CN106940829A - Recommend method in a kind of personalized path under car networking environment - Google Patents

Recommend method in a kind of personalized path under car networking environment Download PDF

Info

Publication number
CN106940829A
CN106940829A CN201710319683.0A CN201710319683A CN106940829A CN 106940829 A CN106940829 A CN 106940829A CN 201710319683 A CN201710319683 A CN 201710319683A CN 106940829 A CN106940829 A CN 106940829A
Authority
CN
China
Prior art keywords
path
section
traveler
personalized
road
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.)
Granted
Application number
CN201710319683.0A
Other languages
Chinese (zh)
Other versions
CN106940829B (en
Inventor
王建强
周文娟
冯鹏军
单丹蕾
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lanzhou Jiaotong University
Original Assignee
Lanzhou Jiaotong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lanzhou Jiaotong University filed Critical Lanzhou Jiaotong University
Priority to CN201710319683.0A priority Critical patent/CN106940829B/en
Publication of CN106940829A publication Critical patent/CN106940829A/en
Application granted granted Critical
Publication of CN106940829B publication Critical patent/CN106940829B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
    • G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
    • G08G1/096838—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route where the user preferences are taken into account or the user selects one route out of a plurality
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Remote Sensing (AREA)
  • Development Economics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

Recommend method the invention discloses the personalized path under a kind of car networking environment, this method is in personalized path recommendation process, while considering 4 kinds of trip sets of factors, i.e. times, expense, convenience, distance；In transportation network, the solution realized using stack thought is from the backtracking algorithms of all feasible path set of origin-to-destination；The path proposed algorithm based on Pearson correlation coefficient realized according to traveler individual character preference profiles vector sum feasible path characteristic vector.The present invention makes full use of real-time accurately a variety of transport information that car networking is provided, and with reference to the personalized trip requirements of traveler, the path recommendation service for meeting individual preference demand is provided for traveler, realizes the private customization of individual trip route；Can some unexpected traffics of real-time response there is provided when unexpected traffic occurs personalized path recommendation.

