CN113283714B - Traffic jam suppression method based on group decision - Google Patents
Traffic jam suppression method based on group decision Download PDFInfo
- Publication number
- CN113283714B CN113283714B CN202110502780.XA CN202110502780A CN113283714B CN 113283714 B CN113283714 B CN 113283714B CN 202110502780 A CN202110502780 A CN 202110502780A CN 113283714 B CN113283714 B CN 113283714B
- Authority
- CN
- China
- Prior art keywords
- route
- data
- traffic
- attribute
- evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000001629 suppression Effects 0.000 title claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims abstract description 114
- 239000011159 matrix material Substances 0.000 claims abstract description 91
- 238000012544 monitoring process Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 9
- 230000008030 elimination Effects 0.000 claims description 6
- 238000003379 elimination reaction Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000007499 fusion processing Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000001351 cycling effect Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 230000005764 inhibitory process Effects 0.000 abstract description 4
- 230000000903 blocking effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000006855 networking Effects 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000003915 air pollution Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Computational Mathematics (AREA)
- Operations Research (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Library & Information Science (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a traffic jam suppression method based on group decision, and belongs to the technical field of traffic jam suppression. And collecting and uploading the traffic data to a cloud platform data center by using a terminal sensor system in the network environment, and collecting the traffic data of the intersections by using a traffic monitoring system of each intersection of the city to form an evaluation matrix. And reassigning and normalizing the attribute weights of each trunk road to obtain a comprehensive evaluation matrix. And calculating the comprehensive sorting value of each trunk according to the user preference and the comprehensive evaluation matrix data, and continuously uploading the latest data to the cloud platform data center. The method has obvious effect on the aspect of road congestion inhibition in the information physical system, effectively reduces road congestion blocking, and further reduces the accident rate of driving; the parking rate and waiting time in traffic driving are effectively reduced, and the travelling cost is further reduced. The congestion of the traffic road network is restrained, and the traffic condition of the urban arterial road is improved.
Description
Technical Field
The invention relates to a traffic jam suppression method based on group decision, and belongs to the technical field of traffic jam suppression.
Background
At present, in the urban development of China, more and more motor vehicles are used in the acceleration and the high-speed development of economy. The urban road is more and more complex, the traffic jam phenomenon is more and more serious, and the living standard of citizens is influenced. Traffic congestion is increasingly becoming a prominent problem in the traffic arts. Meanwhile, with the continuous development of information technology and intelligent manufacturing, cities are endowed with higher requirements, and new development opportunities are brought to the construction of smart cities. Urban traffic systems are an important component enabling human activities. At present, two thirds of cities in China have traffic jam phenomenon, and are particularly prominent in first-line cities. However, when traffic jams occur in large cities, once the traffic jams are not solved in time, more and more crowded areas are caused, even traffic paralysis is caused, and the traffic jams can cause a plurality of problems such as air pollution, travel time, fuel cost, harm to life health of people and the like. On the one hand, traffic jams increase emissions of carbon dioxide and several other pollutants in the air. Besides, the fuel consumption is greatly increased, and the travel cost of the traveler is increased. On the other hand, traffic accidents are very easy to cause due to traffic jams, the life and health of travelers are endangered, the ambulance is blocked during running, and the rescuing time of patients is endangered. Although the intelligent traffic system is a new field in traffic research, by means of ITS (intelligent traffic system), the current traffic facilities can be utilized to formulate a reasonable traffic control strategy, so as to relieve traffic jam and reduce environmental pollution, and thus, the intelligent traffic system is widely focused by students in various countries, and is one of the current approaches for solving the problems in the traffic field. However, existing studies are single decision individuals in making decisions. A single individual is unavoidably provided with a knowledge blind area or a professional limit, the wisdom and experience of multiple persons cannot be fully considered, the group decision theory can fully consider the opinion or experience of the multiple persons, and the decision risk can be greatly reduced in the decision process. There are few researchers from the group decision level that consider how to suppress traffic congestion. The decision of the intelligent traffic system is rarely used for the group decision idea, and the unreasonable and unfair phenomenon may exist in the decision result, which may cause the situation that the advice given by the user to the traffic intelligent system is in the opposite direction, the decision advice given by the traffic system is refused too much by the user, and the traffic system control strategy is invalid, so that the traffic jam is not relieved. Most of the current managers are from the whole, and the influence and preference degree of each factor on the path selection of the driver are analyzed to give a path strength induction scheme. There is an inevitable contradiction between the manager and the traveler. Because modern people have wide information and many influencing factors, the decision making is not possible to be well completed by the capability of a certain person, and the best decision can be made by the advantages of a concentrated group and the wisdom of people. The idea of group decision is proposed to make an auxiliary decision on the traveler, and the decision maker is made to agree in the decision making process, so that the result is more convincing.
Disclosure of Invention
The invention aims to provide a traffic jam suppression method based on group decision in an intelligent networking environment, which relates to multiple technologies of data acquisition (sensors, GPS (global positioning system) and radar), data processing and group decision, is applicable to the traffic jam suppression field in the field of an automobile information physical system (CPS), and particularly relates to a multi-attribute group decision scene, so that the defects in the prior art are overcome.
