full load, and overload.
Preferably, step 3 further comprises: and after the road condition and the load category are classified, determining historical accumulated average oil consumption and/or average power consumption of commercial vehicles of which the types are the same as the current travel load category, wherein the historical accumulated average oil consumption and/or average power consumption are average oil consumption values and/or average power consumption values of a plurality of vehicles under the current road condition and the load according to big data statistics, and determining the influence on the historical accumulated average oil consumption and/or average power consumption according to the past driving behaviors of a driver so as to calculate the oil consumption and/or power consumption of each travel.
Preferably, step 3 specifically includes the steps 3.1 to 3.5 of operating the driving behavior analysis model:
step 3.1: eigenvalue selection
Selecting 5 types of behaviors of rapid acceleration, rapid deceleration, idling, accelerator/electric switch stepping during parking and large accelerator/large electric switch stepping as characteristic values;
step 3.2: data acquisition and preprocessing
Firstly, cleaning and preprocessing the previous driving data of the accessed current driver, checking the data consistency, and processing invalid values and missing values to obtain input data of characteristic values;
step 3.3: eigenvalue statistics and calculations
Counting the characteristic values according to the input data, counting, classifying and calculating the characteristic values in the travel in the input data according to the same load category and the same road condition, and acquiring a plurality of characteristic values G which are the same as the current driving condition i A value of (d);
step 3.4: construction of a Scoring model
Wherein the function f is the composite score of the driving behavior in the road section of the current journey, G i Is the ith characteristic value, a i N is equal to 5 for the feature weight matrix;
step 3.5: driving behavior scoring
Characteristic value G counted according to step 3.3 i And 3.4, calculating a comprehensive score of the driving behavior of the recommended planned route by the scoring model in the step 3.4.
Preferably, based on said composite score f i And obtaining the oil consumption or the electricity consumption Totaloil of each journey according to the following formula i
Totaloil i ＝(AverageOil i- AverageOil i *(f i -80)*D i )*Mileage i
Wherein: totaloil i Representing the cumulative oil or electricity consumption, averageOil, of the ith trip in the recommended route i Representing the accumulated average oil consumption or the average power consumption f of the ith section with the same load type and the same road condition i A composite score, D, representing driving behavior during the ith trip i Is constant coefficient, can be adjusted according to different driving scenes and vehicle types, and is Mileage i Represents the total mileage of the ith journey;
will Totaloil i And summing to obtain the accumulated oil consumption or the accumulated electricity consumption Totaloil of each recommended route:
where m is the total number of trips divided in the corresponding recommended planned route.
Preferably, step 3.4 further includes:
calculating the loss function of the model:
L＝f'-f
wherein, L represents a loss value, f' represents a true value, and f represents a predicted value.
Then, the feature weight matrix a is updated using the Adam gradient descent algorithm and the error back propagation algorithm i And stopping the training of the model after the characteristic weight matrix meets the corresponding condition.
In another aspect, the present invention further discloses an intelligent map trip system for a commercial vehicle, comprising:
at least one processor; and at least one memory communicatively coupled to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the intelligent map travel method for the commercial vehicle according to any one of the above items.
The intelligent map travel system of the commercial vehicle can be a remote server or a local vehicle terminal.
On the other hand, the invention also discloses a vehicle which comprises the intelligent map traveling system for the commercial vehicle.
In another aspect, the present invention also discloses a non-transitory computer readable storage medium storing computer instructions for causing the computer to execute the method of the intelligent map travel system for commercial vehicles according to any one of the above aspects.
(III) advantageous effects
(1) The method for the intelligent map trip of the commercial vehicle is a secondary route planning method, the recommended planning route calculated by a map API is 'the first few recommended planning routes with short time and/or short distance', so that a small number of effective recommended planning routes (for example, the recommended planning routes can be within twenty routes and consist of top ten routes with short time and short distance), secondary planning of the routes is performed on the basis of the recommended planning routes, namely, further comprehensive cost calculation is performed on the 'several recommended planning routes' considering time and distance, so that the 'several recommended planning routes' are ranked according to the total cost of oil consumption and high speed cost, the displayed result mainly considers the cost of money and the cost of time and distance, and is more suitable for the long-distance commercial vehicle navigation of the application, in addition, when the total cost of the several recommended planning routes is calculated secondarily, unnecessary routes is eliminated, the unnecessary routes with overlong time and distance are eliminated, the calculated workload of the total cost of long-distance routes in a remote server or a local vehicle machine is reduced, and the overall processing operation speed of a program is accelerated.