Description

Recommend method in a kind of personalized path under car networking environment
Technical field
The invention belongs to communications and transportation, information science technology field, it is related to the personalized path under a kind of car networking environment Recommendation method.
Background technology
Modern transportation trip based on information technology and the communication technology is used as work indispensable in people's daily life It is dynamic, it is constantly subjected to extensive concern.Car networking is the concentrated reflection that Internet of Things is applied to intelligent transportation system, with car networking technology Constantly promote with popularizing, collection, transmission and the storage of road grid traffic information are also more efficiently convenient, largely related to trip Transport information pours in the visual field of traveler.But, in face of the transport information of such numerous and complicated, how to extract and meet oneself individual character The information for changing preference is always the problem among traffic subject and behavior science.Emerging commending system is to we provide one kind Information overload is tackled, the effective way of information sifting is realized.With recommended technology, it can be extracted from magnanimity information for user Most highly desirable customized information.
Numerous manufacturers (such as electric business Amazon, video display Netflix and music Pandora, Last.fm and domestic bean cotyledon, Jingdone district, day cat etc.) personalized article recommendation service (such as news push, film books and periodicals private customization), effectively meet People filter out the individual demand for meeting own interests preference among the information of overload.Equally, commending system towards Brand-new traffic trip field, people are also increasingly strong to the personalized demand of transport information during trip.However, being directed to Personalized path recommends the feasible personalized path of field, particularly system to recommend method, have not yet to see open report (by In March, 2017).
Existing paths planning method is it is not intended that traveler personalization preferences, and transport information is originated single, big portion Point product is based on static information (no real-time change), or qualitative classification traffic information (very congestion, congestion, unobstructed Deng), and the transport information of non-quantized.The path planning product of main flow, such as Baidu map (navigation), high moral map (navigation), That also simply divides situation provides different types of path planning scheme (such as shortest time, minimum range, preferential highway Deng), do not consider the different trip preferences of Different Individual traveler.
The major defect of existing route planning technology has at following 3 points：
(1) the pathway traffic information of real-time dynamic change is not considered.A paths among transportation network can be by multiple roads Section is constituted, the change that the information such as transit time, road conditions on section also can be over time and change, can so cause path Status information shows non-linear, random complex characteristic.Change over time that is, the path among road network is attribute And the dynamic multi-attribute entity changed；The limitation of the technologies such as conventional traffic information collection, transmission, storage, calculating is limited by, it is existing Path planning system do not account for the pathway traffic information of real-time dynamic change.
(2) do not consider adverse weather factor (such as mist, rain, snow, haze) to path status and the quantization shadow of individual traveler Ring, the influence to events such as road construction, large-scale games to traffic trip is also contemplated for deficiency.Changeable weather conditions are to not people having a common goal The trip influence degree on road is different；Equally, road construction and competitive sports of all kinds of and property etc. are not planted, can influence office yet The road situation in portion region.And existing Path Planning Technique does not quantify to consider these factors to road passage capability Actual influence.
(3) the personalization preferences difference between different trip individuals is not considered.The factor being related among transportation network is various, And the individual traveler among reality is even more that demand is various.The preference factor that different travelers are considered is different, even if examining The preference factor of worry is much the same, and preference also inherently difference.At the same time it is also necessary to recognize, individual traveler Preference be a subjectivity, factor that is fuzzy and being difficult to quantitative measurment.Since so, traditional Path Planning Technique can not Realize the quantitative collection to individual traveler preference factor and analysis.
The content of the invention
It is an object of the invention to overcome defect present in prior art, there is provided the personalization under a kind of car networking environment Method is recommended in path, is a kind of in the transport information that car networking environment is provided, to meet demand of the user to personalization trip, A whole set of solution for the dynamically personalized routing information for meeting user preference is extracted with recommended technology.In the present invention, Road net model is set up, starting point and terminal is given, all feasible paths is searched out in road network, it is inclined according to the trip of traveler It is good, the path most like with user preference is found using proposed algorithm.