The invention is realized by the following technical scheme, which comprises the following steps:
step1: analyzing the decision problem, and selecting an alternative route set S, wherein s=1, 2,3, …, S; collecting road network traffic data by using a terminal sensor system in a network environment and uploading the road network traffic data to a cloud platform data center, and collecting intersection traffic data comprising vehicle-mounted sensors, traffic system data and GPS (global positioning system) position information by using traffic monitoring systems of all intersections of a city;
step2: the cloud platform data center performs data preprocessing on the received data, including data dimension reduction and data redundancy elimination, so as to obtain standardized original data, and determines scheme evaluation attribute sets P= { P1, P2, … and P d };
step3: the cloud platform scores the standardized original data by means of a plurality of road traffic auxiliary systems to form an evaluation matrix, d attributes of the standardized S routes are evaluated and scored by M intelligent traffic systems, and the attribute sets p= { p1, p2, …, p d } and p i of the routes represent the ith attribute of the routes; the scoring results are respectively stored in d multiplied by M matrixes, S evaluation matrixes are finally obtained, and forward processing and dimension elimination processing are carried out on the attribute evaluation indexes;
step4: the cloud platform data center respectively carries out reassignment and normalization processing on the attribute weights of all the trunk roads by using a proposed iterative Reverse Top-k algorithm based on the evaluation matrix of each route to obtain a comprehensive decision matrix;
step 4.1: for evaluation matrix A s S=1, 2,3, …, S, top-k operations are performed, typically k=2 to d-1, and the result is denoted Top (S) -k (m) The set corresponds to Top-k results under an mth expert evaluation system of the s-th route;
step 4.2: for the route, all Top(s) -k (m) The set forms a Top(s) -k set table, reverse Top-k operation is carried out on the Top(s) -k set table, and the obtained result is recorded as RTop(s) -k p[i] Reverse Top-k results for the ith attribute of the ith route, RTop(s) -k for all of the routes p[i] The set is formed into a RTop(s) -k set table, and evaluation similarity among d attributes of the route s can be calculated according to the RTop(s) -k set table obtained by Reverse Top-k operation, so that dominance of each attribute is obtained;
step 4.3: sequentially cycling for d-2 times (k=2-d-1), and carrying out normalization treatment on the attribute dominance obtained by each cycle to obtain an attribute weight value;
step 4.4: the cloud platform data center obtains the evaluation row vector A of the s-th route again according to the attribute weight value s ′ S=1, 2,3, …, S, sequentially obtaining the evaluation matrices of the S routes, merging the evaluation matrices into an s×d comprehensive evaluation matrix a, and transmitting the comprehensive evaluation matrix back to the terminal side;
step5: the equipment at the terminal side receives the data returned by the cloud platform data center, calculates the comprehensive sequencing value of each route according to the user preference and the comprehensive evaluation matrix data, obtains an optimal decision, and continuously uploads the latest data to the cloud platform data center; step6: the cloud platform center acquires new traffic data acquired by the terminal side sensor system and traffic data in the intersection monitoring system in real time, and performs data fusion processing with the historical data.
In the step2, the average speed of the routen is the total number of vehicles traveling on the route, and t is the number of road segments in the route;total length of route travel->Average waiting total duration of route traffic lights +.>Road condition evaluation As of route and road according to video images collected by vehicle-mounted recorder and traffic system, accident rate of million kilometers of route and road
The step3 includes the following scoring rules:
route congestion level: when (when)When the running state is smooth; />When the running state is basically smooth; />When the running state is light congestion; />When the running state is moderate congestion; />When the running state is heavy congestion;
route total length grade: the total length of the route L, the reverse data index, needs to be normalized to a forward evaluation index, generally in two ways:
mode 1, let u= (total route length l×route number S)/sum of all route lengthsThen->Wherein S is the route plan number;
mode 2, road-to-road million kilometers accident rateWherein N is ac The number of accidents on the route; when P>3, the accident rate grade of the million kilometers of the route road is high; when 1<T w When the accident rate of the million kilometers of the route road is less than or equal to 3, the accident rate grade of the million kilometers of the route road is medium; when T is w When the accident rate is less than or equal to 1, the accident rate grade of millions of vehicles and kilometers on the road is low.
The detailed calculation step of the step4 is as follows:
step 4.1: for evaluation matrix A s S=1, 2,3, …, S, performing a Top-k operation involving the number of attributes in the evaluation matrix, evaluating the number of expert scoring systems, for a given attribute set p= { p [1] with a given number of attributes d],p[2],…,p[d]}，p[i]Representing the ith attribute of the attribute p, wherein the value range of k is 2-d-1;
evaluation matrix A 1 ：
A 1 ＝[a 11 a 12 a 13 …a 1(M-1) a 1M
a 21 a 22 a 23 …a 2(M-1) a 2M
a 31 a 32 a 33 …a 3(M-1) a 3M
………………
a d1 a d2 a d3 …a d(M-1) a dM ]
A 1 An evaluation matrix representing route 1, wherein the number of attributes is d, the number of expert scoring systems is M, a 11 A score representing expert system number 1 for attribute 1; similarly, a d1 Is the scoring of the d-th attribute by the scoring system 1;
step 4.2: obtaining a Top (S) -k set table via step 4.1, wherein S = 1,2,3, …, S; top(s) -k set table contains M Top(s) -k (m) Set, where m=1, 2,3,…,M；
Reverse Top-k operation is performed on the set table Top(s) -k, and for a set p= { p [1], p [2], …, p [ d ] } of attributes with the number d of k being 2, the RTop-k set of the ith attribute number p [ i ] is:
wherein: s is the number of the route (s=1, 2,3, …, S), pi is the i-th attribute number of the route (i=1, 2,3, …, d); the evaluation similarity between every two attributes is calculated in sequence, and finally the dominance of each attribute can be obtained;
when k takes 2, the ith attribute p [ i ]]Dominance of |D(s) -2 p[i] |；
Step 4.3: for evaluation matrix A s Sequentially circulating the steps S4.1 to S4.2 until k=d-1; the attribute dominance obtained in each cycle is simply normalized to obtain the attribute pi]Final dominance value |d(s) p[i] |；
The final dominance of the D attributes of the route s may form a D M dominance matrix D(s);
d×m-dimensional attribute dominance matrix D(s):
D(s)＝[D(s) p[1] 0 0…0 0
0D(s) p[2] 0…0 0
0 0D(s) p[3] …0 0
………………
0 0 0…0D(s) p[d] ]
the cloud platform data center calculates and obtains a new evaluation matrix A of the route according to the dominance matrix s ′ ；
Wherein the method comprises the steps ofThereby obtaining
Step 4.4: sequentially for different evaluation matrix A s S=1, 2,3, …, S, and steps 4.1 to 4.3 are cycled to obtain S1 xd evaluation matrices a s ′ S=1, 2,3, …, S; s evaluation matrixes A are used by cloud platform data center s ′ Merging the two to form an S multiplied by d comprehensive evaluation matrix A, and transmitting the comprehensive evaluation matrix A back to the terminal side;
obtaining a comprehensive evaluation matrix A= [ A ] 1 ′ ,A 2 ′ ,A 3 ′ ,…,A S ′ ]。
The comprehensive sorting value calculation step of each route in the step5 is as follows:
definition of user U 1 Is = { u [1]],u[2],u[3],…,u[d]U [ i ]]Representing user U 1 Preference weights on the ith attribute;
each route corresponds to one row of the comprehensive evaluation matrix, and the comprehensive value f of each route is calculated w(s) ：
Wherein f w(s) Represents the integrated value of the s-th route, pi] ′ Calculating f, representing the scoring value of the ith column of the ith row of the comprehensive matrix A w(s) And comparing the magnitude of the value, and finally, selecting the route with the highest score for driving.