(2) The travel method is a route planning method for serially overlapping time/mileage and travel expense, comprehensively considers a plurality of main influence factors in travel, and effectively reduces the comprehensive travel cost including time, distance and travel expense (the travel time can influence the number of fixed routes run per month, the travel distance can influence the service life of vehicle hardware such as tires and the like, which are invisible cost expenses), so that the calculated long-distance route planning strategy is more optimal and better meets the actual travel route planning requirement of a truck driver.
(3) The trip method of the invention also combines road condition information, vehicle load information and driver driving behavior comprehensive analysis to determine the oil consumption or power consumption of each road section in the specific calculation of trip cost, while in the operation of the vehicle, different driving behaviors and habits are particularly important for the oil consumption or power consumption of the vehicle (the difference of total oil consumption or total power consumption influenced by the driving behaviors and the habits can be more than 20 percent), more accurate oil consumption or trip power consumption can be obtained by combining the driving behavior analysis oil consumption or power consumption analysis of a user, and the oil consumption or power consumption calculated by the machine learning method considering characteristic values and weight estimation matrixes can be more and more accurate along with the update of collected data, thereby being beneficial to the follow-up active push prompt of service information such as accurate refueling, power conversion, maintenance and the like for the vehicle.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts:
FIG. 1 is a schematic diagram of a communication relationship of an intelligent map travel system of a commercial vehicle in the invention;
FIG. 2 is a flow chart of the method for the intelligent map trip of the commercial vehicle in the invention;
FIG. 3 is a flow chart of the active recommendation of the commercial vehicle in the maintenance process of the invention.
Reference numerals: 1. data model, 2, internet of vehicles background, 3.TD platform, 4.TBOX,5, travel service APP,6, vehicle map module 6,7, cell phone APP.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Referring to the intelligent map trip system for the commercial vehicle shown in fig. 1, the intelligent map trip system for the commercial vehicle comprises a mobile phone, a server, a TD platform 3, a TBOX4 and a vehicle terminal which are sequentially in communication connection, wherein the server comprises a data model 1 and a vehicle networking background 2, the vehicle terminal comprises a trip service APP5 and a vehicle-mounted map module 6, the mobile phone comprises a mobile phone APP7, the TD platform 3 can also be replaced by other mobile network platforms, and the wireless communication modes are not limited to 3G/4G/5G and the like.
The main functions of each submodule are as follows:
data model 1: a travel service algorithm model;
the Internet of vehicles background 2: the method comprises the following steps of (1) carrying out business processing on travel services, and acquiring and pushing information of a vehicle terminal and a mobile phone;
TD platform 3: the system is responsible for receiving vehicle related data and communicating with the tbox;
TBOX4: the system is in charge of collecting data related to the commercial vehicle and carrying out data communication with the TD platform;
travel service APP5: the system is responsible for processing the related business of the car machine map; and local operation commands of the map service can be issued, such as inputting a starting point, a passing point, a destination and the like.
The vehicle-mounted map module 6: and is responsible for map navigation.
Mobile phone APP7: and issuing a remote operation command of the map service.
The solid line in fig. 1 is a direct communication relation, the dotted line is an indirect communication relation, and the functions and the communication relations of the sub-components in fig. 1 can realize the remote two-way communication between the vehicle terminal and the server, so that the route planning or recommendation is comprehensively carried out on the trip of the intelligent map of the commercial vehicle by utilizing the data model and combining the local information and the network information.
It should be noted that, because the route calculation amount of the travel method of the quadratic programming in fig. 2 to 3 of the present invention is less, the relevant main program may run in the background of the internet of vehicles, and may also run in the local travel service APP according to the actual demand, so as to perform local travel planning by using the data collected by the server remote model, the internet of vehicles, and the like.
In another embodiment, in order to improve the calculation accuracy of the oil cost in the travel cost of long-distance travel of the vehicle and simultaneously perform comprehensive consideration and route planning on the comprehensive travel cost of travel, fig. 2 of the invention also discloses a commercial vehicle intelligent map travel method, and as shown in fig. 1-2, a user can select to remotely set a departure place and a destination on a mobile phone APP or a travel service APP with a large screen of a vehicle, the APP can automatically perform secondary route planning on the travel oil consumption or power consumption and the comprehensive cost of high-speed highway road cost based on the commercial vehicle intelligent map travel method of the invention, then the user selects a route desired by himself, clicks 'send to the vehicle', the route is pushed to the travel service APP through the internet of vehicles, then the route is transmitted to a vehicle-mounted map module through the travel service APP, and the vehicle-mounted map module automatically navigates to the destination when the user gets on the vehicle.
