CN108596727A - A kind of management of shared bicycle and decision-making technique - Google Patents
A kind of management of shared bicycle and decision-making technique Download PDFInfo
- Publication number
- CN108596727A CN108596727A CN201810385708.1A CN201810385708A CN108596727A CN 108596727 A CN108596727 A CN 108596727A CN 201810385708 A CN201810385708 A CN 201810385708A CN 108596727 A CN108596727 A CN 108596727A
- Authority
- CN
- China
- Prior art keywords
- bicycle
- release position
- shared bicycle
- decision
- management
- 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
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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- 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
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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
- 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
Abstract
Management and the decision-making technique of a kind of shared bicycle is claimed in the present invention, including：It determines and launches ground, collect supplemental characteristic, with the model of fuzzy synthetic evaluation of DEA, structure subordinated-degree matrix, which determines, launches ground index grade, is aided with multiple objective programming, determines the bicycle injected volume for launching ground and launches the bicycle injected volume of ground different regions；It is returned using SVM, with the parameter collected, the functional relation of shared bicycle injected volume at any time is determined by the mapping of the gaussian kernel function of higher dimensional space, determines the bicycle injected volume of areal different time；It proposes quantity decision management method, is established based on FICO personal credit appraisement systems, specification user's vehicle reduces O＆M cost by multiple objective programming according to the optimal scheduling maintenance center of release position different set in region.
Description
Technical field
The invention belongs to the models such as fuzzy overall evaluation, multiple objective programming, SVM recurrence, particularly belong to manage shared bicycle
Decision model.
Background technology
Internet lease bicycle (i.e. shared bicycle) refer to enterprise campus, subway station, bus station, residential block,
Shopping centre, common service area etc. provide bicycle bicycle shared service, are a kind of timesharing leasehold modes.Shared bicycle is a kind of new
The shared economy of type.It since 2016, has been poured in the madness of capital, shared bicycle has welcome eruptive growth, is solving city
Traffic trip " last one kilometer " problem, alleviation urban traffic blocking etc. have played positive effect.
Enterprise rides on a horse to enclose under the expansion of formula and the promotion energetically of capital, and the quantity of shared bicycle has obtained very fast swollen
It is swollen.Shared bicycle has become one of Chinese new four inventions at present, has been transported to many cities in the world.It is as one
Typically " Internet of Things+internet " is applied, and bicycle lease service is provided a user by the control in high in the clouds.Its technology used
Including cloud computing basic platform, data assets and platform service etc..
However, consequently also there are various problems of management, and need rapid feedback and satisfied solution.From platform public affairs
The angle of department will handle rapidly user feedback problem, while need to handle as early as possible these vehicles, reduce these disabled vehicles to the greatest extent
The number probability being used by a user.How bicycle is dispatched by riding away to after each corner in city and just can guarantee that they can be by more
More people ride up to.Enterprise also lacks the related punitive measures with vehicle, illegal parking uncivil to user simultaneously.The place of these problems
Reason, platform management person and users both sides extremely pay close attention to.There is presently no finding, one kind is effective, efficiently quantization is managed
Reason method can more timely and effectively handle the problem of encountering, and improve the service quality of platform and the satisfaction of users.
Invention content
Present invention seek to address that the above problem of the prior art.It proposes one kind and can more timely and effectively handle and encounter
The problem of, the method that improves the service quality of platform and the satisfaction of users.Technical scheme is as follows：
A kind of management of shared bicycle and decision-making technique comprising following steps：
1) it determines and launches ground, collect supplemental characteristic, establish the model of fuzzy synthetic evaluation based on DEA DEAs,
By building subordinated-degree matrix, maximum membership degree is calculated, shared bicycle is obtained and launches evaluation index grade to pick out needs
Launch the area for sharing bicycle；
2) it establishes and shares bicycle release position site selection model, the release position in area is determined by multiple objective programming, according to not
The bicycle quantity that should be launched with position quadratic programming determination；
3) Gaussian kernel SVR regression models are established, shared bicycle is determined by the mapping of the gaussian kernel function of higher dimensional space
The functional relation of injected volume at any time；
4) it proposes quantity decision management method, personal credit appraisement system is established based on U.S.'s personal credit evaluation method, advise
Model user's vehicle reduces O＆M by multiple objective programming according to the optimal scheduling maintenance center of release position different set in region
Cost.
Further, it is specific to establish the shared bicycle dispensing addressing evaluation model of the fuzzy synthesis based on DEA for the step 1)
Including step：Is defined by shared bicycle and launches suitable comment according to bicycle release position selecting index principle for geographic classification first
Valence index, then by DEA algorithms, the index of the assessment of efficiency of k-th of DMU decision package is obtained, formula is as follows：
1≤k≤s is the index of the assessment of efficiency of k-th of decision package, ur>=0, vi≥0
Wherein XjIt is inputted for m, k>0, st. indicates condition, Xj=(x1j,x2j,...,xmj),YjIt is exported for n, Yj=
(Y1j,Y2j,...,Ynj) and xij>0,yrj>0, the weight vector of input is v=(v1,v2,...,vm)T, u=(u1,u2,...un)T,
Vm indicates that m-th evaluation unit corresponds to input weight vector, and .un indicates that n-th of evaluation unit corresponds to output weight vector, efficiency index
Refer to output uTYjWith input vTxjRatio.
Further, it further includes the steps that determining index weights that the step 1), which shares bicycle to launch evaluation index,：First
Judgement Matricies compare relative importance two-by-two using expert graded to lower layer's element that identity element dominates, and construction is sentenced
Disconnected matrix B=(bij)m×n, by the way that factor is carried out multilevel iudge two-by-two, obtain the comparison power of relative importance, establish and judge
Matrix；
Consistency check is carried out to matrix：CI=0, CR=0<1, judgment matrix can consider with uniformity, calculating power
Then vector utilizes DEA algorithms to calculate the index of the assessment of efficiency of each DMU, and by the power for the indexs at different levels being finally calculated
Data-Statistics.
Further, the structure subordinated-degree matrix, specifically includes step：
For whether suggesting setting up the opinion rating of bicycle release position according to specific influence, it is subordinate to by nondimensionalization
Category degree matrix:Then two-level index subordinated-degree matrix is obtained according to three-level weight matrix：Obtain weight vector to the end：According to most
Big degree of membership principle obtains the shared bicycle in area and launches evaluation index level, finally determines each department score；Finally according to reality
Appraisal result is divided into five grades by situation, and multiple areas of selection are calculated score and are classified according to standards of grading.