The data fusion mode in the step6 is as follows:
classifying according to the date and time of collection in the collected data according to quarters, months, weeks and days respectively; and fusing the data acquired in real time during decision-making with the historical data corresponding to the time period, and adding the data reliability as new original data.
The method has the advantages that the method has obvious effect on the aspect of road congestion inhibition in the information physical system, effectively reduces road congestion blocking, and further reduces the accident rate of driving; the parking rate and waiting time in traffic driving are effectively reduced, and the travelling cost is further reduced. The congestion of the traffic road network is restrained, and the traffic condition of the urban arterial road is improved.
Drawings
Fig. 1 is a flow chart of a traffic congestion suppression method based on group decisions in an intelligent networking environment.
Fig. 2 is a schematic diagram of an algorithm flow.
Fig. 3 is a scene model diagram under the traffic CPS.
Detailed Description
The invention aims to solve the technical problem of providing a novel technical method in the field of traffic jam suppression by utilizing the multi-attribute group decision theory, relates to multiple technologies of multi-data acquisition (sensors, GPS (global positioning system) and radar), data processing and group decision, and is applicable to the field of an automobile information physical system (CPS). Preferred embodiments of the present invention will be further described with reference to fig. 1 to 3; a flow chart of the method of the present invention is shown in fig. 1. The invention uses the terminal sensor system in the network environment to collect and upload to the cloud platform data center, and at the same time, uses the traffic monitoring system of each intersection to collect the traffic data of the intersection. The cloud platform data center performs data preprocessing on the received data, including data dimension reduction, data redundancy elimination and the like, so as to obtain standardized original data, and then scores the standardized original data by means of a plurality of road traffic auxiliary systems to form an evaluation matrix. And the cloud platform data center respectively reassigns and normalizes the attribute weights of the main roads by using the proposed algorithm based on the evaluation matrix of each main road to obtain a comprehensive evaluation matrix. And finally, the cloud platform data center transmits the comprehensive evaluation matrix back to the terminal side equipment. The equipment at the terminal side receives the data returned by the cloud platform data center, calculates the comprehensive sorting value of each trunk according to the user preference and the comprehensive evaluation matrix data, obtains an optimal decision, and continuously uploads the latest data to the cloud platform data center. In addition, the cloud platform center acquires new traffic data acquired by the terminal side sensor system and traffic data in the intersection monitoring system in real time, and performs fusion processing with the historical data. The invention has obvious effect in the aspect of road congestion inhibition in an information physical system (CPS), effectively reduces road congestion, and further reduces the accident rate of driving; the parking rate and waiting time in traffic driving are effectively reduced, and the travelling cost is further reduced. The congestion of the traffic road network is restrained, and the traffic condition of the urban arterial road is improved.
The algorithm flow chart of the method is shown in fig. 2, and the steps are as follows:
step1: and collecting and uploading the traffic data to a cloud platform data center by using a terminal sensor system in the network environment, and collecting intersection traffic data by using a traffic monitoring system of each intersection of the city. Including vehicle sensors, traffic system data, and GPS location information. The general reference is to: road segment number ID, road segment average vehicle speed V id Date of data acquisition D co Date D of data upload up Number N of road crossing s Waiting time T of red, yellow and green lamps on road section id Length of travel H of road section id Travel length S of road section id And road segment video image data;
the raw data is stored in the following format:
name: road segment ID, code: SEGMENT_ID, data type: string;
name: average speed V of road section id Code: SEGMENT_Vid, data type: number (Number);
name: date of data acquisition D co Code: SEGMENT_Dco, data type: date;
name: date D of data upload up Code: SEGMENT_Dup, data type: date;
name: number N of road crossing s Code: SEGMENT_Ns, data type: number (Number);
name: waiting time T of red, yellow and green lamps id Code: SEGMENT_Tid, data type: date;
name: road section travel time length H id Code: SEGMENT_Hid, data type: date;
name: road section travel length S id Code: SEGMENT_Sid, data type: number (Number);
name: road condition video image path VI, code: SEGMENT_PATH, data type: string;
name: valid samples, code: used_sample, data type: bool;
name: invalid samples, code: unused_sample, data type: and (3) Bool.