Specifically, referring to fig. 2, the method for traveling the intelligent map of the commercial vehicle of the present invention includes: :
step 1: inputting a departure place and a destination;
specifically, the inputting of the departure place and the destination in step 1 is performed in an APP of the terminal device, where the APP may be a travel service APP in the car terminal in fig. 1 or a mobile phone APP in communication connection with a server, so that a user can freely select to input the navigation parameters at a mobile phone remote terminal or a car local terminal. Besides, the APP can input a departure point and a destination, and a passing point can also be input into the APP, so that the recommended planned route planned in the step 2 meets the requirements of the commercial vehicle user.
Step 2: calculating a plurality of recommended planning routes and highway tolls corresponding to each recommended planning route through a map API (application programming interface), wherein the recommended planning routes are a plurality of previous routes with short time and/or short distance;
in the step 2, the calculation amount of the secondary route planning based on the travel cost consideration can be reduced by determining a small number of effective routes as the recommended planning route, for example, the routes may be twenty routes, and the twenty routes are composed of routes ranked in the first ten times and short in time and distance on the basis of meeting the requirements of the departure point, the destination and the passing point.
In addition, the map API can be used as a third-party open source data interface to be in communication connection with the internet of vehicles background of the server, so that a planned recommended planned route and high-speed cost can be obtained by using the navigation function of the internet data and the existing map software such as Baidu and God.
And step 3: for the recommended planning route, firstly, slicing and segmenting according to road conditions to obtain each journey, and then, analyzing and determining the oil consumption and/or the power consumption of each journey according to the load category of the vehicle and the driving behavior of a driver in each journey (the hybrid vehicle needs to determine the oil consumption and the power consumption at the same time, and the oil consumption and the power consumption are calculated at the same time); the road conditions comprise plain high speed, plain national road, hilly high speed, hilly national road, mountainous area high speed, mountainous area national road and plateau;
in the step 3, the road conditions are simply and effectively divided into plain high speed, plain national road, hill high speed, hill national road, mountain high speed, mountain national road and plateau, so that the working conditions of flatness, bending, altitude and the like of the route can be comprehensively considered at the same time, and the calculation complexity is not excessively increased. In addition, the route secondary planning and the specific calculation of energy consumption (oil consumption is considered for oil vehicles and power consumption is considered for electric vehicles) are carried out on the basis of a plurality of recommended planned routes, so that the energy consumption calculation accuracy of the long-distance driving route of the commercial vehicle can be effectively improved, and the load and the driving behaviors have great influence on the energy consumption calculation accuracy of each section of the route except for road conditions.
In another embodiment, the load category in step 3 can be specifically divided into the following five categories: no-load, light load, half load, full load, and overload. For large trucks below 45 tons, the respective loads can be set in the ranges: no load (less than 15 tons), light load (15-25 tons), half load (25-35 tons), full load (35-45 tons) and overload (more than 45 tons). After the road condition and the load category are classified in sequence, determining historical accumulated average oil consumption and/or average power consumption of commercial vehicles of which the types are the same as the current travel load category, wherein the historical accumulated average oil consumption and/or average power consumption are average oil consumption values and/or average power consumption values of a plurality of vehicles under the current road condition and the load, which are obtained according to big data statistics, and determining the influence on the historical accumulated average oil consumption and/or average power consumption according to the past driving behaviors of a driver, so that the oil consumption or the power consumption of the driver on each travel is accurately calculated in advance.
Further, in another embodiment, taking fuel consumption as an example (the same driving behavior analysis model of power consumption), the influence of the driving behavior on the fuel consumption in step 3 is specifically the comprehensive score f determined according to the dynamic driving behavior analysis model i The driving behavior analysis model may be previously set in the data model 1 of fig. 1 by integrating the score f i The fuel consumption Totaloil which is influenced by the past driving behaviors of the driver and accords with the ith journey condition in the recommended and planned route can be calculated under the condition that the load types are the same i 。
Specifically, step 3 includes the following steps 3.1 to 3.5 of operating the driving behavior analysis model:
step 3.1: selecting a characteristic value: and 5 types of behaviors of suddenly accelerating, suddenly decelerating, idling, stopping and stepping on an accelerator/electric valve and a large accelerator/electric valve are selected as characteristic values.