The present invention is in personalized path recommendation process, while consider 4 kinds of trip sets of factors, i.e., the time, expense, just Victory, distance }；In transportation network, the solution realized using stack thought is returned from all feasible path set of origin-to-destination Trace back algorithm；According to the realization of traveler individual character preference profiles vector sum feasible path characteristic vector based on Pearson correlation coefficient Path proposed algorithm.
Its concrete technical scheme is：
Method is recommended in a kind of personalized path under car networking environment, is comprised the following steps：
Step 1：Under car networking environment, the road net model for meeting personalized trip is set up；
Step 2：According to starting point and terminal, all feasible paths are found in road network；
Step 3：Obtain the route characteristic vector of feasible path；
Step 4：Traveler preference profiles vector is obtained according to the preference of traveler；
Step 5：Feasible path is ranked up with proposed algorithm；
Step 6：Output is ordered as the path of foremost as personalized recommendation path.
Further, the step 1 includes：
Step 1.1：The physics transportation network that G (V, A) represents to be made up of the node of finite number is defined, V represents set of node Close, A represents oriented section set.A represents an oriented section in road network, a ∈ A；R represents source point set, andS generations The point set of entry, andR represents a source point and r ∈ R；One point of destination of behalf, and s ∈ S；KrsRepresent OD to rs Between all feasible paths set；K represent OD one rs can walking along the street pass through,
Step 1.2：Path length attribute, path length can by Actual path via the physical distance in each section fold Plus obtain.
The path length attribute is defined as：Physics trip distance ls of the OD kth paths rsRs, kIt can be counted by formula (1) Calculate：
Wherein, laSection a physical length is represented,For correlated variables of the OD section a rs and path k, i.e. 0-1 Variable, if section a in connection OD on the kth paths rs,Otherwise
Step 1.3：Convenience is also the important attribute in section, influence section convenience principal element for category of roads, Weather condition, traffic accident situation and road control situation, path convenience by constitute the path all sections it is convenient Property superposition obtain.
Step 1.4：BPR functions are improved, for calculating section transit time.And then, path transit time can be by The transit time superposition for constituting all sections in the path is obtained.
The BPR functions are defined as：BPR functions are Bureau of Public Road's functions, are used in the free running time in section Calculate.
The section transit time is defined as：The actual travel time on section, it can be calculated with formula (4)：
Wherein,It is zero flow impedance, i.e. when flow is zero on section a the time required to vehicle traveling；xaFor section a traffic Flow；Qa' the actual capacity for being section a；α1, α2For retardation coefficient.
The actual capacity is defined as：After being influenceed by weather, traffic accident and road control on section The traffic capacity, can be calculated with formula (5)：
Wherein, QaFor section a basic capacity.
The path transit time is defined as：Travel times of the h moment OD kth paths rsCan be by formula (6) It is shown：
Step 1.5：Path expense attribute, path expense can by Actual path via the earned rates in each section fold Plus obtain.
The path expense attribute definition is：Travel cost es of the OD kth paths rsRs, k, can be calculated by formula (7)：
Wherein, eaRepresent the Congestion Toll on a of section.
Further, in step 1.3, the category of roads is defined as：Urban road grade be divided into through street, trunk roads, Secondary distributor road, branch road level Four；
For the convenient degree in section, one-level section value is set as " 1 ", and second grade highway section value is " 2 ", and three-level section value is " 3 ", level Four section value is " 4 "；
The weather condition is defined as：Influence degree of the weather condition to section a；
The traffic accident situation is defined as：Influence degree of the traffic accident situation to section a；
The road control situation is defined as：Influence degree of the road control situation to section a；
The section convenience is defined as：Section a convenience baCalculated by formula (2)：
Wherein, gaFor section a category of roads,Be expressed as influence degree of the weather condition to section a, such as mist, the rainy day, Snowy day etc.；It is expressed as influence degree of the traffic accident situation to section a；It is expressed as shadow of the road control situation to section a The degree of sound, such as repairs the roads, repaiies subway, and
The path convenience is defined as：Convenience bs of the OD kth paths rsRs, kCalculated by formula (3)：
Further, the step 2 includes：
Step 2.1：Input starting point vrWith terminal vs；
Step 2.2：By vjThe adjacent node in order of numbers of (j ∈ { 1,2,3 ..., n }) is sequentially stored into number from small to large GroupIn；Initialization pointers arrayA newly-built stack Stack；M=1；
Step 2.3：push(vr)；
Step 2.4：If Stack is not sky, vk=peek ()；Otherwise, step 2.8 is turned to；
Step 2.5：IfThenOtherwise, pop (),Turn To step 2.4；
Step 2.6：If peek () ≠ vs, turn to step 2.4；
2.7：Whole elements in backward (from stack bottom to stack top) printing stack Stack, record to KRs, m, m=m+1, pop (), turns to step 2.4；
2.8：The new set K of generationrs={ KRs, m|m∈N*}；
2.9：Algorithm terminates.
Push (the vr) be defined as：By data element vrStack top is pressed into, similarly
The peek () is defined as：Read stack top element and return to its value.
The pop () is defined as：Delete stack top element.
Further, the step 3 includes：
Step 3.1：By feasible path route characteristic vectorMark.
Step 3.2：In order that path is recommended with unified feasible standard, it is necessary to which the data in route characteristic vector are entered Row normalization, as shown in formula (8)：