Step2: and the cloud platform data center performs data preprocessing on the received data, including data dimension reduction, data redundancy elimination and the like, so as to obtain standardized original data. The processed data metrics typically include: average speed of routeTotal running length L of route and number of road section traffic lights L S Average waiting total duration T of route traffic lights w Number of route accidents N ac The road condition assessment As (video image data dimension reduction) of the route and the road and the million car kilometer accident rate P of the route and the like;
the pre-processed data is stored in the following format:
name: average speed of routeCode: SEGMENT_V, data type: number (Number);
name: total route travel length L, code: SEGMENT_L, data type: number (Number);
name: traffic light number L S Code: SEGMENT_Ls, data type: number (Number);
name: average waiting total duration T of route traffic lights w Code: SEGMENT_Tw, data type: date;
name: number of route incidents N ac Code: SEGMENT_Nac, data type: number (Number);
name: route road condition assessment As, code: SEGMENT_As, data type: number (Number);
name: route road million car kilometer accident rate P, code: SEGMENT_P, data type: number (Number);
wherein the average speed of the routen is the total number of vehicles traveling on the route, and t is the number of road segments in the route; total length of route travel->Average waiting total duration of route traffic lights +.>Road condition evaluation As of route and road according to video images collected by vehicle-mounted recorder and traffic system, accident rate of million kilometers of route and road +.>
Step3: the cloud platform scores the standardized original data by means of a plurality of road traffic auxiliary systems to form an evaluation matrix (for incomplete evaluation matrix, filling is carried out by adopting a mean method). D attributes of standardized S routes (number of schemes for routing routes according to user location) through M intelligent transportation systems (attribute set p= { p [1] of routes],p[2],…,p[d]}，p[i]The i-th attribute representing the route) to score, and the scoring results are respectively stored in a d×M matrix A s (s=1, 2,3, …, S), S evaluation matrices are finally obtained.
The basic scoring rules are as follows:
route congestion level: when (when)When the running state is smooth; />When the running state is basically smooth; />When the running state is light congestion; />When the running state is moderate congestion; />When the running state is heavy congestion.
Route total length grade: the total length of the route L, the reverse data index, needs to be normalized to a forward evaluation index, generally in two ways: mode 1, let u= (total route length l×route number S)/sum of all route lengthsThen->Where S is the number of route schemes. When 1.5<When U, the route length grade is far; when 1.1<When U is less than or equal to 1.5, the route length grade is far; when 0.9<When U is less than or equal to 1.1, the route length grade is moderate; when 0.5<When U is less than or equal to 0.9, the route length grade is relatively close; when U is less than or equal to 0.5, the route length grade is near. Mode 2, when the total length L of the route>At 15km, the route length scale is far; when 12km<When L is less than or equal to 15km, the route length grade is far; when 8km<When L is less than or equal to 12km, the route length grade is moderate; when 5km<When L is less than or equal to 8km, the route length grade is relatively close; when L is less than or equal to 5km, the route length grade is near.
The average waiting total duration grade of the route traffic lights: because the development of traffic foundation engineering of each city is extremely unbalanced, the traffic road network of different cities is causedAll the more different. According to the information of the Chinese main urban traffic analysis report issued by the Goldmap and the traffic bureau together, the delay time of the Shanghai traffic is 39 seconds/car, and the delay time of the combined fertilizer is 25 seconds/car. Therefore, the division of the average waiting total duration level of the route traffic light should be dynamically adjusted to correspond to the corresponding city. Here we take the long salesman as an example: when the traffic lights of the route wait for the total duration T averagely w >150, the average waiting total duration grade of the route traffic lights is long; average waiting total duration 110 when route traffic light<T w When the average waiting total duration grade of the route traffic lights is less than or equal to 150, the average waiting total duration grade of the route traffic lights is longer; average waiting total duration 70 when route traffic light<T w When the average waiting total duration grade of the route traffic lights is less than or equal to 110, the average waiting total duration grade of the route traffic lights is moderate; when the traffic lights of the route wait for the total time length of 30<T w When the average waiting total duration grade of the route traffic lights is less than or equal to 70, the average waiting total duration grade of the route traffic lights is shorter; when the traffic lights of the route wait for the total duration T averagely w And when the average waiting total duration grade of the route traffic lights is less than or equal to 30, the average waiting total duration grade of the route traffic lights is short.
Route road condition assessment As: the road condition evaluation grade is simpler, and the urban road is generally processed by cement or asphalt. However, some roads with longer years have potholes, cracks, and the like. And performing data dimension reduction on video image data of the vehicle-mounted sensor, the vehicle data recorder and the traffic system by using a learned convolutional neural network to obtain a road condition evaluation value. The higher the evaluation value, the flatter the road is indicated.
Accident rate of million vehicles and kilometers on roadWherein N is ac Is the number of accidents occurring on the route. When P>3, the accident rate grade of the million kilometers of the route road is high; when 1<T w When the accident rate of the million kilometers of the route road is less than or equal to 3, the accident rate grade of the million kilometers of the route road is medium; when T is w When the accident rate is less than or equal to 1, the accident rate grade of millions of vehicles and kilometers on the road is low.
Step4: and the cloud platform data center respectively reassigns and normalizes the attribute weights of the main roads by using the proposed algorithm based on the evaluation matrix of each main road to obtain a comprehensive decision matrix.First, for the evaluation matrix A s (s=1, 2,3, …, S) Top-k operation (generally k=2 to d-1) was performed, and the result was denoted Top (S) -k (m) Set (Top-k results under the mth expert evaluation system corresponding to the s-th route). Next, for this route, all Top(s) -k (m) The set forms a Top(s) -k set table, reverse Top-k operation is carried out on the Top(s) -k set table, and the obtained result is recorded as RTop(s) -k p[i] (Reverse Top-k result for the ith attribute of the s-th route). RTop(s) -k for all of the route p[i] The sets form a table of RTop(s) -k sets. The evaluation similarity among d attributes of the route s can be calculated according to the RTop(s) -k set table obtained by Reverse Top-k operation, so that the dominance of each attribute is obtained. And (3) sequentially cycling for d-2 times (k=2-d-1), and carrying out normalization processing on the attribute dominance obtained by each cycle to obtain an attribute weight value. Finally, the cloud platform data center retrieves the evaluation matrix A of the s-th route according to the attribute weight value s ′ (s=1, 2,3, …, S), the evaluation matrices of the S routes obtained in sequence are combined into an s×d comprehensive evaluation matrix a, and the comprehensive evaluation matrix is transmitted back to the terminal side.
