CN109767291B - Shared parking method facing elastic parking incentive mechanism - Google Patents
Shared parking method facing elastic parking incentive mechanism Download PDFInfo
- Publication number
- CN109767291B CN109767291B CN201811558514.3A CN201811558514A CN109767291B CN 109767291 B CN109767291 B CN 109767291B CN 201811558514 A CN201811558514 A CN 201811558514A CN 109767291 B CN109767291 B CN 109767291B
- Authority
- CN
- China
- Prior art keywords
- parking
- bidding
- owner
- factor
- influence
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a shared parking method facing an elastic parking excitation mechanism, which comprises the following steps: obtaining individual activity travel behavior characteristics and modes from individual travel behavior tracks of the berth owner, and performing correlation analysis to obtain influence factors influencing the travel decision of the berth owner; constructing a Cox risk model by taking the parking bidding duration as an analysis variable and taking each influence factor as an independent variable; analyzing each influencing factor sub-variable through significance test and collinearity diagnosis and screening; analyzing the screened factors by using a sensitivity analysis method to obtain an influence rule of each factor on the evolution of the bidding behavior of the berth owner; and adjusting the value of the corresponding factor, improving the probability of the parking place owner participating in bidding, and sharing the parking place given by bidding to other vehicle owners with requirements. The method comprehensively considers the influence rule of each factor on the evolution of the shared parking bidding behavior, can effectively enhance the implementation effect of the elastic parking incentive mechanism, and improves the turnover rate of the parking.
Description
Technical Field
The invention belongs to the field of shared parking planning in traffic planning, and particularly relates to a shared parking method for an elastic parking incentive mechanism.
Background
The elastic parking incentive mechanism is a shared parking strategy for motivating car travelers to actively share parking berths through economic subsidies and selecting other green travel modes to finish commuting travel. The commuter driver who owns the parking lot transfers the commuting parking right in a certain period of time to a parking lot manager by proposing a bidding application, the manager chooses to accept or refuse bidding, and the commuter driver who successfully bids needs to choose other green and low-carbon travel modes (such as public transport, bicycles or walking) to complete commuting and obtain economic compensation. And the parking lot manager puts the parking weight into the parking demand market again to realize shared parking.
With the further growth of urban road vehicles, the elastic parking incentive mechanism is expected to alleviate the problem of difficult parking to a certain extent. However, in practical implementation, the effect is not ideal, the parking turnover rate is not high, mainly because the current implementation is mainly related to the excitation intensity, the excitation intensity is high, the enthusiasm of parking owners for participating in shared parking is high, the excitation intensity is low, the participation degree is low, in order to attract more drivers owning parking to actively participate in parking sharing, the excitation effect is better if more investment is made, but the excitation intensity is set to be too high, the operation cost is obviously increased, and the scheme is not the optimal scheme in terms of finally obtained comprehensive benefits. Although researchers also propose a method for calculating incentive benefit according to game theory, the method is limited to the research of the single dimension. Actually, the parking space sharing for the elastic parking incentive mechanism is a scheme related to multiple aspects, and from the viewpoint of parking space offering, whether a parking space owner chooses to drive or not may be influenced by multiple factors, such as distance, road conditions, time, weather and other objective conditions, and how to dig out the relationship among the factors and improve the relationship in a targeted manner so as to enhance the implementation effect of the elastic parking mechanism and improve the parking space turnover rate is still an unknown subject at present.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the defects of the prior art, the invention provides a shared parking method facing to an elastic parking excitation mechanism, which can effectively enhance the implementation effect of the elastic parking excitation mechanism and improve the turnover rate of parking positions.