Step 3.2: data acquisition and preprocessing; firstly, the accessed previous driving data of the current driver is cleaned and preprocessed, the data consistency is checked, and the input data of the characteristic value is obtained after invalid values and missing values are processed.
Furthermore, the driving data acquired in the car networking mode can be cleaned by using a median filtering function, and the driving data is used as input data of the characteristic values after invalid values and missing values are eliminated.
Step 3.3: counting and calculating characteristic values; counting the characteristic values according to the input data in the step 3.2, and counting, classifying and calculating the characteristic values in the journey in the input data according to the same load category and the same road condition, thereby obtaining a plurality of characteristic values G which are the same as the current driving working condition i The value of (c).
It should be particularly noted that "in-trip" in the feature values in the trip in the input data may refer to a case that the trip in the input data is equal to or longer than the planned trip, and if the trip of the input data is longer than the planned trip, a part of feature value data that is the same as the trip mileage of this time is intercepted as a reference feature value, for example, a feature value of a trip with full load, hilly country road and length of 20km exists in the input data, and a trip with full load, hilly country road and length of 15km is required for the recommended route planning of this time, a historical feature value in the first 15km trip in 20km may be intercepted as a reference value (also may be middle 15km or last 15 km), so as to restore the real road condition of each trip in the recommended route planning of step 3 as much as possible; of course, if the travel distances are the same, the historical characteristic values of which the load categories, the road conditions and the travel distances are all completely the same are preferentially used as reference values; in addition, if a plurality of groups of characteristic values G which are completely the same as the current driving working condition (namely the same load category, the same road condition type and the same driving distance) exist i Then the eigenvalues in each set of data may be summedThe latter average value is used as the characteristic value G which is the same as the current running condition i Thereby improving the accuracy of the calculation.
For example: referring to table 1 below, when calculating and calculating the feature value, the recommended route according to the navigation may be divided into three routes, namely, route 1 (where the road condition corresponds to plain high speed), route 2 (where the road condition corresponds to hilly country road) and route 3 (where the road condition corresponds to mountain high speed).
Firstly, 5 types of characteristic values G with the same three-section running working condition are counted for the stroke 1, the stroke 2 and the stroke 3 i And carrying out statistics and accumulation calculation to obtain a 1-e 1, a 2-e 2 and a 3-e 3, wherein the total number n of the characteristic values is 5.
TABLE 1 eigenvalue calculation
| Characteristic value | Stroke 1 | |
|
| Quick acceleration (second time) | a1 | a2 | a3 |
| Fast deceleration (times) | b1 | b2 | b3 |
| Idle speed (minutes) | c1 | c2 | c3 |
| Stepping on the throttle/electric door when parking (second) | d1 | d2 | d3 |
| Big throttle/big electric door driving (second time) | e1 | e2 | e3 |
Step 3.4: construction of a Scoring model
Wherein the function f is the composite score of the driving behavior in the road section of the current journey, G i Is the ith characteristic value, a i N is equal to 5 for the feature weight matrix.
Further, the loss function of the model can be calculated:
L＝f'-f
wherein, L represents a loss value, f' represents a true value, and f represents a predicted value.
Then, the feature weight matrix a is updated using the Adam gradient descent algorithm and the error back propagation algorithm i And stopping the training of the model after the characteristic weight matrix meets the corresponding condition.
Step 3.5: scoring the driving behavior according to the characteristic value G counted in step 3.3 i And 3.4, calculating a comprehensive score of the driving behavior of the recommended planned route by using the scoring model in the step 3.4.
For example: referring to table 2, the driving behavior full score may be set to 100, and the characteristic value G may be set i Substituting the feature weight matrix a i In the determined function f, the strokes 1-3 can be obtainedThe total score of each of the above-mentioned three points is f1 to f3.