Wherein, xmaxFor the maximum of each single item attribute in the four-tuple of alternative path.
Step 3.3：Route characteristic vectorAfter normalized, standardization is converted to Route characteristic vector
Further, the step 4 includes：
Step 4.1：Different travelers are different to the preference of travel time, expense, convenient degree and path distance. It therefore, it can define traveler i path preference profiles vectorAnd set 0≤ul≤ 1, and
Further, the step 5 includes：
Step 5.1：The related journey between preference profiles vector sum route characteristic vector is measured using Pearson correlation coefficient Degree.K is calculated according to Pearson correlation coefficientrsIn every feasible path and specified traveler i similarity degree, and then will be similar Recommend traveler i in degree highest path.Then h moment traveler i and alternative path k similarityIt can be counted by formula (9) Calculate：
The degree of strength of two correlation of variables is described, and
Further, the step 6 includes：
Step 6.1：
Traveler i is directed to, in the path that h moment similarity is maximumBe expressed as traveler i recommendations best suits trip The path of person's preference, and
Compared with prior art, beneficial effects of the present invention are：
1. the real-time accurately a variety of transport information for making full use of car networking to provide, are needed with reference to the personalized trip of traveler Ask, the path recommendation service for meeting individual preference demand is provided for traveler, realize the private customization of individual trip route；
2. can real-time response some unexpected traffics, such as traffic accident, road construction maintenance, large-scale game are carried Recommend for the personalized path when these situations occur；
3. from the perspective of overall transportation network, because the preference of traveler varies, personalized path is recommended can Effectively to realize that traffic flow is allocated according to individual preference, collection of all travelers on individual path is objectively avoided It is poly- so that the traffic flow distribution of whole transportation network is more rationally balanced.
Brief description of the drawings
Fig. 1 is that method flow diagram is recommended in the personalized path under car networking environment；
Fig. 2 is emulation road network.
Embodiment
Technical scheme is described in more detail with reference to specific drawings and Examples.
Method is recommended in a kind of personalized path under reference picture 1, car networking environment, is comprised the following steps：
Step 1：Under car networking environment, the road net model for meeting personalized trip is set up；
Step 2：According to starting point and terminal, all feasible paths are found in road network；
Step 3：Obtain the route characteristic vector of feasible path；
Step 4：Traveler preference profiles vector is obtained according to the preference of traveler；
Step 5：Feasible path is ranked up with proposed algorithm；
Step 6：Output is ordered as the path of foremost as personalized recommendation path.
Further, the step 1 includes：
Step 1.1：The physics transportation network that G (V, A) represents to be made up of the node of finite number is defined, V represents set of node Close, A represents oriented section set.A represents an oriented section in road network, a ∈ A；R represents source point set, andS generations The point set of entry, andR represents a source point and r ∈ R；One point of destination of behalf, and s ∈ S；KrsRepresent OD to rs Between all feasible paths set；K represent OD one rs can walking along the street pass through,
Step 1.2：Path length attribute, path length can by Actual path via the physical distance in each section fold Plus obtain.
The path length attribute is defined as：Physics trip distance ls of the OD kth paths rsRs, kIt can be counted by formula (1) Calculate：
Wherein, laSection a physical length is represented,For correlated variables of the OD section a rs and path k, i.e. 0-1 Variable, if section a in connection OD on the kth paths rs,Otherwise
Step 1.3：Convenience is also the important attribute in section, influence section convenience principal element for category of roads, Weather condition, traffic accident situation and road control situation.And then, path convenience can be by constituting all sections in the path Convenience superposition obtain.
The category of roads is defined as：Urban road grade is divided into through street, trunk roads, secondary distributor road, branch road level Four.According to Country《Urban planning quota index temporary provisions》Pertinent regulations, road can be divided into level Four, as shown in table 1：
The category of roads of table 1 divides table
For ease of quantitative research, for the convenient degree in section, one-level section value is set as " 1 " in the present invention, second grade highway section Value is " 2 ", and three-level section value is " 3 ", and level Four section value is " 4 ".
The weather condition is defined as：Weather condition is to section a influence degree, such as mist, rainy day, snowy day.
The traffic accident situation is defined as：Influence degree of the traffic accident situation to section a.
The road control situation is defined as：Road control situation is such as repaired the roads to section a influence degree, repaiies subway.
The section convenience is defined as：Section a convenience baCalculated by formula (2)：
Wherein, gaFor section a category of roads,Be expressed as influence degree of the weather condition to section a, such as mist, the rainy day, Snowy day etc.；It is expressed as influence degree of the traffic accident situation to section a；It is expressed as shadow of the road control situation to section a The degree of sound, such as repairs the roads, repaiies subway, and