The detailed calculation steps are as follows:
s4.1 pair evaluation matrix A s (s=1, 2,3, …, S) performing Top-k operation involving the number of attributes in the evaluation matrix, the number of evaluation expert scoring systems, and for a given attribute number of d, the set of attributes p= { p [1]],p[2],…,p[d]}，p[i]Represents the ith attribute of the attribute p, wherein the value range of k is 2-d-1,
evaluation matrix A 1 ：
A 1 ＝[a 11 a 12 a 13 …a 1(M-1) a 1M
a 21 a 22 a 23 …a 2(M-1) a 2M
a 31 a 32 a 33 …a 3(M-1) a 3M
………………
a d1 a d2 a d3 …a d(M-1) a dM ]
A 1 An evaluation matrix representing route 1, wherein the number of attributes is d, the number of expert scoring systems is M, a 11 Representing the expert system number 1 for the scoring value of attribute 1. Similarly, a d1 Is the scoring of the d-th attribute by the scoring system 1;
if the expert number is M, k, taking 2, selecting the first 2 attributes with the highest score of the route, and calculating, wherein the evaluation matrix of the route can obtain M Top(s) -2 (m) Set (where m=1, 2,3, …, M; s=1, 2,3, …, S). When route number is 4, expert scoring system number is 1, top-k set when k is taken as 2 is:
evaluation matrix A for route 4 4 In the expert system number 1, the highest scoring 2 items are the 1 st and 3 rd attributes, top (4) -2 (1) ＝{a 11 ,a 31 }；
Suppose that the evaluation matrix A of the route of the present number 4 4 The expert scoring system comprises M expert scoring systems, wherein a Top (4) -2 set is obtained and comprises M Top (4) -2 (m) ；
Top(s)-k (m) The mth Top-k set for S route (s=1, 2,3, …, S; m=1, 2,3, …, M; k=2, 3, …, d-1). M Top(s) -k (m) Constructing a Top(s) -k set table;
top (4) -2 set table { Top (4) -2 (1) ，Top(4)-2 (2) ，Top(4)-2 (3) ，…，Top(4)-2 (M) }。
S4.2 through the step S4.1 described above we can obtain 1 Top (S) -k set table (where s=1, 2,3, …, S). A Top(s) -k set table contains M Top(s) -k (m) Set (where m=1, 2,3, …, M). Then, reverse Top-k operation is performed on the set table Top(s) -k, and for k being 2, the attribute set p= { p [1] with the number of attributes being d],p[2],…,p[d]I-th attribute number p [ i ]]The RTop-k set of (2) is:
wherein: s is the number of the route (s=1, 2,3, …, S), pi [ i ]]The i-th attribute number (i=1, 2,3, …, d) for the route. RTop(s) -k p[i] P [ i ] th route numbered s]RTop-k set of individual attributes, find out existence of pi from Top(s) -k set table]Expert scoring system number m forms RTop(s) -k p[i] . d RTops(s) -k p[i] Constructing an RTop(s) -k set table; RTop (4) -2 set table { RTop (4) -2 p[1] ，RTop(4)-2 p[2] ，RTop(4)-2 p[3] ，…，RTop(4)-2 p[d] -a }; the dominance among d attributes of the route s can be calculated according to the RTop(s) -k set table;
attributes pi in route s]And attribute p [ j ]]The evaluation similarity between them is |sim(s) -k (ij) |。
Wherein: i, j e 1,2,3, …, d. When k is taken to be 2,the evaluation similarity between every two attributes is calculated in sequence, and finally the dominance of each attribute can be obtained,/I>And j not equal to i, when k is 2, the ith attribute pi [ i ]]Dominance of |D(s) -2 p[i] |。
S4.3 pair evaluation matrix A s Steps S4.1 to S4.2 are sequentially circulated until k=d-1. Finally, the attribute dominance obtained by each cycle is simply normalized to obtain the attribute pi]Final dominance value |d(s) p[i] |；
The final dominance of the D attributes of the route s may form a D M dominance matrix D(s);
d×m-dimensional attribute dominance matrix D(s):
D(s)＝[D(s) p[1] 0 0…0 0
0D(s) p[2] 0…0 0
0 0D(s) p[3] …0 0
………………
0 0 0…0D(s) p[d] ]
the cloud platform data center calculates and obtains a new evaluation matrix A of the route according to the dominance matrix s ′ ；
Wherein the method comprises the steps ofThereby obtaining
S4.4 sequentially evaluating the matrix A for different s (s=1, 2,3, …, S) the steps S4.1 to S4.3 are looped, and S1 xd evaluation matrices a can be obtained s ′ (s=1, 2,3, …, S). S evaluation matrixes A are used by cloud platform data center s ′ Merging into an Sxd comprehensive evaluation matrix A, transmitting the comprehensive evaluation matrix back to the terminal side,
comprehensive evaluation matrix a= [ a ] 1 ′ ,A 2 ′ ,A 3 ′ ,…,A S ′ ]。
Step5: the equipment at the terminal side receives the data returned by the cloud platform data center, calculates the comprehensive sorting value of each route according to the user preference and the comprehensive evaluation matrix data, and presumes the user U 1 Is = { u [1]],u[2],u[3],…,u[d]U [ i ]]Representing user U 1 Preference weight on the ith attribute. Each route corresponds to one row of the comprehensive evaluation matrix, so we can calculate the comprehensive value f of each route w(s) ，
Wherein f w(s) Represents the integrated value of the s-th route, pi] ′ The score value of the ith column of the s-th row of the synthesis matrix a. Calculating f w(s) And comparing the magnitude of the value, and finally, selecting the route with the highest score for driving.