TABLE 2 Driving behavior Scoring
| Scoring | Stroke 1 | |
|
| Comprehensive score of driving behavior | f 1 | f 2 | f 3 |
The preset 80 is divided into historical accumulated average oil consumption with the same state load category, and the higher the score of the driving behavior comprehensive score is, the better the driving habit is represented, and the less the oil consumption is; the invention sets 80-point historical accumulated average fuel consumption as a preset threshold value which is based on the influence of the driving behavior of commercial vehicle drivers with different vehicle speed fluctuations on the fuel consumption and is generally about 20% -25%.
It should be noted that, since the above steps 3.1-3.5 take into account the influence of various factors on the driving behavior, even for the same driver, the difference of the composite score of the driving behavior may occur due to different recommended routes, because some drivers are better at running mountain roads and higher at running speeds, and the distribution of the road conditions such as hills, mountain roads and high speeds in different routes is different, which may affect the composite score of the same driver in different recommended routes.
Based on the composite score f 1 ～f 3 And the following formula can obtain the fuel consumption of each journey i
Totaloil i ＝(AverageOil i- AverageOil i *(f i -80)*D i )*Mileage i
Wherein: totaloil i Representing the cumulative oil consumption, averageOil, of the ith trip in the recommended route i F represents historical accumulated average oil consumption with the same load type and the same road condition of the ith section of travel i A composite score, D, representing driving behavior during the ith trip i Is a constant coefficient, can be adjusted according to different driving scenes and vehicle types, and is Mileage i Representing the total mileage of the ith trip.
Therefore, the accurate oil consumption of each journey which is simultaneously comprehensively influenced by road conditions, load types and driving behaviors can be calculated by the method.
And 4, step 4: and superposing the oil consumption or the power consumption of each journey, outputting the total oil charge and/or the total power charge based on each recommended planning route by combining the oil price and/or the power price, adding the total oil charge and/or the total power charge and the highway tolls to obtain the travel cost of each recommended planning route, and planning the route based on the travel cost. It should be emphasized once more that the hybrid electric vehicle needs to determine the oil consumption and the electricity consumption at the same time, and the oil consumption and the electricity consumption need to be calculated at the same time, while the oil vehicle and the pure electric vehicle need to calculate the total oil charge or the total electricity charge separately.
Adding Totaloil in step 3 i And summing to obtain the accumulated oil consumption or the accumulated electricity consumption Totaloil of each recommended route:
where m is the total number of trips divided in the corresponding recommended planned route.
And finally, the recommended planning route performs secondary route planning and recommendation according to the ranking of the total oil cost/total electricity cost plus the trip cost of the high-speed fee, so that the user can select the map trip route of the commercial vehicle with the lowest comprehensive cost.
And 5: after selecting a proper route, the user clicks and sends the route to the vehicle, and the vehicle-mounted map module automatically navigates to the destination.
It is worth mentioning that, in the route planning based on the travel cost, the step 5 is not a necessary step, but the convenience of pushing and displaying the navigation information can be improved, the user experience is improved, and the route selection and sending operation of the user in the step 5 can be executed in the mobile phone APP or directly executed in the travel service APP.
On the basis of the travel method shown in fig. 2, after the user selects a final travel route according to actual needs, the method can also actively recommend service information to the vehicle-mounted map module for display and reminding when the vehicle needs to be maintained, and a specific flow is shown in fig. 3.
Judging whether the vehicle needs maintenance in the journey or after reaching the destination, if not, not pushing the service information; if the service station information is the service station information, the relevant service information is pushed through the background of the server, the travel service APP receives and receives the most convenient service station information, and the relevant information is displayed through the vehicle-mounted map module.
In addition, if maintenance needs to be completed in the process of travel, the travel route comprises a passing point of the most direct service station; if maintenance is needed after the journey is finished, the information of the service station closest to the destination can be actively displayed on the vehicle-mounted map module, so that the safety and reliability of commercial vehicles such as trucks and the like are guaranteed.
In conclusion, the travel method disclosed by the invention effectively and serially superposes the calculation modes of time, distance and travel cost, designs the intelligent map travel service system of the fuel vehicle and the electric vehicle, which can improve the economic performance and the attendance rate, and also accurately analyzes the oil consumption/electricity consumption by combining the driving behavior habits of users.