The path convenience is defined as：Convenience bs of the OD kth paths rsRs, kIt can be calculated by formula (3)：
Step 1.4：BPR functions are improved, for calculating section transit time.And then, path transit time can be by The transit time superposition for constituting all sections in the path is obtained.
The BPR functions are defined as：BPR functions are Bureau of Public Road's functions, are used in the free running time in section Calculate.
The section transit time is defined as：The actual travel time on section, it can be calculated with formula (4)：
Wherein,It is zero flow impedance, i.e. when flow is zero on section a the time required to vehicle traveling；xaFor section a traffic Flow；Qa' the actual capacity for being section a；α1, α2For retardation coefficient.
The actual capacity is defined as：After being influenceed by weather, traffic accident and road control on section The traffic capacity, can be calculated with formula (5)：
Wherein, QaFor section a basic capacity.
The path transit time is defined as：Travel times of the h moment OD kth paths rsCan be by formula (6) It is shown：
Step 1.5：Path expense attribute, path expense can by Actual path via the earned rates in each section fold Plus obtain.
The path expense attribute definition is：Travel cost es of the OD kth paths rsRs, k, can be calculated by formula (7)：
The step 2 includes：
Step 2.1：Input starting point vrWith terminal vs；
Step 2.2：By vjThe adjacent node in order of numbers of (j ∈ { 1,2,3 ..., n }) is sequentially stored into number from small to large GroupIn；Initialization pointers arrayA newly-built stack Stack；M=1；
Step 2.3：push(vr)；
Step 2.4：If Stack is not sky, vk=peek ()；Otherwise, step 2.8 is turned to；
Step 2.5：IfThenOtherwise, pop (),Turn To step 2.4；
Step 2.6：If peek () ≠ vs, turn to step 2.4；
2.7：Whole elements in backward (from stack bottom to stack top) printing stack Stack, record to KRs, m, m=m+1, pop (), turns to step 2.4；
2.8：The new set K of generationrs={ KRs, m|m∈N*}；
2.9：Algorithm terminates.
Push (the vr) be defined as：By data element vrStack top is pressed into, similarly
The peek () is defined as：Read stack top element and return to its value.
The pop () is defined as：Delete stack top element.
The step 3 includes：
Step 3.1：By feasible path route characteristic vectorMark.
Step 3.2：In order that path is recommended with unified feasible standard, it is necessary to which the data in route characteristic vector are entered Row normalization, as shown in formula (8)：
Wherein, xmaxFor the maximum of each single item attribute in the four-tuple of alternative path.
Step 3.3：Route characteristic vectorAfter normalized, standardization is converted to Route characteristic vector
The step 4 includes：
Step 4.1：Different travelers are different to the preference of travel time, expense, convenient degree and path distance. It therefore, it can define traveler i path preference profiles vectorAnd set 0≤ul≤ 1, and
The step 5 includes：
Step 5.1：The related journey between preference profiles vector sum route characteristic vector is measured using Pearson correlation coefficient Degree.K is calculated according to Pearson correlation coefficientrsIn every feasible path and specified traveler i similarity degree, and then will be similar Recommend traveler i in degree highest path.Then h moment traveler i and alternative path k similarityIt can be counted by formula (9) Calculate：
The degree of strength of two correlation of variables is described, and
The step 6 includes：
Step 6.1：
Traveler i is directed to, in the path that h moment similarity is maximumBe expressed as traveler i recommendations best suits trip The path of person's preference, and
Embodiment
First, real-time traffic road net model, emulation road network as shown in Figure 2 are set up.Numerical order in figure on side is successively For section numbering, length (unit：Km), traffic capacity (unit：Veh/h), Road Expense (unit：Member), section grade.
Secondly, according to the trip purpose of traveler, from origin number 1 to terminal numbering 9, calculate it is all can walking along the street Footpath.According to the section attribute on feasible path, path basis attribute is obtained, as shown in table 2.
The path basis attribute of table 2.
Path attribute data is normalized, route characteristic vector is obtained, according to route characteristic vector analysis outbound path Feature, as shown in table 3.
The route characteristic of table 3. vector
Finally, for the traveler with difference preference, all feasible paths and the Pearson phases between them are calculated Like coefficient, Pearson similarity factors are ranked up, Pearson similarity factors it is bigger more meet traveler preference, so as to obtain Recommendation paths result is obtained, as shown in table 4.
Pearson similarity factors between the traveler of table 4. and path
For traveler 1, trip preference stresses time and convenience, therefore path 1 is most like therewith；For traveler 2, Trip preference stresses expense, to time and convenience also more preference, therefore path 2 is most like therewith；For traveler 3, go out Row preference stresses convenience, to the time also more preference, therefore path 1 is most like therewith；For traveler 4, trip preference side Weight length, to time and expense also more preference, therefore path 4 is most like therewith；For traveler 5, when trip preference stresses Between, to expense and convenience also more preference, therefore path 2 is most like therewith；For traveler 6, trip preference stresses convenient Property, to time and expense also more preference, therefore path 1 is most like therewith.
The foregoing is intended to be a preferred embodiment of the present invention, protection scope of the present invention not limited to this, any ripe Those skilled in the art are known in the technical scope of present disclosure, the letter for the technical scheme that can be become apparent to Altered or equivalence replacement are each fallen within protection scope of the present invention.