Further, the step 2) is established specifically is wrapped based on the shared bicycle release position site selection model of multiple objective programming foundation
Include step：
Initially set up regional bicycle injected volume model：
In formula：Pi：The shared bicycle output (/ hour) in regional i planning years：Sij:J classes property ground in regional i
Product (square metre)；αj:Jth class land character reference capacity rate；βj：Jth class land character Traffic area location regulation coefficient；δj：Jth
Class land character cycling trip ratio；ω：Shared bicycle trip accounts for cycling trip ratio；
In formula：ZZL：Shared bicycle turnover rate；CI：Unit interval shares bicycle and lends number；SL：Initial time bicycle number
Amount；
In formula：wi:The shared bicycle injected volume of i-th of release position；
Finally, it establishes to establish based on multiple objective programming and shares bicycle release position site selection model, made using cosine distribution function
For service quality function, while considering two targets of service quality that overall society cost and facility provide, thus establishes multiple target
Public bicycles release position site selection model.
Further, the public bicycles release position site selection model for establishing multiple target is specially：
In formula：C:Release position construction cost (ten thousand yuan)；cj：The fixed cost of j-th of release position；wi：I-th release position
Shared bicycle injected volume；D2：With a distance from pedestrian farthest tolerates from shared bicycle, D1：With a distance from pedestrian is tolerated recently from shared bicycle；Q:
Release position service quality；J：The set of dispensing；cjz：The fixed cost of j-th of release position；qij：J-th of release position is to demand point i
Service quality；c0：Distance costs in unit demand；dij：Distance of j-th of release position to demand point i；xj：Whether in j
Establish demand point；yij：Demand point i is serviced by j.
Further, further include the steps that being optimized to model：Item is carried out using based on release position and demand point distance
Part constrained optimization.
Further, the step 3) establishes Gaussian kernel SVR regression models and specifically includes step：
Support vector machines first indicates the relationship of different areas injected volume and time by equation：It is damaged with hinge
It loses function and solves this equation, be re-introduced into sparse variable and solve this problem：
Then gaussian kernel function is used, present data are mapped to higher dimensional space, keep it linear in higher dimensional space
Expression, then carries out Taylor expansion：The data of gained are mapped back into the injected volume that original space is last again；
Finally, it is converted into a dual problem by introducing Lagrange multiplier, relational model is solved, is finally solved
Different regions, the relationship of bicycle injected volume and time.
Further, the step 4) establishes quantity decision management method and specifically includes step：
It is primarily based on FICO and establishes personal credit appraisement system；For management bicycle, the tune set based on release position is set up
Repair center system is spent, shared bicycle release position position and scale and demand is found out, establishes Multiobjective programming models, to
Make allotment center construction operation, transportation cost sheet is minimum, therefore we are with the target letter of the minimum target as an optimization of transportation cost
Number, it is determined that be based on multiple objective programming control centre model.
Further, the object function of the optimization aim is：
Z：Transportation cost；N：The set of release position；M：The set of home-delivery center's candidate point；qj:The tune of release position j (j ∈ N)
With demand；dij:Node i (i ∈ M ∪ N) arrives the distance of node j (j ∈ M ∪ N)；c1：Unit cost；Oi：Candidate point i (i
∈ M) build fixed cost；Qi：Dispense supply amount；zi：0-1 variables；yij=1：Indicate the clothes for being responsible for client's point j by candidate point i
Business, ziIndicate that candidate point i is selected.
It advantages of the present invention and has the beneficial effect that：
(1) the problem of the problem of linearly inseparable, can be converted to linear separability by Gaussian kernel SVR regression models.
(2) model can adapt to higher dimensional space data and fitting effect it is better than commonly returning.
For two above advantage we by taking rain spends the injected volume of door as an example, compare the homing method of several mainstreams, it is minimum
Two multiply recurrence, ridge regression, and lasso is returned.
Experiment is as can be seen that the fitting effect of our model is better than other mainstream homing methods.
(3) the personal credit evaluation system based on FICO has stronger generalization, and company can be according to actual conditions to it
Evolution rules carry out specific customization.
(4) plot ratio, land type, density of stream of people of regional bicycle injected volume models coupling different areas etc. because
Element has practicability.
(5) sharing the addressing of bicycle release position can be in conjunction with different regions with shared bicycle scheduling maintenance center location model
Different situations account for, and are applicable in flexible.
Innovative point is to determine that shared bicycle launches addressing place from multiple angles, has been carried out once with Gaussian kernel to data
It is mapped to higher dimensional space, then has carried out linear regression.
Description of the drawings
Fig. 1 is the work flow diagram that the present invention provides that preferred embodiment provides：
Fig. 2 shows the fuzzy synthesis based on DEA to share bicycle dispensing addressing evaluation model flow chart；
Fig. 3, which shows to establish based on multiple objective programming, shares bicycle release position site selection model flow chart；
Fig. 4 shows Gaussian kernel SVR regression model flow charts；
Fig. 5 shows the Establishing process figure of quantity decision management method；
Fig. 6 is that the present invention provides preferred embodiment Gaussian kernel SVR linear regression model (LRM) fitting result charts：
Fig. 7 is least square regression fitting result chart：
Fig. 8 is Ridge regression fit design sketch：
Fig. 9 is Lasso regression fit design sketch.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, detailed
Carefully describe.Described embodiment is only a part of the embodiment of the present invention.
The present invention solve above-mentioned technical problem technical solution be：
S11, the area for needing dispensing to share bicycle is pointed out for quantitative analysis, it is right according to the difference of regional land status
Classify in area.
Specifically, with reference to《The newly-built regional utility management system standard planning in Nanjing is guided》, according to land use function pair
Classify in Nanjing area.Here we are divided into 6 types, are school, scenic spot, commercial center railway station, house, work respectively
Industry garden.
It is required to be noted that shared bicycle is to provide bicycle bicycle shared service, solve urban transportation trip " most
Latter kilometer " problem, alleviation urban traffic blocking etc. have played positive effect, and meet low-carbon trip theory, meanwhile,
As important linking tool, shared bicycle is as flexibly easily mode of transportation can be very good to make up public transport accessibility not
The scope of application of high defect, the supplement public transport as end will greatly improve.