The above-mentioned intelligent map travel method for the commercial vehicle of the present invention can be implemented in a non-transitory computer-readable storage medium as a software program or a computer instruction or implemented in a control system having a memory and a processor, and the computing program is simple and fast to operate. Each functional unit in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit. The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, the invention also discloses a vehicle, wherein the vehicle comprises the intelligent map travel system for the commercial vehicle, and a processor in the intelligent map travel system for the commercial vehicle calls a program instruction to execute the intelligent map travel method for the commercial vehicle. The vehicle can be a gasoline vehicle, a pure electric vehicle or a hybrid vehicle according to three different calculation modes of the total oil charge and/or the total electric charge.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (11)
1. An intelligent map travel method for a commercial vehicle is characterized by comprising the following steps:
step 1: inputting a departure place and a destination;
step 2: calculating a plurality of recommended planning routes and highway tolls corresponding to each recommended planning route through a map API (application programming interface), wherein the recommended planning routes are a plurality of previous routes with short time and/or short distance;
and step 3: for the recommended planned route, firstly, slicing and segmenting according to road conditions to obtain each journey, and then analyzing and determining the oil consumption and/or the power consumption of each journey according to the load category of the vehicle and the driving behavior of a driver in each journey; the road conditions comprise plain high speed, plain national road, hilly high speed, hilly national road, mountainous area high speed, mountainous area national road and plateau;
and 4, step 4: and superposing the oil consumption or the power consumption of each journey, outputting total oil charge and/or total power charge based on each recommended planning route by combining the oil price and/or the power price, adding the total oil charge and/or the total power charge and the highway tolls to obtain the travel cost of each recommended planning route, and planning the route based on the travel cost.
2. The method for the intelligent map trip of the commercial vehicle according to claim 1, further comprising the following step 5: after selecting a proper route, the user clicks and sends the route to the vehicle, and the vehicle-mounted map module automatically navigates to the destination.
3. The method for intelligent map travel of commercial vehicles according to claim 1, wherein the step 1 is executed on a mobile phone remote terminal or a vehicle-mounted local terminal.
4. The method for the intelligent map trip of the commercial vehicle according to claim 1, wherein the load category is specifically divided into the following 5 categories: no-load, light load, half load, full load, and overload.
5. The method for intelligent map travel of commercial vehicles according to claim 1 or 4, wherein step 3 further comprises: and after the road condition and the load category are classified, determining historical accumulated average oil consumption and/or average power consumption of commercial vehicles of which the types are the same as the current travel load category, wherein the historical accumulated average oil consumption and/or average power consumption are average oil consumption values and/or average power consumption values of a plurality of vehicles under the current road condition and the load according to big data statistics, and determining the influence on the historical accumulated average oil consumption and/or average power consumption according to the past driving behaviors of a driver so as to calculate the oil consumption and/or power consumption of each travel.
6. The method for intelligent map travel of commercial vehicles according to claim 5, wherein step 3 specifically comprises the operation steps 3.1-3.5 of the driving behavior analysis model:
step 3.1: eigenvalue selection
Selecting 5 types of behaviors of rapid acceleration, rapid deceleration, idling, accelerator/electric switch stepping during parking and large accelerator/large electric switch stepping as characteristic values;
step 3.2: data acquisition and preprocessing
Firstly, cleaning and preprocessing the previous driving data of the accessed current driver, checking the data consistency, and obtaining the input data of the characteristic value after processing an invalid value and a missing value;
step 3.3: eigenvalue statistics and calculations
Counting the characteristic values according to the input data, counting, classifying and calculating the characteristic values in the travel in the input data according to the same load category and the same road condition, and acquiring a plurality of characteristic values G which are the same as the current driving condition i A value of (d);
step 3.4: construction of a Scoring model
Wherein the function f is the composite score of the driving behavior in the road section of the current journey, G i Is the ith characteristic value, a i N is equal to 5 for the feature weight matrix;
step 3.5: driving behavior scoring
Characteristic value G counted according to step 3.3 i And 3.4, calculating a comprehensive score of the driving behavior of the recommended planned route by the scoring model in the step 3.4.
7. The method of claim 6, wherein the method is based on the composite score f i And obtaining the oil consumption or the electricity consumption Totaloil of each journey according to the following formula i
Totaloil i ＝(AverageOil i- AverageOil i *(f i -80)*D i )*Mileage i
Wherein: totaloil i Representing the cumulative oil or electricity consumption, averageOil, of the ith trip in the recommended route i Representing the accumulated average oil consumption or the average power consumption f of the ith section with the same load type and the same road condition i A composite score, D, representing driving behavior during the ith trip i Is constant coefficient, can be adjusted according to different driving scenes and vehicle types, and is Mileage i Represents the total mileage of the ith journey;
mixing Totaloil i And summing to obtain the accumulated oil consumption or the accumulated electricity consumption Totaloil of each recommended route:
where m is the total number of trips divided in the corresponding recommended planned route.