Claims (8)

1. method is recommended in the personalized path under a kind of car networking environment, it is characterised in that comprised the following steps：
Step 1：Under car networking environment, the road net model for meeting personalized trip is set up；
Step 2：According to starting point and terminal, all feasible paths are found in road network；
Step 3：Obtain the route characteristic vector of feasible path；
Step 4：Traveler preference profiles vector is obtained according to the preference of traveler；
Step 5：Feasible path is ranked up with proposed algorithm；
Step 6：Output is ordered as the path of foremost as personalized recommendation path.
2. method is recommended in the personalized path under car networking environment according to claim 1, it is characterised in that the step 1 includes：
Step 1.1：The physics transportation network that G (V, A) represents to be made up of the node of finite number is defined, V represents node set, A Represent oriented section set；A represents an oriented section in road network, a ∈ A；R represents source point set, andS represents mesh Point set, andR represents a source point and r ∈ R；One point of destination of behalf, and s ∈ S；KrsRepresent OD institute rs There is the set of feasible path；K represent OD one rs can walking along the street pass through,
Step 1.2：Path length attribute, path length by Actual path via each section physical distance superposition obtain；
The path length attribute is defined as：Physics trip distance ls of the OD kth paths rsRs, kCalculated by formula (1)：
l r s , k = Σ a l a · δ r s , k a , ∀ r , s , k - - - ( 1 )
Wherein, laSection a physical length is represented,For correlated variables of the OD section a rs and path k, i.e. 0-1 variables, If section a in connection OD on the kth paths rs,Otherwise
Step 1.3：Convenience is also the important attribute in section, and the principal element of influence section convenience is category of roads, weather Situation, traffic accident situation and road control situation, path convenience are folded by the convenience for constituting all sections in the path Plus obtain；
Step 1.4：BPR functions are improved, for calculating section transit time；And then, path transit time is by constituting this The transit time superposition in all sections in path is obtained；
The BPR functions are defined as：BPR functions are Bureau of Public Road's functions, are used in section and freely travel Time Calculation；
The section transit time is defined as：The actual travel time on section, calculated with formula (4)：
t a h ( x a ) = t a 0 [ 1 + α 1 ( x a Q a ′ ) α 2 ] , ∀ a ∈ A - - - ( 4 )
Wherein,It is zero flow impedance, i.e. when flow is zero on section a the time required to vehicle traveling；xaFor the section a magnitude of traffic flow； Qa' the actual capacity for being section a；α1, α2For retardation coefficient；
The actual capacity is defined as：It is current after being influenceed by weather, traffic accident and road control on section Ability, is calculated with formula (5)：
Q a ′ = ( 1 - h w a ) · ( 1 - h d a ) · ( 1 - h m a ) · Q a - - - ( 5 )
Wherein, QaFor section a basic capacity；
The path transit time is defined as：Travel times of the h moment OD kth paths rsBy formula (6) Suo Shi：
t r s . k h = Σ a t a h · δ r s , k a , ∀ r , s , k - - - ( 6 )
Step 1.5：Path expense attribute, path expense can by Actual path via the earned rates in each section be superimposed Arrive；
The path expense attribute definition is：Travel cost es of the OD kth paths rsRs, k, calculated by formula (7)：
e r s . k = Σ a e a · δ r s , k a , ∀ r , s , k - - - ( 7 )
Wherein, eaRepresent the Congestion Toll on a of section.
3. method is recommended in the personalized path under car networking environment according to claim 2, it is characterised in that step 1.3 In, the category of roads is defined as：Urban road grade is divided into through street, trunk roads, secondary distributor road, branch road level Four；
For the convenient degree in section, one-level section value is set as " 1 ", second grade highway section value is " 2 ", three-level section value is " 3 ", Level Four section value is " 4 "；
The weather condition is defined as：Influence degree of the weather condition to section a；
The traffic accident situation is defined as：Influence degree of the traffic accident situation to section a；
The road control situation is defined as：Influence degree of the road control situation to section a；
The section convenience is defined as：Section a convenience baCalculated by formula (2)：
b a = g a ( h w a + h d a + h m a ) - - - ( 2 )
Wherein, gaFor section a category of roads,It is expressed as influence degree of the weather condition to section a；It is expressed as traffic thing Therefore situation is to section a influence degree；Influence degree of the road control situation to section a is expressed as, and
The path convenience is defined as：Convenience bs of the OD kth paths rsRs, kCalculated by formula (3)：
b r s , k = Σ a b a · L a · δ r s , k a Σ a L a · δ r s , k a , ∀ r , s , k - - - ( 3 ) .
4. method is recommended in the personalized path under car networking environment according to claim 1, it is characterised in that the step 2 include：
Step 2.1：Input starting point vrWith terminal vs；
Step 2.2：By vjThe adjacent node in order of numbers of (j ∈ { 1,2,3 ..., n }) is sequentially stored into array from small to large In：Initialization pointers array A newly-built stack Stack；M=1；
Step 2.3：push(vr)；
Step 2.4：If Stack is not sky, vk=peek ()；Otherwise, step 2.8 is turned to；
Step 2.5：IfThenOtherwise, pop (),Turn to step Rapid 2.4；
Step 2.6：If peek () ≠ vs, turn to step 2.4；
2.7：Whole elements in backward (from stack bottom to stack top) printing stack Stack, record to KRs, m, m=m+1, pop () turn To step 2.4；
2.8：The new set K of generationrs={ KRs, m|m∈N*}；
2.9：Algorithm terminates；
Push (the vr) be defined as：By data element vrStack top is pressed into, similarly
The peek () is defined as：Read stack top element and return to its value；
The pop () is defined as：Delete stack top element.
5. method is recommended in the personalized path under car networking environment according to claim 1, it is characterised in that the step 3 include：
Step 3.1：By feasible path route characteristic vectorMark；
Step 3.2：In order that path is recommended with unified feasible standard, it is necessary to which the data in route characteristic vector are returned One changes, as shown in formula (8)：
X = 1 - x x m a x - - - ( 8 )
Wherein, xmaxFor the maximum of each single item attribute in the four-tuple of alternative path；
Step 3.3：Route characteristic vectorAfter normalized, standardization path is converted to Characteristic vector
6. method is recommended in the personalized path under car networking environment according to claim 1, it is characterised in that the step 4 include：
Step 4.1：Different travelers are different to the preference of travel time, expense, convenient degree and path distance；Definition Traveler i path preference profiles vectorAnd set 0≤ul≤ 1, and
7. method is recommended in the personalized path under car networking environment according to claim 1, it is characterised in that the step 5 include：
Step 5.1：The degree of correlation between preference profiles vector sum route characteristic vector is measured using Pearson correlation coefficient；Root K is calculated according to Pearson correlation coefficientrsIn every feasible path and specified traveler i similarity degree, and then by similarity highest Path recommend traveler i；Then h moment traveler i and alternative path k similarityCalculated by formula (9)：
p k h , i = s i m ( k h , u i ) = Σ j = 1 4 ( u j i - u i ‾ ) ( k j h - k h ‾ ) Σ j = 1 4 ( u j i - u i ‾ ) 2 Σ j = 1 4 ( k j h - k h ‾ ) 2 - - - ( 9 )
The degree of strength of two correlation of variables is described, and
8. method is recommended in the personalized path under car networking environment according to claim 1, it is characterised in that state step 6 Including：Step 6.1：
Traveler i is directed to, in the path that h moment similarity is maximumBe expressed as traveler i recommendations to best suit traveler inclined Good path, and
CN201710319683.0A 2017-04-28 2017-04-28 Personalized path recommendation method in Internet of vehicles environment Expired - Fee Related CN106940829B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710319683.0A CN106940829B (en) 2017-04-28 2017-04-28 Personalized path recommendation method in Internet of vehicles environment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710319683.0A CN106940829B (en) 2017-04-28 2017-04-28 Personalized path recommendation method in Internet of vehicles environment