Further specifically, so according to 6 types of division, Nanjing different regions flow of the people thermodynamic chart is being referred to
Afterwards, the representative area of these types is picked out：In Xian Lin university cities, the Confucius Temple, Jiangning Wanda, Nanjing southern station, Hunan Road, the west of a river
Entreat business district, the postindustrial garden in day, the area of Xin Jie Kou eight.
S12, be established based on DEA model of fuzzy synthetic evaluation evaluation index, adjust Check obtain it is related to cycling trip
Major influence factors.
Specifically, true according to principle of whole, scientific principle, principle of objectivity, operability principle, principle of comparability
Evaluation index is determined, wherein having：
Index system refers to the organic set of target, not only wants the inner link of leading indicator system entirety.And it is noted that
Whole function and target, and form certain level.
Index system must scientifically image study object level, index Design title, meaning, content, space-time and
The necessary science of computer capacity, measurement unit and metering method etc. is clear, without ambiguity.
Index system as research foundation, it is necessary to it is objective, credible, by investigation, without consulting, only with
Index system is established in subjectivity conjecture, necessarily causes research to lack credible.
The design of index must have operability, it is necessary to consider the measurement of index value and the possibility of data collection effort
Property, meanwhile, the proportionate relationship that subjective index and objective indicator are matched when establishing index system is also required, as far as possible using existing
Capable statistical indicator.
Index should be comparable in different times or in spatial dimension.To make the index of foundation be comparable,
It realizes indices quantification, the evaluation criteria for establishing relative superior or inferior is also needed for non-quantitation index.
Further specifically, according to mentioned above principle, by inquiry and in conjunction with the classification situation in Nanjing area.It defines herein
Shared bicycle launches the evaluation index of comprehensive suitability degree, including：
Area (square kilometre) y11：The size of the area in selected area determines that any two points needs use in area
The probability that bicycle is ridden instead of walk.Usual region area is big, then more release position should be arranged, conversely, region area is too small, then release position
Setting be likely to unnecessary.
Population/flow of the people y12：The bicycle frequency of use of release position most directly depends on population or the stream of people with circulating rate
Amount, population/flow of the people of only unit area can reach a particular value, can guarantee the frequency of use of bicycle, then herein
It is meaningful to set release position.
Cost of land y21：Cost of land is the important component of shared bicycle release position construction investment expense, each
The benchmark land price in area is different, it is with regional Exploitation degree and function value etc. at related.
Bicycle maintenance cost y22：Bicycle maintenance cost be also shared bicycle release position construction major investment content it
One, it has certain correlation with benchmark land price.
Neighbouring subway station number y31：The supplement of shared bicycle positioned i.e. as public transport is plugged into, in setting release position
When, it should appropriate dispersion is laid, and bicycle user is facilitated to give back and change to other modes of transportation.The average daily stream of subway station
There are many logical person-time number, will provide huge radix for bicycle use.
Neighbouring bus station number y32：Densely distributed in busy areas bus routes, frequency of arriving at a station is high, and get off and get on the bus passenger
More, the demand to bicycle increases also with flow of the people and is increased.
Neighbouring house influences y41：Rapid, many residential quarters and public traffic station or large size are built in urban development at present
Shop distance farther out, needs bicycle to be supplemented as the tool of plugging into.
Neighbouring Office Area influences y42：Working distance is longer, is typically chosen public transport or car trip.Bicycle simultaneously
Also it is required, solves the problems, such as " last one kilometer ".
Neighbouring public construction influences y43：Influence of the periphery public construction to bicycle release position addressing is very big, especially people
Intensive shopping centre, amusement and travel area and other large-scale public places are flowed, it is big that bicycle leases turnover rate.
S13, index weights are determined.
Specifically, Judgement Matricies, compare phase two-by-two using expert graded to lower layer's element that identity element dominates
To importance.Generally use number 1-9 and its inverse carry out Judgement Matricies B=(b as scaleij)m×nFactor is carried out two
Two multilevel iudges obtain the comparison power of relative importance, establish judgment matrix.
Three-level Index Establishment judgment matrix：
Two-level index establishes judgment matrix：
Consistency check is carried out to matrix：CI=0, CR=0<1, judgment matrix can consider with uniformity, calculating power
Vector.Then we calculate the index of the assessment of efficiency of each DMU, and the fingers at different levels that will be finally calculated using DEA algorithms
Target weights statistics such as following table：
Table 5-1 index weight value tables at different levels
Specifically, structure subordinated-degree matrix (by taking Xian Lin university cities as an example), for whether suggesting setting up according to specific influence
There are five the opinion ratings of bicycle release position：
U=(V1 V2 V3 V4 V5)
Build Xian Lin university cities three-level index subordinated-degree matrix：
Subordinated-degree matrix is obtained by nondimensionalization obtains：
The three-level weight matrix obtained according to table 5-4 obtains two-level index subordinated-degree matrix：
Obtain weight vector to the end：
P=(0.301 0.263 0.200 0.145 0.091)
According to maximum membership grade principle, Xian Lin university cities share bicycle dispensing evaluation index and belong to V1Grade.
Specifically, determining each department score
Each grade scoring standards of table 5-2
According to table 5-5 standards of grading, Xian Lin university cities score is determined：
S14, according to actual conditions, appraisal result is divided into five grades by us, and eight areas of selection are calculated
Divide and classify according to standards of grading, such as table 5-6：
The regional standards of grading classification of table 5-3 eight
The foundation of S21, bicycle injected volume model.
Specifically, according to《Standard for classification of urban land and for planning of constructional land》The land used of the property divided, due to list
The volume of traffic in plane product is different, when predicting regional stream of people's travel amount, need to consider land use classes,
Plot ratio, soil intensity step on factor, establish using land area and property as independent variable, and stream of people's travel amount demand is the mould of dependent variable
Type, therefore regional bicycle injected volume model is established, including：
It should be noted that in formula：Pi：The shared bicycle output (/ hour) in regional i planning years；Sij：J in regional i
Class property land area (square metre)；αj：Jth class land character reference capacity rate；βj：Jth class land character Traffic area location adjusts
Coefficient；δj：Jth class land character cycling trip ratio；ω：Shared bicycle trip accounts for cycling trip ratio, wherein going on a journey
Relationship between number and cycling trip amount be 1 people/.