8. The method for intelligent map travel of commercial vehicles according to claim 6, wherein the step 3.4 further comprises:
calculating the loss function of the model:
L＝f'-f
wherein, L represents a loss value, f' represents a true value, and f represents a predicted value.
Then, the feature weight matrix a is updated using the Adam gradient descent algorithm and the error back propagation algorithm i And stopping the training of the model after the characteristic weight matrix meets the corresponding condition.
9. The utility model provides a commercial car intelligence map trip system which characterized in that includes:
at least one processor; and at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method according to any one of claims 1 to 8.
10. A vehicle, characterized in that the vehicle comprises the intelligent map travel system for commercial vehicle as claimed in claim 9.
11. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method according to any one of claims 1 to 8.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211049928 | 2022-08-30 | ||
| CN202211049928X | 2022-08-30 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115587678A true CN115587678A (en) | 2023-01-10 |
Family
ID=84771190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211073893.3A Pending CN115587678A (en) | 2022-08-30 | 2022-09-02 | Intelligent map traveling method and system for commercial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115587678A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116013086A (en) * | 2023-03-22 | 2023-04-25 | 鱼快创领智能科技(南京)有限公司 | Oiling method and system based on Internet of vehicles |
| CN117152961A (en) * | 2023-09-20 | 2023-12-01 | 深圳市孪生云计算技术有限公司 | Wisdom road condition monitoring display system based on data analysis |
-
2022
- 2022-09-02 CN CN202211073893.3A patent/CN115587678A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116013086A (en) * | 2023-03-22 | 2023-04-25 | 鱼快创领智能科技(南京)有限公司 | Oiling method and system based on Internet of vehicles |
| CN117152961A (en) * | 2023-09-20 | 2023-12-01 | 深圳市孪生云计算技术有限公司 | Wisdom road condition monitoring display system based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115587678A (en) | Intelligent map traveling method and system for commercial vehicle | |
| DE102020101625A1 (en) | REAL-TIME EMISSION ASSESSMENT AND MONITORING | |
| US8682572B2 (en) | Method and device for evaluating vehicle's fuel consumption efficiency | |
| CN106643747B (en) | Navigation method and device | |
| CN108256714A (en) | A kind of wheelpath real-time risk assessment model based on car networking big data | |
| CN109703389B (en) | Vehicle pile network integrated charging scheduling device and method based on new energy bus | |
| CN108573600B (en) | Driver behavior induction and local traffic flow optimization method | |
| CN106022846A (en) | Automobile insurance pricing method, second-hand automobile pricing method and corresponding devices | |
| CN108154261B (en) | Recommendation method and device for optimal gas station | |
| CN115837918B (en) | Safe oil consumption reduction method and system based on scientific uphill and downhill driving guidance of commercial vehicle | |
| CN112580945B (en) | Multi-correlation coefficient-based dispatching method and vehicle dispatching optimization system | |
| CN110254285B (en) | Method and system for providing service for mileage anxiety user based on Internet of vehicles | |
| CN105608528A (en) | Taxi driver income-pressure assessment method and system based on big data analysis | |
| CN111210537A (en) | Oil consumption analysis method, device, equipment and storage medium | |
| CN117875674B (en) | Bus scheduling method based on Q-learning | |
| Bera et al. | Assessing consumer preferences for plug-in hybrid electric vehicle (PHEV): an Indian perspective | |
| CN113673756B (en) | Method and device for determining recommended speed of vehicle and computer equipment | |
| CN104331746A (en) | Separate-type dynamic path optimization system and method thereof | |
| CN111723871B (en) | Estimation method for real-time carriage full load rate of bus | |
| CN113408833A (en) | Public traffic key area identification method and device and electronic equipment | |
| CN111160597A (en) | Intelligent scheduling method based on comprehensive satisfaction degree of taxi driver | |
| CN112632374B (en) | Resident trip mode selection analysis method considering customized buses | |
| CN116129651A (en) | Traffic capacity calculation method based on resident trip behavior selection | |
| CN115456381A (en) | Gas station recommendation method based on intelligent networking data | |
| CN115713184A (en) | Bus route operation service evaluation method |
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 |