Publications (2)

Publication Number Publication Date
CN106940829A true CN106940829A (en) 2017-07-11
CN106940829B CN106940829B (en) 2021-06-18

Family

ID=59464388

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710319683.0A Expired - Fee Related CN106940829B (en) 2017-04-28 2017-04-28 Personalized path recommendation method in Internet of vehicles environment

Country Status (1)

Country Link
CN (1) CN106940829B (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107146416A (en) * 2017-07-18 2017-09-08 陈剑桃 A kind of Intelligent traffic management systems
CN107368931A (en) * 2017-08-09 2017-11-21 西南交通大学 Logistics distribution path dynamic programming method and system based on big data analytical technology
CN108663062A (en) * 2018-03-27 2018-10-16 斑马网络技术有限公司 Paths planning method and its system
CN109272169A (en) * 2018-10-10 2019-01-25 深圳市赛为智能股份有限公司 Traffic flow forecasting method, device, computer equipment and storage medium
CN109598367A (en) * 2018-11-14 2019-04-09 阿里巴巴集团控股有限公司 Multipath processing method and processing device
CN109724616A (en) * 2019-02-28 2019-05-07 广州大学 Electric vehicle air navigation aid, system, readable storage medium storing program for executing and terminal device
CN110095134A (en) * 2019-05-16 2019-08-06 李培嵩 It is a kind of using the preference of user as the method and system of the path planning of core and navigation
CN110415546A (en) * 2018-04-26 2019-11-05 中移(苏州)软件技术有限公司 It parks abductive approach, device and medium
CN110569450A (en) * 2018-05-18 2019-12-13 北京搜狗科技发展有限公司 path recommendation method and device
CN110647693A (en) * 2019-09-23 2020-01-03 京东城市(北京)数字科技有限公司 Path recommendation method and device
WO2020019901A1 (en) * 2018-07-23 2020-01-30 腾讯科技（深圳）有限公司 Travel time determination method and apparatus, computer device, and storage medium
CN110853375A (en) * 2019-11-21 2020-02-28 东南大学 Random user balanced day-by-day dynamic traffic flow prediction method considering influence of overlapped paths
CN110930747A (en) * 2018-09-20 2020-03-27 南京锦和佳鑫信息科技有限公司 Intelligent internet traffic service system based on cloud computing technology
CN110992724A (en) * 2019-11-05 2020-04-10 华为技术有限公司 Vehicle navigation method and terminal
CN112991740A (en) * 2021-03-23 2021-06-18 苏州蓝图智慧城市科技有限公司 Vehicle guiding method, medium and equipment based on travel dispersion and clustering
CN113032444A (en) * 2021-05-24 2021-06-25 车巴达（苏州）网络科技有限公司 Travel planning method and device, electronic equipment and medium
CN113380064A (en) * 2021-05-21 2021-09-10 徐州工程学院 Efficient highway passing system and method
CN113538920A (en) * 2021-09-14 2021-10-22 腾讯科技（深圳）有限公司 Method and device for determining target driving route, electronic equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008180577A (en) * 2007-01-24 2008-08-07 Xanavi Informatics Corp Navigation device
CN102798394A (en) * 2011-05-26 2012-11-28 上海博泰悦臻电子设备制造有限公司 Route planning method and system
CN102916929A (en) * 2011-08-01 2013-02-06 杭州信雅达数码科技有限公司 Trust evaluating method based on fuzzy Petri net
CN104331743A (en) * 2014-10-11 2015-02-04 清华大学 Electric vehicle travel planning method based on multi-target optimization
CN104899195A (en) * 2014-01-26 2015-09-09 武汉联影医疗科技有限公司 Customized educational resource recommending method and apparatus
CN105547306A (en) * 2015-08-11 2016-05-04 深圳大学 Route pushing method and system thereof
CN106096756A (en) * 2016-05-31 2016-11-09 武汉大学 A kind of urban road network dynamic realtime Multiple Intersections routing resource

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008180577A (en) * 2007-01-24 2008-08-07 Xanavi Informatics Corp Navigation device
CN102798394A (en) * 2011-05-26 2012-11-28 上海博泰悦臻电子设备制造有限公司 Route planning method and system
CN102916929A (en) * 2011-08-01 2013-02-06 杭州信雅达数码科技有限公司 Trust evaluating method based on fuzzy Petri net
CN104899195A (en) * 2014-01-26 2015-09-09 武汉联影医疗科技有限公司 Customized educational resource recommending method and apparatus
CN104331743A (en) * 2014-10-11 2015-02-04 清华大学 Electric vehicle travel planning method based on multi-target optimization
CN105547306A (en) * 2015-08-11 2016-05-04 深圳大学 Route pushing method and system thereof
CN106096756A (en) * 2016-05-31 2016-11-09 武汉大学 A kind of urban road network dynamic realtime Multiple Intersections routing resource