The technical scheme is as follows: the invention discloses a shared parking method facing an elastic parking excitation mechanism, which comprises the following steps:
(1) obtaining an individual travel behavior track of a berth owner, obtaining individual activity travel behavior characteristics and patterns from the travel behavior track through a machine learning algorithm, and performing correlation analysis by taking each item of travel behavior characteristics and pattern as an observation variable to obtain influence factors influencing the travel decision of the berth owner;
(2) obtaining a bidding request of a parking owner, taking the parking bidding duration as an analysis variable and each influence factor obtained in the step 1 as an independent variable, constructing a Cox risk model, and fitting coefficients of each variable;
(3) analyzing each influencing factor sub-variable through significance test and collinearity diagnosis and screening;
(4) obtaining a Cox risk prediction model of parking bidding according to the coefficient fitting result of the model, and analyzing the screened influence factors by applying a sensitivity analysis method to obtain the influence rule of each factor on the evolution of the bidding behavior of the parking owner;
(5) based on the supply and demand conditions of the current berth number, the value of the corresponding factor is adjusted according to the influence rule of each factor on the evolution of the bidding behavior of the berth owner, the probability of participation of the berth owner in bidding is improved, and the berth given by bidding is shared to other owners with requirements.
Preferably, in the step 1, the correlation analysis is performed by using each item of travel behavior characteristics and the mode as observation variables, and obtaining influence factors influencing the travel decision of the berth owner includes:
carrying out correlation analysis on the behavior characteristics and the patterns of each individual activity trip by using the Pearson correlation coefficient in the SPSS Statistics 22.0, wherein the formula is as follows:
ρX,Yrepresenting the degree of linear correlation between the variables X and Y, cov (X, Y) being the covariance, σX·σYIs the standard deviation;
according to the calculation result, eliminating the variables with the coefficients lower than the specified standard value to obtain the influence factors of the activity trip decision of the berth owner, wherein the influence factors comprise the following six types: social and economic attributes, outside trip weather, position characteristics of the working and living areas, activity schedule arrangement, parking bid decision and trip mode decision.
Preferably, the step 2 constructs a Cox risk model as follows:
h(t,u)＝h0(t)eβu
wherein u ═ u (u)1,u2,...,un)TRepresenting various influencing factors; h is0(t) is the baseline risk function, β ═ β1,β2,...,βn)TIs a regression coefficient vector corresponding to each influence factor.
Preferably, in step 3, sub-variables with a significance test value greater than 0.1 are removed through significance test, then sub-variables with a variance expansion factor greater than 5 are removed in colinearity diagnosis, and factors with a variance expansion factor less than 5, including sex, number of households, number of electric vehicles, entropy of family positions, entropy of unit positions, commuting distance, bid amount, and total number of bids, are obtained through multiple screening and fitting and serve as parameters of the Cox risk model.
Preferably, the Cox risk prediction model for parking bid in step 4 is as follows:
wherein the content of the first and second substances,
μiis the variable screened in step 3.
Has the advantages that:
1. the invention takes the continuous action effect of the elastic parking incentive mechanism as an entry point, and ensures the sustainability of the implementation of the policy mechanism. In addition, the invention firstly proposes that the parking bidding behaviors of drivers are regarded as a group of state sequences carried in daily behaviors, and introduces a survival analysis theory to depict the life and death process of the parking bidding continuous behaviors. The parking bidding behavior has survival characteristics and survival factors influencing the bidding continuation exist, if the parking bid behavior is completed by the parking position owner in a certain working day, namely the parking bid of the individual can be considered to be in a 'survival state' theoretically, and if the parking position owner stops bidding in a certain working day, the behavior is considered to be in a 'death state', so that the survival theory can well explain the parking bid intention and the evolution situation of the behavior.
2. According to the invention, through constructing a driver bidding behavior evolution model based on the Cox risk ratio and applying a sensitivity analysis method to explore the influence mechanism of a plurality of key factors on the change of the continuous duration of the driver bidding behavior, a berth sharing method facing to an elastic parking incentive mechanism is further provided, and the multidimensional analysis and excavation method can fully master the elements of the elastic parking incentive mechanism and effectively improve the implementation effect.
Drawings
FIG. 1 is a flow chart of a shared parking method according to the present invention;
fig. 2 is a diagram illustrating a risk rate prediction result of duration of a parking bidding activity according to an embodiment of the present invention.
Detailed Description
In order to more clearly understand the technical solution of the present invention, the main technical concept of the present invention is first described.
Survival Analysis (survivval Analysis) is the statistical inference of one or more Survival states based on companion information provided by an individual or population. Where "survival data" refers to temporal data describing the occurrence of an event or state. From a time dimension, a shared parking space bid initiated by a commuter driver who owns a parking space (hereinafter referred to as a parking space owner) belongs to a "voluntary" behavior which changes along with a time sequence. Parking bids can be broadly considered as a "state" of decision preference carried by a parking owner in a daily activity trip, which may persist on a parking owner for a period of time during which the parking owner may also be persistently involved in parking bid decisions.