Step6: the cloud platform center acquires new traffic data acquired by the terminal side sensor system and traffic data in the intersection monitoring system in real time, and performs data fusion processing with the historical data;
the data collected are classified by quarter, month, week and day according to the date and time of collection, respectively. And fusing the data acquired in real time during decision-making with the historical data corresponding to the time period, and adding the data reliability as new original data.
The invention has obvious effect in the aspect of road congestion inhibition in an information physical system (CPS), effectively reduces road congestion, and further reduces the accident rate of driving; the parking rate and waiting time in traffic driving are effectively reduced, and the travelling cost is further reduced. The congestion of the traffic road network is restrained, and the traffic condition of the urban arterial road is improved.
As shown in fig. 3, the invention establishes a vehicle decision-making auxiliary model in a traffic CPS scene, collects information of vehicles in the running process through the sensor in fig. 3, and each vehicle uploads the collected real-time information to the cloud data platform. The preprocessed data is finally obtained, assuming that the data is scored by four expert scoring systems { e } 1 ,e 2 ,e 3 ,e 4 Three routes { s } are subjected to respective scoring rules 1 ,s 2 ,s 3 Property set p= { p [ 1}],p[2],p[3],p[4]Scoring, p [ i ]]Representing the set of properties pFour attributesL、T w P. The results are shown in tables 1,2 and 3, respectively.
Table 1:
table 2:
TABLE 3 Table 3
First, S.1 converts the tables into evaluation matrices A s (s＝s 1 ,s 2 ,s 3 ) Evaluation matrix of Table 1The method comprises the following steps:
correspondingly, the evaluation matrix of Table 2The method comprises the following steps:
evaluation matrix of Table 3The method comprises the following steps:
for s as above 1 Is an evaluation matrix A of (2) s1 Performing Top-k operation (k sequentially takes values of 2-d-1) to obtain Top(s) 1 ) -2 set table:
s.2 at Top(s) 1 ) Performing Reverse Top-k operation on the basis of the-2 set table to obtain RTop(s) 1 ) -2 set table, RTop(s) 1 )-2 p[1] ＝{e 1 ,e 3 }；RTop(s 1 )-2 p[2] ＝{e 3 ,e 4 }；
RTop(s 1 )-2 p[3] ＝{e 2 }；RTop(s 1 )-2 p[4] ＝{e 1 ,e 2 ,e 4 }。
S.3 according to RTop(s) 1 ) -2 the aggregate table can calculate the route s 1 Is a dominance among the 4 attributes of (c),
attribute p [1]]And attribute p [2]]Evaluation of similarity asSimilarly, the evaluation similarity between the attributes can be calculated for every two, and the +.>
S.4 calculating the dominance |D(s) of each attribute when k takes 2 1 )-2 p[i] |，
S.5 pair evaluation matrix A 1 Steps s.1 to s.4 are sequentially cycled until k=d-1. As above, when k takes 3, the dominance |D (s 1 )-3 p[i] |，
Normalizing the attribute dominance obtained in each cycle to obtain attribute pi]Final dominance value |d (s 1 ) p[i] |，
In the same way, can obtainRoute s 1 The final dominance of the 4 attributes of (a) may form a 4 x 4 dominance matrix D (s 1 )，
Cloud platform numberThe new evaluation matrix of the route is calculated according to the dominance matrix by the center
From the preceding formulaI.e. < ->The method can obtain:
s.6 sequentially evaluating the matrix A s (s＝s 1 ,s 2 ,s 3 ) And (5) circulating the steps S1 to S5. It is possible to obtain a solution,finally obtaining a 3 multiplied by 4 comprehensive evaluation matrix->1 st behavioral route s of comprehensive evaluation matrix A 1 Evaluation matrixIth column is p [ i ] of route]The attribute score is a score of the attribute,
A＝[19.313 24.180 11.440 22.470
15.150 16.636 24.032 21.000
24.462 18.434 12.923 21.360]。
s.7 suppose user U 1 For four attributesL、T w Preference of P is{0.25,0.35,0.3,0.1}, we can calculate the integrated value f for each route w(s) ，
Wherein s=s 1 ,s 2 ,s 3 . Can obtainFrom the calculation result->From the point of view, route s is selected 1 Is the optimal solution.
The invention provides an auxiliary decision for travelers based on the traffic jam suppression problem in the intelligent networking environment by using the thought of group decision, and the auxiliary decision is far away from the traffic jam area, so that the maximum throughput of a traffic trunk is obtained without losing fairness. Based on this situation, most people's wisdom is developed to induce driving of the driving vehicle by using the group decision idea. The group decision is to fully develop collective wisdom, and a plurality of decision makers participate in the whole process of decision analysis and decision making together, so that the group decision is more convincing. The decision maker is made to agree during the group decision making process, making the result more convincing.