Cited By (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107146416B (en) * 2017-07-18 2020-01-21 深圳市锦粤达科技有限公司 Intelligent traffic management system
CN107146416A (en) * 2017-07-18 2017-09-08 陈剑桃 A kind of Intelligent traffic management systems
CN107368931B (en) * 2017-08-09 2020-10-09 西南交通大学 Logistics distribution path dynamic planning method and system based on big data analysis technology
CN107368931A (en) * 2017-08-09 2017-11-21 西南交通大学 Logistics distribution path dynamic programming method and system based on big data analytical technology
CN108663062A (en) * 2018-03-27 2018-10-16 斑马网络技术有限公司 Paths planning method and its system
CN108663062B (en) * 2018-03-27 2022-07-22 斑马网络技术有限公司 Path planning method and system
CN110415546A (en) * 2018-04-26 2019-11-05 中移(苏州)软件技术有限公司 It parks abductive approach, device and medium
CN110569450B (en) * 2018-05-18 2024-03-26 北京搜狗科技发展有限公司 Path recommendation method and device
CN110569450A (en) * 2018-05-18 2019-12-13 北京搜狗科技发展有限公司 path recommendation method and device
WO2020019901A1 (en) * 2018-07-23 2020-01-30 腾讯科技（深圳）有限公司 Travel time determination method and apparatus, computer device, and storage medium
CN110930747A (en) * 2018-09-20 2020-03-27 南京锦和佳鑫信息科技有限公司 Intelligent internet traffic service system based on cloud computing technology
CN110930747B (en) * 2018-09-20 2021-11-19 上海丰豹商务咨询有限公司 Intelligent internet traffic service system based on cloud computing technology
CN109272169A (en) * 2018-10-10 2019-01-25 深圳市赛为智能股份有限公司 Traffic flow forecasting method, device, computer equipment and storage medium
CN109598367B (en) * 2018-11-14 2023-05-09 创新先进技术有限公司 Multipath processing method and device
CN109598367A (en) * 2018-11-14 2019-04-09 阿里巴巴集团控股有限公司 Multipath processing method and processing device
CN109724616A (en) * 2019-02-28 2019-05-07 广州大学 Electric vehicle air navigation aid, system, readable storage medium storing program for executing and terminal device
CN110095134A (en) * 2019-05-16 2019-08-06 李培嵩 It is a kind of using the preference of user as the method and system of the path planning of core and navigation
CN110095134B (en) * 2019-05-16 2023-02-10 李培嵩 Method and system for planning and navigating path by taking preference of user as core
CN110647693A (en) * 2019-09-23 2020-01-03 京东城市(北京)数字科技有限公司 Path recommendation method and device
CN110647693B (en) * 2019-09-23 2021-03-05 北京京东智能城市大数据研究院 Path recommendation method and device
CN110992724A (en) * 2019-11-05 2020-04-10 华为技术有限公司 Vehicle navigation method and terminal
CN110992724B (en) * 2019-11-05 2021-11-19 华为技术有限公司 Vehicle navigation method and terminal
CN110853375A (en) * 2019-11-21 2020-02-28 东南大学 Random user balanced day-by-day dynamic traffic flow prediction method considering influence of overlapped paths
CN112991740B (en) * 2021-03-23 2022-03-11 苏州蓝图智慧城市科技有限公司 Vehicle guiding method, medium and equipment based on travel dispersion and clustering
CN112991740A (en) * 2021-03-23 2021-06-18 苏州蓝图智慧城市科技有限公司 Vehicle guiding method, medium and equipment based on travel dispersion and clustering
CN113380064A (en) * 2021-05-21 2021-09-10 徐州工程学院 Efficient highway passing system and method
CN113032444A (en) * 2021-05-24 2021-06-25 车巴达（苏州）网络科技有限公司 Travel planning method and device, electronic equipment and medium
CN113538920A (en) * 2021-09-14 2021-10-22 腾讯科技（深圳）有限公司 Method and device for determining target driving route, electronic equipment and storage medium
CN113538920B (en) * 2021-09-14 2021-12-10 腾讯科技（深圳）有限公司 Method and device for determining target driving route, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN106940829B (en) 2021-06-18

Similar Documents

Publication Publication Date Title
CN106940829A (en) Recommend method in a kind of personalized path under car networking environment
Lang et al. The new metropolis: Rethinking megalopolis
CN104484514B (en) A kind of elastic public bus network method for designing for evading congested link
Boussauw et al. Short trips and central places: The home-school distances in the Flemish primary education system (Belgium)
Ngo Urban bus ridership, income, and extreme weather events
CN102169524A (en) Staged multi-path model algorithm of urban rail transit network passenger flow distribution
CN105205557A (en) Design method for conventional urban public transit network
CN103530694B (en) The city underground dynamic bus traveler assignment method built based on time-space network
CN107123260A (en) Method of traffic assignment based on traveler budget limit
CN106203725A (en) Door-to-door trip route scheme personalized recommendation method based on heuristic search
CN107301492A (en) A kind of subway ticketing classifying method based on gauss hybrid models
CN111060119B (en) City slow-travel navigation method and system based on street view visual element scoring
CN107527137A (en) Urban mass transit network maturity determines method
de Jong et al. The driving factors of passenger transport
CN110222912A (en) Railway stroke route method and device for planning based on Time Dependent model
CN108986459A (en) A kind of highway crowded leading method current based on reservation
CN107092986A (en) The bus passenger travel route choice method based on website and collinearly run
CN106709591A (en) Cooperative car-pooling route selection method with uncertain demand in Internet of Vehicles environment
Turner et al. Bicycle and pedestrian travel demand forecasting: Literature review
Winters et al. The Canadian Bikeway Comfort and Safety metrics (Can-BICS): National measures of the bicycling environment for use in research and policy
Yagi et al. Joint models of home-based tour mode and destination choices: applications to a developing country
Himanen et al. Daily travelling viewed by self-organizing maps
Mogridge If London is more spread out than Paris, why don't Londoners travel more than Parisians?
Chu Network equilibrium model with dogit and nested logit structures
Götschi et al. Valuing public investments to support bicycling

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20210618