The parking bidding behavior is regarded as a continuous state with survival characteristics from the individual perspective, key factors influencing the bidding duration exist, a survival analysis theory method is further applied to explain the parking bidding willingness and the evolution situation of the behavior of a parking owner, the continuous action effect of an elastic parking excitation mechanism is used as an entry point, a Cox risk model based on the survival analysis theory is constructed, the individual bidding initiating behavior and the bidding duration are regarded as dependent variables, the influence mechanism of the key factors on the change of the duration of the bidding behavior of the parking owner is analyzed, the value of the influence factors is further adjusted to improve the probability of participation of the parking owner in bidding, the parking allowed by bidding is shared to other owners with needs, and the parking turnover rate is improved.
The technical scheme of the invention is explained in detail in the following with the accompanying drawings.
As described in the background, the resilient parking actuation mechanism mainly involves two bodies: the parking manager and the bid requester (namely the parking owner) work by the way that the parking manager initiates a bid request to the parking manager, and the parking manager accepts the bid or refuses the bid. The method process of the present invention is explained below in the perspective of a parking manager, but the working process of the parking space owner and the interaction process between them will also be apparent from the following detailed description taken in conjunction with the accompanying drawings. Referring to fig. 1, the shared parking method facing to the elastic parking incentive mechanism of the present invention comprises the following steps:
step 1, obtaining individual activity travel behavior characteristics and modes from individual travel behavior tracks of a berth owner, and carrying out correlation analysis to obtain influence factors influencing travel decision of the berth owner.
In particular, personal information such as gender, family size, residence time, number of vehicles owned by the family, etc. may be obtained by investigating the parking owner, or such information may be obtained from a relational database, for example, by crawling information from a website of a statistical department using a web crawler and analyzing key fields. Meanwhile, the daily travel behavior track of the berth owner can be acquired from a GPS module of an intelligent mobile terminal or vehicle-mounted navigation equipment of the berth owner, high-quality travel information is excavated by utilizing the inherent space-time structure of GPS track data and combining a machine learning algorithm, time position data recorded by an instrument is converted into recognizable semantic information, and individual activity travel behavior characteristics and modes are obtained and serve as candidate variable sets of influencing factors of travel decision.
In the correlation analysis, the Pearson correlation coefficient (Pearson correlation coefficient) in the SPSS Statistics 22.0 is applied in the embodiment to perform the correlation analysis on each observation variable (behavior feature and pattern of individual activity trip), and the formula is as follows:
the pearson correlation coefficient between two variables is defined as the quotient of the covariance and the standard deviation between the two variables, which describes the degree of the linear correlation between the two variables. The value of rho is between-1 and +1, if rho is more than 0, the two variables are positively correlated; if ρ < 0, it indicates that the two variables are negatively correlated. A larger absolute value of ρ indicates a stronger correlation, and if ρ is 0, it indicates that there is not a linear correlation between the two variables.
In the above acquired individual activity travel behavior characteristics and the variables of the mode, 0.25 is selected as a standard for judging whether the individual activity travel behavior characteristics and the mode are related, and influence factors of the activity travel decision of the berth owner are obtained while eliminating the variables of which the correlation coefficient is lower than the standard value, and are classified into the following six categories: social and economic attributes, outside trip weather, position characteristics of the working and living areas, activity schedule arrangement, parking bid decision and trip mode decision.
And 2, obtaining a bidding request of the parking owner, taking the parking bidding duration as an analysis variable and each influence factor as an independent variable, constructing a Cox risk model, and fitting coefficients of each variable.
From the bidding request message initiated by the berth owner, the time nodes of each behavior in the bidding application process can be obtained according to the timestamp of each event, and the duration of bidding is the time length from the initiation of the request to the cancellation of the request event.