It should be noted that in formula：ZZL:Shared bicycle turnover rate；CI：Unit interval shares bicycle and lends number；SL：
Initial time bicycle quantity.
Further, by the turnover rate of shared bicycle and in the unit interval, bicycle is lent number, i.e. the peak hour produces
Amount, so that it may to obtain the shared bicycle number of initial time website, then：
It should be noted that in formula：wi：The shared bicycle injected volume of i-th of release position.
S22, the area further analysis for needing to launch shared bicycle is chosen, determines the shared bicycle injected volume in this area.
S23, it establishes to establish based on multiple objective programming and shares bicycle release position site selection model, determine the regional bicycle chosen
Release position.
Specifically, we are it needs to be determined that release position the maximal covering location model, is used as using cosine distribution function and is taken first
Two targets of service quality that business mass function combination overall society cost and facility provide, the public bicycles for establishing multiple target are thrown
Put a site selection model.
It should be noted that in formula：C:Release position construction cost (ten thousand yuan)；Q:Release position service quality；J：Release position
Set；cj：The fixed cost of j-th of release position；qij：Service quality of j-th of release position to demand point i；c0：Unit demand
Interior distance costs；dij：Distance of j-th of release position to demand point i；xj：Whether in j demand point is established；yij：Demand point i is by j
Service.
S24, the difference according to release position carry out quadratic programming, determine the supply volume of each release position.
Specifically, according to selected interior land use situation and shared bicycle demand really, the weight of release position, root are determined
Shared bicycle is redistributed according to the weight size of release position, sharing bicycle demand until each release position is optimal, therefore
It is as follows to define city's resident trip cost：
Mcost=(Pbus×Mbus+Ptaxi×Mtaxi+Pcar×Mcar+Pmotor×Mmotor)×N×DoverSFurther specifically,
According to the investigation that travel modal in all parts of the country is charged, everyone every kilometer Urban Transportation expense (unit is obtained：Member/people/
Kilometer), the factors such as comprehensive injected volume bring Multiobjective programming models into, and optimal value solution is carried out to it with Matlab.
Further specifically model is optimized, since each point injected volume is non-uniform, and otherness is excessive, in order to
This problem is avoided, we are based on release position and carry out constrained optimization with demand point distance, according to D1 in progressive coverage function
=100m, D2=200m we list with drag：
st.dij200 → d of ＞ij=0
It should be noted that in formula, Mj is the injected volume of each point.
S31, it selects bicycle " supply and demand matching " this index to share whether bicycle configures rationally as judgement, and determines it
Evaluation index grade.
Specifically, it is shared to realize, the utilization rate for sharing bicycle is improved, company's benefit is improved, needs to set up " supply and demand
With " appraisement system.According to the system of foundation, establish and share the daily different time sections of bicycle, quantity that different regions are launched and when
Between relationship.
Wherein, from the point of view of reasonability is optimal, the injected volume of shared bicycle should be consistent with actual demand amount.From utilization
From the point of view of rate highest, the bicycle quantity of dispensing should not be greater than demand.
Further specifically, according to above-mentioned 2 points, " supply and demand matching " refers to aerial when a certain determining, the demand of bicycle
The ratio of amount and supply amount is balance.Originally in a certain special time period that taxi demand and supply amount difference is absolute
The maximum value of value is defined as " supply and demand matching " evaluation index, but the bicycle quantity of different regions has the difference in magnitude.Cause
This introduces bicycle demand on the basis of original and the index of supply amount specifically uses demand and supply amount difference absolute
The maximum value of value and demand and supply amount and make ratio.And it is newly defined as " supply and demand matching " evaluation index.Index expression
Mode is as follows：
It should be noted that the time terminal that t1, t2 are required taxi " supply and demand matching " evaluating deg more connects when P values
It is bordering on 1, then illustrates that the matching degree of area's at the appointed time section is poorer.When P values illustrate closer to 0 this area's at the appointed time section
Matching degree is better, in conjunction with to regional injected volume, shares bicycle using the fuzzy synthesis based on DEA and launches addressing evaluation model,
Determine P metrics evaluation grades, such as table：
Table 5-4 " supply and demand matching " intensity grade table
S32, according to the evaluation index, collect the data of required regional correlative factor and processing.
The foundation of S33, Gauss SVR regression models linearly give expression to the relationship of different types of regional injected volume and time.
Specifically, equation first indicates the relationship of different areas injected volume and time：
F (x)=WTX+b
It should be noted that for so that model has high fitness and prevents over-fitting, we are added to f mono- soft
Every the point in soft margin does not consider its function loss.
Further, this equation is solved with hinge loss functions, is re-introduced into sparse variable and solves this problem：
Further specifically, being found by analysis, with linear equation it is difficult to give expression to the relationship of injected volume and time.According to
Real-life experience, it is understood that data may show preferably in higher dimensional space linear separability, as it is likely that there are one
A hyperplane separates low-dimensional data, for example, two dimension can not divided data have good linear separability property in three dimensions.
Further, gaussian kernel function is introduced, it is therefore an objective to want to present data being mapped to higher dimensional space, make it
It can linearly be expressed in higher dimensional space.
Wherein, it is as follows can to carry out Taylor expansion for a upper formula：
Original X can be projected in infinite dimensional space, under the mapping of gaussian kernel function then this when as a result,
Data must be linear separability, the data of gained are mapped back into the injected volume that original space is last again at this time.
Further specifically, being converted into a dual problem by introducing Lagrange multiplier.Introduce Lagrange
MultiplierLagrangian is obtained by method of Lagrange multipliers：
By derivation, we can solve this equation with KKT conditions are added：
Thus in the configuration for considering bicycle, utilization rate has obtained supply volume and time under the optimum organization of corporate income
Relationship.
S41, it establishes and personal credit appraisement system is established based on FICO, to manage user behavior.
Specifically, with reference to after ant credit and the appraisement system standard of FICO and the utility efficiency of shared bicycle report,
It establishes the personal credit appraisement system of shared bicycle company and makes following rule and formulated (full marks 900), according to current
Bicycle present situation makes appropriate rewards and punishments measure, specification user behavior.
Each metrics evaluation references of table 5-5
Table 5-6 personal credit opinion ratings are classified
S42, the scheduling repair center system address based on release position setting are set up, and shared bicycle is launched for recycling.