The invention is illustrated by the above examples and is not limited to the examples, but rather the specific details of the process may be varied by those skilled in the art without departing from the scope of the invention as claimed.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (6)
1. The traffic jam suppression method based on the group decision is characterized by comprising the following steps of:
step1: analyzing the decision problem, and selecting an alternative route set S, wherein s=1, 2,3, …, S; collecting road network traffic data by using a terminal sensor system in a network environment and uploading the road network traffic data to a cloud platform data center, and collecting intersection traffic data comprising vehicle-mounted sensors, traffic system data and GPS (global positioning system) position information by using traffic monitoring systems of all intersections of a city;
step2: the cloud platform data center performs data preprocessing on the received data, including data dimension reduction and data redundancy elimination, so as to obtain standardized original data, and determines scheme evaluation attribute sets P= { P1, P2, … and P d };
step3: the cloud platform scores the standardized original data by means of a plurality of road traffic auxiliary systems to form an evaluation matrix, d attributes of the standardized S routes are evaluated and scored by M intelligent traffic systems, and the attribute sets p= { p1, p2, …, p d } and p i of the routes represent the ith attribute of the routes; the scoring results are respectively stored in d multiplied by M matrixes, S evaluation matrixes are finally obtained, and forward processing and dimension elimination processing are carried out on the attribute evaluation indexes;
step4: the cloud platform data center respectively carries out reassignment and normalization processing on the attribute weights of all the trunk roads by using a proposed iterative Reverse Top-k algorithm based on the evaluation matrix of each route to obtain a comprehensive decision matrix;
step 4.1: for evaluation matrix A s S=1, 2,3, …, S, top-k operations are performed, typically k=2 to d-1, and the result is denoted Top (S) -k (m) The set corresponds to Top-k results under an mth expert evaluation system of the s-th route;
step 4.2: for the route, all Top(s) -k (m) The set forms a Top(s) -k set table, reverse Top-k operation is carried out on the Top(s) -k set table, and the obtained result is recorded as RTop(s) -k p[i] Reverse Top-k results for the ith attribute of the ith route, RTop(s) -k for all of the routes p[i] The set is formed into a RTop(s) -k set table, and d attributes of the route s can be calculated according to the RTop(s) -k set table obtained by Reverse Top-k operationEvaluating the similarity to obtain the dominance of each attribute;
step 4.3: sequentially cycling for d-2 times (k=2-d-1), and carrying out normalization treatment on the attribute dominance obtained by each cycle to obtain an attribute weight value;
step 4.4: the cloud platform data center obtains the evaluation row vector A of the s-th route again according to the attribute weight value s ′ S=1, 2,3, …, S, sequentially obtaining the evaluation matrices of the S routes, merging the evaluation matrices into an s×d comprehensive evaluation matrix a, and transmitting the comprehensive evaluation matrix back to the terminal side;
step5: the equipment at the terminal side receives the data returned by the cloud platform data center, calculates the comprehensive sequencing value of each route according to the user preference and the comprehensive evaluation matrix data, obtains an optimal decision, and continuously uploads the latest data to the cloud platform data center;
step6: the cloud platform center acquires new traffic data acquired by the terminal side sensor system and traffic data in the intersection monitoring system in real time, and performs data fusion processing with the historical data.
2. The traffic congestion suppression method according to claim 1, wherein in the step2, the average speed of the routen is the total number of vehicles traveling on the route, and t is the number of road segments in the route; total length of route travel->Average waiting total duration of route traffic lights +.>Road condition evaluation As of route and road according to video images collected by vehicle-mounted recorder and traffic system, accident rate of million kilometers of route and road +.>
3. The traffic congestion suppression method based on group decision according to claim 1,
the step3 includes the following scoring rules:
route congestion level: when (when)When the running state is smooth; />When the running state is basically smooth;when the running state is light congestion; />When the running state is moderate congestion; />When the running state is heavy congestion;
route total length grade: the total length of the route L, the reverse data index, needs to be normalized to a forward evaluation index, generally in two ways:
mode 1, let u= (total route length l×route number S)/sum of all route lengthsThen->Wherein S is the route plan number;
mode 2, road-to-road million kilometers accident rateWherein N is ac The number of accidents on the route; when P>3, the accident rate grade of the million kilometers of the route road is high; when 1<T w When the accident rate of the million kilometers of the route road is less than or equal to 3, the accident rate grade of the million kilometers of the route road is medium; when T is w When the accident rate is less than or equal to 1, the accident rate grade of millions of vehicles and kilometers on the road is low.
4. The traffic congestion suppression method based on group decision as recited in claim 1, wherein the step4 detailed calculation step is as follows:
step 4.1: for evaluation matrix A s S=1, 2,3, …, S, performing a Top-k operation involving the number of attributes in the evaluation matrix, evaluating the number of expert scoring systems, for a given attribute set p= { p [1] with a given number of attributes d],p[2],…,p[d]}，p[i]Representing the ith attribute of the attribute p, wherein the value range of k is 2-d-1;
evaluation matrix A 1 ：
A 1 ＝[a 11 a 12 a 13 …a 1(M-1) a 1M
a 21 a 22 a 23 …a 2(M-1) a 2M
a 31 a 32 a 33 …a 3(M-1) a 3M
………………
a d1 a d2 a d3 …a d(M-1) a dM ]
A 1 An evaluation matrix representing route 1, wherein the number of attributes is d, the number of expert scoring systems is M, a 11 A score representing expert system number 1 for attribute 1; similarly, a d1 Is the scoring of the d-th attribute by the scoring system 1;
step 4.2: obtaining a Top (S) -k set table via step 4.1, wherein S = 1,2,3, …, S; top(s) -k set table contains M Top(s) -k (m) A collection, wherein M = 1,2,3, …, M;
reverse Top-k operation is performed on the set table Top(s) -k, and for a set p= { p [1], p [2], …, p [ d ] } of attributes with the number d of k being 2, the RTop-k set of the ith attribute number p [ i ] is:
wherein: s is the number of the route (s=1, 2,3, …, S), pi is the i-th attribute number of the route (i=1, 2,3, …, d);
the evaluation similarity between every two attributes is calculated in sequence, and finally the dominance of each attribute can be obtained;
and j is not equal to i;
when k takes 2, the ith attribute p [ i ]]Dominance of |D(s) -2 p[i] |；
Step 4.3: for evaluation matrix A s Sequentially circulating the steps S4.1 to S4.2 until k=d-1; the attribute dominance obtained in each cycle is simply normalized to obtain the attribute pi]Final dominance value |d(s) p[i] |；
The final dominance of the D attributes of the route s may form a D M dominance matrix D(s);
d×m-dimensional attribute dominance matrix D(s):
D(s)＝[D(s) p[1] 0 0…0 0
0D(s) p[2] 0…0 0
0 0D(s) p[3] …0 0
………………
0 0 0…0D(s) p[d] ]
the cloud platform data center calculates and obtains a new evaluation matrix A of the route according to the dominance matrix s ′ ；
Wherein the method comprises the steps ofThereby obtaining
Step 4.4: sequentially for different evaluation matrix A s S=1, 2,3, …, S, and steps 4.1 to 4.3 are cycled to obtain S1 xd evaluation matrices a s ′ S=1, 2,3, …, S; s evaluation matrixes A are used by cloud platform data center s ′ Merging the two to form an S multiplied by d comprehensive evaluation matrix A, and transmitting the comprehensive evaluation matrix A back to the terminal side;
obtaining a comprehensive evaluation matrix A= [ A ] 1 ′ ,A 2 ′ ,A 3 ′ ,…,A S ′ ]。
5. The traffic congestion suppression method based on group decision according to claim 1, wherein the step of calculating the comprehensive ranking value of each route in step5 is as follows:
definition of user U 1 Is = { u [1]],u[2],u[3],…,u[d]U [ i ]]Representing user U 1 Preference weights on the ith attribute;
each route corresponds to one row of the comprehensive evaluation matrix, and the comprehensive value f of each route is calculated w(s) ：
Wherein f w(s) Represents the integrated value of the s-th route, pi] ′ Calculating f, representing the scoring value of the ith column of the ith row of the comprehensive matrix A w(s) And comparing the magnitude of the value, and finally, we select the route with the highest score to enterAnd (5) traveling.