Specifically, situations such as needing the release position location distribution according to each region, allotment demand, setting area tune
With maintenance center, subregion allotment is realized, the allotment task execution in each region is by the same control of total allotment center, subdispatch repair
Center executes the entity of task.To preferably proceed from the situation as a whole, each areas case is coordinated.
Further specifically, according to the shared bicycle release position position and scale and demand acquiring method, build
Vertical Multiobjective programming models, to keep allotment center construction operation, transportation cost sheet minimum.Therefore we are with its mesh as an optimization
Mark, it is determined that be based on multiple objective programming control centre model：
Object function：
Constraints：
Wherein it should be noted that N：The set of release position；M：The set of home-delivery center's candidate point；qj：Release position j (j ∈
N allotment demand)；dij：Node i (i ∈ M ∪ N) arrives the distance of node j (j ∈ M ∪ N)；c1：Unit cost；Oi：It waits
Reconnaissance i (i ∈ M) builds fixed cost；Qi：Dispense supply amount；zi：0-1 variables；yij=1：It indicates to be responsible for visitor by candidate point i
The service of family point j, ziIndicate that candidate point i is selected.
Those of ordinary skill in the art may realize that moulds described in conjunction with the examples disclosed in the embodiments of the present disclosure
Block, unit and algorithm steps pointedly can implement management to shared bicycle.Simultaneously depending on technical solution specific application and
Design constraint, professional technician can realize described work(using distinct methods to each specific application
Can, but such implementation should not be considered as beyond the scope of the present invention.
The above embodiment is interpreted as being merely to illustrate the present invention rather than limit the scope of the invention.
After the content for having read the record of the present invention, technical staff can make various changes or modifications the present invention, these equivalent changes
Change and modification equally falls into the scope of the claims in the present invention.
Claims (10)
1. management and the decision-making technique of a kind of shared bicycle, which is characterized in that include the following steps：
1) it determines and launches ground, collect supplemental characteristic, establish the model of fuzzy synthetic evaluation based on DEA DEAs, pass through
Subordinated-degree matrix is built, maximum membership degree is calculated, shared bicycle dispensing evaluation index grade is obtained and needs to launch to pick out
The area of shared bicycle；
2) it establishes and shares bicycle release position site selection model, the release position in area is determined by multiple objective programming, according to different positions
Set the bicycle quantity that quadratic programming determination should launch；
3) Gaussian kernel SVR regression models are established, determine that shared bicycle is launched by the mapping of the gaussian kernel function of higher dimensional space
The functional relation of amount at any time；
4) it proposes quantity decision management method, personal credit appraisement system is established based on U.S.'s personal credit evaluation method, specification is used
Family vehicle reduces O＆M cost by multiple objective programming according to the optimal scheduling maintenance center of release position different set in region.
2. management and the decision-making technique of a kind of shared bicycle according to claim 1, which is characterized in that
The step 1) establishes the shared bicycle dispensing addressing evaluation model of the fuzzy synthesis based on DEA and specifically includes step：First
Is defined by shared bicycle and launches suitable evaluation index, then is passed through according to bicycle release position selecting index principle for geographic classification
DEA algorithms, obtain the index of the assessment of efficiency of k-th of DMU decision package, and formula is as follows：
1≤k≤s is the index of the assessment of efficiency of k-th of decision package, ur>=0, vi≥0
Wherein XjIt is inputted for m, k>0, st. indicates condition, Xj=(x1j,x2j,...,xmj),YjIt is exported for n, Yj=(Y1j,
Y2j,...,Ynj) and xij>0,yrj>0, the weight vector of input is v=(v1,v2,...,vm)T, u=(u1,u2,...un)T, vm tables
Show that m-th evaluation unit corresponds to input weight vector .un indicates that n-th of evaluation unit corresponds to output weight vector, and efficiency index refers to
Output uTYjWith input vTxjRatio.
3. management and the decision-making technique of a kind of shared bicycle according to claim 2, which is characterized in that
It further includes the steps that determining index weights that the step 1), which shares bicycle to launch evaluation index,：Judgement Matricies first,
Relative importance, Judgement Matricies B=are compared using expert graded two-by-two to lower layer's element that identity element dominates
(bij)m×n, by the way that factor is carried out multilevel iudge two-by-two, obtain the comparison power of relative importance, establish judgment matrix；
Consistency check is carried out to matrix：CI=0, CR=0<1, judgment matrix can consider with uniformity, calculating weight vector,
Then it utilizes DEA algorithms to calculate the index of the assessment of efficiency of each DMU, and the weights for the indexs at different levels being finally calculated is united
Meter.
4. management and the decision-making technique of a kind of shared bicycle according to claim 2, which is characterized in that
The structure subordinated-degree matrix, specifically includes step：
For whether suggesting setting up the opinion rating of bicycle release position according to specific influence, degree of membership is obtained by nondimensionalization
Matrix:Then two-level index subordinated-degree matrix is obtained according to three-level weight matrix：Obtain weight vector to the end：It is subordinate to according to maximum
Category degree principle obtains the shared bicycle in area and launches evaluation index level, finally determines each department score；Finally according to actual conditions
Appraisal result is divided into five grades, and multiple areas of selection are calculated into score and are classified according to standards of grading.
5. management and the decision-making technique of a kind of shared bicycle according to claim 2, which is characterized in that
The step 2) is established specifically includes step based on the shared bicycle release position site selection model of multiple objective programming foundation：
Initially set up regional bicycle injected volume model：
In formula：Pi：The shared bicycle output (/ hour) in regional i planning years：Sij:J classes property land area is (flat in regional i
Square rice)；αj:Jth class land character reference capacity rate；βj：Jth class land character Traffic area location regulation coefficient；δj：Jth class land used
Property cycling trip ratio；ω：Shared bicycle trip accounts for cycling trip ratio；
In formula：ZZL：Shared bicycle turnover rate；CI：Unit interval shares bicycle and lends number；SL：Initial time bicycle quantity；
In formula：wi:The shared bicycle injected volume of i-th of release position；
Finally, it establishes to establish based on multiple objective programming and shares bicycle release position site selection model, be used as and taken using cosine distribution function
Business mass function, while considering two targets of service quality that overall society cost and facility provide, thus establish the public affairs of multiple target
Bicycle release position site selection model altogether.
6. management and the decision-making technique of a kind of shared bicycle according to claim 5, which is characterized in that described to establish more mesh
Target public bicycles release position site selection model is specially：
In formula：C:Release position construction cost (ten thousand yuan)；cj：The fixed cost of j-th of release position；wi：I-th release position it is shared
Bicycle injected volume；D2：With a distance from pedestrian farthest tolerates from shared bicycle, D1：With a distance from pedestrian is tolerated recently from shared bicycle；Q:It launches
Point service quality；J：The set of dispensing；cjz：The fixed cost of j-th of release position；qij：Clothes of j-th of release position to demand point i
Business quality；c0：Distance costs in unit demand；dij：Distance of j-th of release position to demand point i；xj：Whether established in j
Demand point；yij：Demand point i is serviced by j.
7. management and the decision-making technique of a kind of shared bicycle according to claim 5, which is characterized in that
Further include the steps that being optimized to model：Constrained optimization is carried out using based on release position and demand point distance.
8. management and the decision-making technique of a kind of shared bicycle according to claim 1, which is characterized in that
The step 3) establishes Gaussian kernel SVR regression models and specifically includes step：
Support vector machines first indicates the relationship of different areas injected volume and time by equation：Letter is lost with hinge
Number solves this equation, is re-introduced into sparse variable and solves this problem：
Then gaussian kernel function is used, present data are mapped to higher dimensional space, it is enable linearly to be expressed in higher dimensional space,
Then Taylor expansion is carried out：The data of gained are mapped back into the injected volume that original space is last again；
Finally, it is converted into a dual problem by introducing Lagrange multiplier, relational model is solved, finally solution is different
Area, the relationship of bicycle injected volume and time.
9. management and the decision-making technique of a kind of shared bicycle according to claim 1, which is characterized in that
The step 4) establishes quantity decision management method and specifically includes step：
It is primarily based on FICO and establishes personal credit appraisement system；For management bicycle, sets up the scheduling set based on release position and repair
Centring system is managed, shared bicycle release position position and scale and demand is found out, establishes Multiobjective programming models, to make tune
With center construction operation, transportation cost sheet is minimum, therefore we are with the object function of the minimum target as an optimization of transportation cost, really
Determine to be based on multiple objective programming control centre model.
10. management and the decision-making technique of a kind of shared bicycle according to claim 9, which is characterized in that the optimization mesh
Target object function is：
Z：Transportation cost；N：The set of release position；M：The set of home-delivery center's candidate point；qj:The allotment of release position j (j ∈ N) needs
The amount of asking；dij:Node i (i ∈ M ∪ N) arrives the distance of node j (j ∈ M ∪ N)；c1：Unit cost；Oi：Candidate point i (i ∈ M)
Build fixed cost；Qi：Dispense supply amount；zi：0-1 variables；yij=1：Indicate the service for being responsible for client's point j by candidate point i, zi
Indicate that candidate point i is selected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810385708.1A CN108596727B (en) | 2018-04-26 | 2018-04-26 | Management and decision-making method for shared bicycle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810385708.1A CN108596727B (en) | 2018-04-26 | 2018-04-26 | Management and decision-making method for shared bicycle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108596727A true CN108596727A (en) | 2018-09-28 |
| CN108596727B CN108596727B (en) | 2022-05-03 |
Family
ID=63610175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810385708.1A Active CN108596727B (en) | 2018-04-26 | 2018-04-26 | Management and decision-making method for shared bicycle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596727B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191903A (en) * | 2018-11-07 | 2019-01-11 | 大连大学 | A kind of parking management method based on cloud |
| CN109191904A (en) * | 2018-11-07 | 2019-01-11 | 大连大学 | A kind of parking stall management platform based on personal credit appraisement system |
| CN109191905A (en) * | 2018-11-07 | 2019-01-11 | 大连大学 | Parking management method based on multiple objective programming |
| CN109409768A (en) * | 2018-11-12 | 2019-03-01 | 广东工业大学 | The method for early warning of transport truck |
| CN109410638A (en) * | 2018-11-07 | 2019-03-01 | 大连大学 | A kind of control method of parking space management system |
| CN109410637A (en) * | 2018-11-07 | 2019-03-01 | 大连大学 | A kind of parking space management system |
| CN109448426A (en) * | 2018-11-07 | 2019-03-08 | 大连大学 | A kind of control device for parking space management system |
| CN109472513A (en) * | 2018-11-23 | 2019-03-15 | 东南大学 | A method of determining that shared bicycle influences public bicycles usage amount |
| CN109492894A (en) * | 2018-10-31 | 2019-03-19 | 北京摩拜科技有限公司 | Monitor the method, apparatus and server that vehicle is launched |
| CN110046378A (en) * | 2019-02-28 | 2019-07-23 | 昆明理工大学 | A kind of integrated Gaussian process recurrence soft-measuring modeling method of the selective layering based on Evolutionary multiobjective optimization |
| CN110059986A (en) * | 2019-05-08 | 2019-07-26 | 武汉大学 | A kind of shared bicycle dynamic put-on method and system |
| CN110163660A (en) * | 2019-04-19 | 2019-08-23 | 深圳大学 | A kind of shared bicycle dispensing scale calculation method and system |
| CN110222893A (en) * | 2019-06-06 | 2019-09-10 | 武汉元光科技有限公司 | Dispensing location recommendation method, device and the electronic equipment of shared traffic resource |
| CN110288380A (en) * | 2019-05-29 | 2019-09-27 | 东南大学 | Lease bicycle based on traffic zone launches method for measuring and calculating |