6. The traffic congestion suppression method based on group decision according to claim 1,
the data fusion mode in the step6 is as follows:
classifying according to the date and time of collection in the collected data according to quarters, months, weeks and days respectively; and fusing the data acquired in real time during decision-making with the historical data corresponding to the time period, and adding the data reliability as new original data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110502780.XA CN113283714B (en) | 2021-05-09 | 2021-05-09 | Traffic jam suppression method based on group decision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110502780.XA CN113283714B (en) | 2021-05-09 | 2021-05-09 | Traffic jam suppression method based on group decision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113283714A CN113283714A (en) | 2021-08-20 |
| CN113283714B true CN113283714B (en) | 2023-09-29 |
Family
ID=77278358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110502780.XA Active CN113283714B (en) | 2021-05-09 | 2021-05-09 | Traffic jam suppression method based on group decision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113283714B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886720A (en) * | 2017-11-07 | 2018-04-06 | 长沙理工大学 | Interval two-type fuzzy set festival holiday-based urban traffic congestion transfer analysis method |
| CN110570654A (en) * | 2019-09-16 | 2019-12-13 | 河南工业大学 | road section traffic jam dynamic detection method based on immunity |
-
2021
- 2021-05-09 CN CN202110502780.XA patent/CN113283714B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886720A (en) * | 2017-11-07 | 2018-04-06 | 长沙理工大学 | Interval two-type fuzzy set festival holiday-based urban traffic congestion transfer analysis method |
| CN110570654A (en) * | 2019-09-16 | 2019-12-13 | 河南工业大学 | road section traffic jam dynamic detection method based on immunity |
Non-Patent Citations (3)
| Title |
|---|
| 一种针对反向空间偏好top-k查询的高效处理方法;李淼;谷峪;陈默;于戈;;软件学报(02);全文 * |
| 基于乘客心理的最佳公交乘车路线选择方法研究;陈剑飞;徐良杰;;武汉理工大学学报(交通科学与工程版)(03);全文 * |
| 面向诱导的交通状态信息提取方法;戢晓峰;黄永忠;何增辉;韩春华;;计算机工程与应用(25);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113283714A (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105913661B (en) | A kind of express highway section traffic state judging method based on charge data | |
| CN107680401B (en) | Parking space satisfaction evaluation method based on interval two-type fuzzy set | |
| WO2018122808A1 (en) | Comfort-based self-driving planning method | |
| CN105608902B (en) | A kind of expressway traffic accident Multiple trauma identification system and method | |
| CN103895649B (en) | A kind of driver safety driving warning method | |
| CN101599217B (en) | Method for rapidly judging traffic state | |
| CN104318324B (en) | Shuttle Bus website and route planning method based on taxi GPS records | |
| CN108665191B (en) | Subway station outside association area calculation method based on aggregation effect | |
| CN108256714A (en) | A kind of wheelpath real-time risk assessment model based on car networking big data | |
| CN107729938B (en) | Rail station classification method based on bus connection radiation zone characteristics | |
| CN103745089A (en) | Multi-dimensional public transport operation index evaluation method | |
| CN109272745A (en) | A kind of track of vehicle prediction technique based on deep neural network | |
| CN107680391A (en) | Two pattern fuzzy control methods of crossroad access stream | |
| CN109686090A (en) | A kind of virtual traffic method of calculating flux based on multisource data fusion | |
| CN110084397A (en) | A kind of subway straightforward line planing method | |
| Majumdar et al. | Methodological framework to obtain key factors influencing choice of bicycle as a mode | |
| CN109118787A (en) | A kind of car speed prediction technique based on deep neural network | |
| WO2023143000A1 (en) | Auditing system for elderly age-friendly subdistrict built environment on basis of multi-source big data | |
| CN111080158A (en) | Urban intersection traffic danger index evaluation method based on composite weight | |
| CN113283762A (en) | Device for evaluating parking lot road planning | |
| CN103824450A (en) | Special vehicle route planning method based on traffic state rule for large-scale activities | |
| CN106548628A (en) | The road condition analyzing method that a kind of view-based access control model space transition net is formatted | |
| CN114550445B (en) | Urban area traffic safety state assessment method and device | |
| CN113487872B (en) | Bus transit time prediction method based on big data and artificial intelligence | |
| CN113283714B (en) | Traffic jam suppression method based on group decision |
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 |