| CN111191342A (en) * | 2019-12-05 | 2020-05-22 | 太原理工大学 | Vertical program control exercise bike human-machine engineering simulation and evaluation method based on CATIA |
| CN112184088A (en) * | 2020-11-12 | 2021-01-05 | 同济大学 | Urban ride quality evaluation method and system based on multi-source data |
| CN112330205A (en) * | 2020-11-25 | 2021-02-05 | 詹桂亭 | Shared bicycle release position analysis system based on big data |
| CN112734101A (en) * | 2021-01-04 | 2021-04-30 | 北京瀚文智远信息技术有限公司 | Sharing bicycle intelligent allocation method based on vehicle demand prediction |
| CN112766591A (en) * | 2021-01-27 | 2021-05-07 | 同济大学 | Shared bicycle scheduling method |
| CN112862176A (en) * | 2021-02-01 | 2021-05-28 | 上海元卓信息科技有限公司 | Public service facility site selection method and device |
| CN115018389A (en) * | 2022-08-05 | 2022-09-06 | 深圳壹家智能锁有限公司 | Management scheduling method, device, equipment and storage medium of self-service wheelchair |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060220450A1 (en) * | 2005-03-17 | 2006-10-05 | Nissin Kogyo Co., Ltd. | Vehicular brake control apparatus and control method therefor |
| JP2010055261A (en) * | 2008-08-27 | 2010-03-11 | Nec Corp | Reporting equipment, notification method, and program |
| CN101727627A (en) * | 2009-12-16 | 2010-06-09 | 工业和信息化部电子第五研究所 | Information system security risk assessment model based on combined evaluation method |
| CN103606266A (en) * | 2013-06-28 | 2014-02-26 | 长沙理工大学 | Road network traffic improvement scheme efficiency assessment method based on data envelopment analysis |
| CN105426997A (en) * | 2015-11-18 | 2016-03-23 | 西南交通大学 | Intelligent dispatching and application management system of urban public bicycles and implementation method thereof |
| CN105809270A (en) * | 2016-01-05 | 2016-07-27 | 淮海工学院 | Security investment combination evolution optimization method based on interval multi-target planning |
| CN106446538A (en) * | 2016-09-19 | 2017-02-22 | 中山大学 | Vehicle terminal point and travel time calculation method based on dynamic time wrapping |
| CN106875670A (en) * | 2017-03-07 | 2017-06-20 | 重庆邮电大学 | Taxi concocting method based on gps data under Spark platforms |
| CN107093104A (en) * | 2017-04-13 | 2017-08-25 | 成都步共享科技有限公司 | A kind of shared bicycle dispatching method participated in based on user |
| CN107292520A (en) * | 2017-06-26 | 2017-10-24 | 华北电力大学 | A kind of Wu electricity villages utilization of new energy resources Benefit Evaluation Method |
| CN107809469A (en) * | 2017-10-11 | 2018-03-16 | 北京摩拜科技有限公司 | Vehicle dispatching method, server, client and system |
| CN107832950A (en) * | 2017-11-09 | 2018-03-23 | 国家电网公司 | A kind of power distribution network investment effect evaluation method based on improvement Interval Fuzzy evaluation |
-
2018
- 2018-04-26 CN CN201810385708.1A patent/CN108596727B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060220450A1 (en) * | 2005-03-17 | 2006-10-05 | Nissin Kogyo Co., Ltd. | Vehicular brake control apparatus and control method therefor |
| JP2010055261A (en) * | 2008-08-27 | 2010-03-11 | Nec Corp | Reporting equipment, notification method, and program |
| CN101727627A (en) * | 2009-12-16 | 2010-06-09 | 工业和信息化部电子第五研究所 | Information system security risk assessment model based on combined evaluation method |
| CN103606266A (en) * | 2013-06-28 | 2014-02-26 | 长沙理工大学 | Road network traffic improvement scheme efficiency assessment method based on data envelopment analysis |
| CN105426997A (en) * | 2015-11-18 | 2016-03-23 | 西南交通大学 | Intelligent dispatching and application management system of urban public bicycles and implementation method thereof |
| CN105809270A (en) * | 2016-01-05 | 2016-07-27 | 淮海工学院 | Security investment combination evolution optimization method based on interval multi-target planning |
| CN106446538A (en) * | 2016-09-19 | 2017-02-22 | 中山大学 | Vehicle terminal point and travel time calculation method based on dynamic time wrapping |
| CN106875670A (en) * | 2017-03-07 | 2017-06-20 | 重庆邮电大学 | Taxi concocting method based on gps data under Spark platforms |
| CN107093104A (en) * | 2017-04-13 | 2017-08-25 | 成都步共享科技有限公司 | A kind of shared bicycle dispatching method participated in based on user |
| CN107292520A (en) * | 2017-06-26 | 2017-10-24 | 华北电力大学 | A kind of Wu electricity villages utilization of new energy resources Benefit Evaluation Method |
| CN107809469A (en) * | 2017-10-11 | 2018-03-16 | 北京摩拜科技有限公司 | Vehicle dispatching method, server, client and system |
| CN107832950A (en) * | 2017-11-09 | 2018-03-23 | 国家电网公司 | A kind of power distribution network investment effect evaluation method based on improvement Interval Fuzzy evaluation |
Non-Patent Citations (2)
| Title |
|---|
| A MAROUFMASHAT等: "《Multi-objective Optimization for Design and Operation of Distributed Energy Systems through the Multi-energy Hub Network Approach》", 《ACS》 * |
| 夏芸 等: "《共享单车需求评估及调度方案设计》", 《长安大学学报(社会科学版)》 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492894A (en) * | 2018-10-31 | 2019-03-19 | 北京摩拜科技有限公司 | Monitor the method, apparatus and server that vehicle is launched |
| CN109492894B (en) * | 2018-10-31 | 2022-01-07 | 汉海信息技术(上海)有限公司 | Method and device for monitoring vehicle delivery and server |
| CN109191905B (en) * | 2018-11-07 | 2020-09-22 | 大连大学 | Parking management method based on multi-target planning |
| CN109410637B (en) * | 2018-11-07 | 2020-09-22 | 大连大学 | Parking space management system |
| CN109410638A (en) * | 2018-11-07 | 2019-03-01 | 大连大学 | A kind of control method of parking space management system |
| CN109410638B (en) * | 2018-11-07 | 2020-09-22 | 大连大学 | Control method of parking space management system |
| CN109448426A (en) * | 2018-11-07 | 2019-03-08 | 大连大学 | A kind of control device for parking space management system |
| CN109191903A (en) * | 2018-11-07 | 2019-01-11 | 大连大学 | A kind of parking management method based on cloud |
| CN109191905A (en) * | 2018-11-07 | 2019-01-11 | 大连大学 | Parking management method based on multiple objective programming |
| CN109191904B (en) * | 2018-11-07 | 2020-09-22 | 大连大学 | Parking space management platform based on personal credit evaluation system |
| CN109410637A (en) * | 2018-11-07 | 2019-03-01 | 大连大学 | A kind of parking space management system |
| CN109448426B (en) * | 2018-11-07 | 2020-09-22 | 大连大学 | Control device for parking space management system |
| CN109191904A (en) * | 2018-11-07 | 2019-01-11 | 大连大学 | A kind of parking stall management platform based on personal credit appraisement system |
| CN109409768A (en) * | 2018-11-12 | 2019-03-01 | 广东工业大学 | The method for early warning of transport truck |
| CN109472513A (en) * | 2018-11-23 | 2019-03-15 | 东南大学 | A method of determining that shared bicycle influences public bicycles usage amount |
| CN110046378A (en) * | 2019-02-28 | 2019-07-23 | 昆明理工大学 | A kind of integrated Gaussian process recurrence soft-measuring modeling method of the selective layering based on Evolutionary multiobjective optimization |
| CN110046378B (en) * | 2019-02-28 | 2022-09-13 | 昆明理工大学 | Selective hierarchical integration Gaussian process regression soft measurement modeling method based on evolutionary multi-objective optimization |
| CN110163660A (en) * | 2019-04-19 | 2019-08-23 | 深圳大学 | A kind of shared bicycle dispensing scale calculation method and system |
| CN110163660B (en) * | 2019-04-19 | 2021-05-14 | 深圳大学 | Method and system for measuring and calculating release scale of shared bicycle |
| CN110059986A (en) * | 2019-05-08 | 2019-07-26 | 武汉大学 | A kind of shared bicycle dynamic put-on method and system |
| CN110288380A (en) * | 2019-05-29 | 2019-09-27 | 东南大学 | Lease bicycle based on traffic zone launches method for measuring and calculating |
| CN110288380B (en) * | 2019-05-29 | 2023-03-24 | 东南大学 | Method for measuring and calculating rental bicycle putting amount based on traffic subareas |
| CN110222893B (en) * | 2019-06-06 | 2021-11-16 | 武汉元光科技有限公司 | Method and device for recommending delivery places of shared traffic resources and electronic equipment |
| CN110222893A (en) * | 2019-06-06 | 2019-09-10 | 武汉元光科技有限公司 | Dispensing location recommendation method, device and the electronic equipment of shared traffic resource |
| CN111191342A (en) * | 2019-12-05 | 2020-05-22 | 太原理工大学 | Vertical program control exercise bike human-machine engineering simulation and evaluation method based on CATIA |
| CN112184088B (en) * | 2020-11-12 | 2022-05-17 | 同济大学 | Urban ride quality evaluation method and system based on multi-source data |
| CN112184088A (en) * | 2020-11-12 | 2021-01-05 | 同济大学 | Urban ride quality evaluation method and system based on multi-source data |
| CN112330205A (en) * | 2020-11-25 | 2021-02-05 | 詹桂亭 | Shared bicycle release position analysis system based on big data |
| CN112330205B (en) * | 2020-11-25 | 2021-09-21 | 乐清市辰卓电气有限公司 | Shared bicycle release position analysis system based on big data |
| CN112734101A (en) * | 2021-01-04 | 2021-04-30 | 北京瀚文智远信息技术有限公司 | Sharing bicycle intelligent allocation method based on vehicle demand prediction |
| CN112734101B (en) * | 2021-01-04 | 2022-06-03 | 北京瀚文智远信息技术有限公司 | Sharing bicycle intelligent allocation method based on vehicle demand prediction |
| CN112766591A (en) * | 2021-01-27 | 2021-05-07 | 同济大学 | Shared bicycle scheduling method |
| CN112862176A (en) * | 2021-02-01 | 2021-05-28 | 上海元卓信息科技有限公司 | Public service facility site selection method and device |
| CN115018389A (en) * | 2022-08-05 | 2022-09-06 | 深圳壹家智能锁有限公司 | Management scheduling method, device, equipment and storage medium of self-service wheelchair |
| CN115018389B (en) * | 2022-08-05 | 2022-10-25 | 深圳壹家智能锁有限公司 | Management scheduling method, device, equipment and storage medium of self-service wheelchair |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108596727B (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596727A (en) | A kind of management of shared bicycle and decision-making technique | |
| Pedro et al. | Integrating GIS spatial dimension into BREEAM communities sustainability assessment to support urban planning policies, Lisbon case study | |
| Lowry et al. | Determinants of urban tree canopy in residential neighborhoods: household characteristics, urban form, and the geophysical landscape | |
| Shang et al. | A unified framework for multicriteria evaluation of transportation projects | |
| CN110889562A (en) | Dynamic city model system based on scenario planning | |
| Yang et al. | Urban traffic congestion prediction using floating car trajectory data | |
| AlFanatseh | Land suitability analysis of urban development in the Aqaba area, Jordan, using a GIS-based analytic hierarchy process | |
| Setturu et al. | Modeling landscape dynamics of policy interventions in Karnataka State, India | |
| Bousonville et al. | Data driven analysis and forecasting of medium and heavy truck fuel consumption | |
| Dewangan et al. | Tourism recommendation using machine learning approach | |
| Hassan et al. | Modelling of urban growth and planning: A critical review | |
| Tripathy et al. | An innovative approach to assess sustainability of urban mobility—Using fuzzy MCDM method | |
| CN108764518A (en) | A kind of traffic resource dynamic optimization method based on Internet of Things big data | |
| Nodrat et al. | Prioritizing Road Maintenance Activities using GIS Platform and Vb. net | |
| Bayram et al. | An application of routing location and allocation model for drinking water distribution | |
| Wang et al. | P-DBL: a deep traffic flow prediction architecture based on trajectory data | |
| Thanh et al. | Application of combined SWOT and AHP analysis to assess the reality and select the priority factors for social and economic development (a case study for Soc Trang City) | |
| Bharath et al. | Land allocation model using cellular automata to understand housing demand and supply | |
| Wang et al. | A hybrid deep learning approach for traffic flow prediction in highway domain | |
| Li et al. | The application of fuzzy neural network in distribution center location | |
| Wei et al. | A Data-driven System for City-wide Energy Footprinting and Apportionment | |
| CN116108997B (en) | Method and system for predicting farmland land number and manufacturing cost of expressway in hilly area | |
| Sarajlić et al. | Selection of Environmentally Sustainable Means of Urban Mobility During Daily Population Migration in Order to Satisfy the Need for Transportation Using Methods of Multicriteria Analysis | |
| Han et al. | Mixed logit model based on nonlinear random utility functions: a transfer passenger demand prediction method on overnight D-trains | |
| Hansun et al. | Hybrid double exponential smoothing method for predicting foreign tourist arrivals to Bali |
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 |