The Cox risk model is a semi-parameter regression model, the survival time (namely, the parking bidding duration of a parking space owner) is not required to obey a certain distribution form when each parameter is estimated, in addition, the model can take the survival state result (namely, the bidding duration) and the survival time as dependent variables, and simultaneously perform regression fitting on a plurality of influence factors, and the risk function of the specific parking bidding duration t can be expressed as follows:
h(t,u)＝h0(t)eβu
wherein u ═ u (u)1,u2,...,un)TRepresenting various influencing factors; h is0(t) is the baseline risk function, β ═ β1,β2,...,βn)TThe regression coefficient vectors corresponding to the influence factors show that the Cox risk model is assumed to have the advantages of ensuring that the model baseline part is only related to the parking bidding duration t and is not related to the influence factors u, and the index part is only related to the influence factors u and is not related to the parking bidding duration t.
In the embodiment, a single-factor Cox regression analysis is performed on 841 parking bidding behavior samples of 23 berth owners, and the specific regression analysis results are shown in table 1, wherein the indexes in the table are all common indexes in the regression analysis.
TABLE 1 results of regression analysis of the one-factor Cox Risk model
And 3, analyzing each influencing factor sub-variable through significance test and collinearity diagnosis and screening.
According to the regression analysis result of the single-factor Cox risk model, because some variables are not enough or not significantly related to other variables, the variables are eliminated when the structural equation model is constructed, so that the significance of the result variables is firstly tested, namely, an assumption is made on the parameters of the variables in advance, then the sample information is utilized to judge whether the assumption is reasonable or not, and whether the total real situation is significantly different from the original assumption or not is judged. In addition, when the Cox risk model is fitted, the model parameter estimation is distorted or difficult to estimate accurately if a plurality of factors have significant multiple collinearity, so that the above indexes need to be subjected to collinearity diagnosis, variables meeting the requirements are screened and sorted, and the factors are incorporated into the Cox risk model parameter fitting.
Relevant variables are screened by a significance test value, the value of significance, i.e., probability, usually denoted by p, reflecting the magnitude of the likelihood of an event occurring. The statistical significance of the p-value obtained by the significance test method means the probability that the difference between samples is caused by sampling error, and is generally significant with p < 0.1. As can be seen from table 1, except for "activity schedule", each of the other categories has sub-variables with significance check value less than 0.1, i.e. these sub-variables can be considered to belong to significant variables, while sub-variables with significance check value greater than 0.1 are considered to be insignificant and must be culled. The results of the collinearity diagnosis of the above-described indices are shown in table 2.
TABLE 2 results of collinearity diagnosis
As can be seen from the first column of table 2, there is significant multiple collinearity between the four factors "highest degree fahrenheit", "lowest degree fahrenheit", "average degree fahrenheit" and "dew point" in the initial regression fitting scheme, resulting in a Variance Inflation Factor (VIF) value of greater than 5. In order to guarantee the effectiveness of parameter fitting, the model only incorporates the "dew point" term with the minimum variance expansion factor into the subsequent modeling process. Similarly, for the multiple collinearity characteristics among the three factors of the current bid accumulation, the bid success times and the total bid times, the model parameter fitting process only retains the total bid times. The second column in table 2 is to perform multiple collinearity tests on the factors after the primary screening again, and the results show that the screened factors all meet the collinearity test requirements (that is, VIF value is less than 5), so the factors are included in the Cox risk model parameter fitting, and as a result, as shown in table 3, 8 of 10 key factors all have different degrees of influence on the parking bidding behavior according to the significance test, wherein the degree of influence on the parking bidding behavior by the home-scale situation is the most significant, and the relative risk rate reaches 1.446.
TABLE 3 results of regression analysis of multifactor Cox Risk model
And 4, obtaining a Cox risk prediction model for parking bidding according to the coefficient fitting result of the model, and analyzing the screened factors by using a sensitivity analysis method to obtain an influence rule of each factor on the evolution of the bidding behavior of the parking position owner.
The expression of the Cox risk model for deducing parking bid of the parking owner through the fitting result is as follows:
in the formula, the subscript numbers of the fitting parameters and the influencing factors correspond to the numbers in Table 3, respectively, and h0The function value of (t) can be calculated according to the following formula:
in order to further analyze the influence evolution mechanism of key factors on the parking bidding duration of the parking owner, the formula is used as a prediction model in the embodiment, and if the parking owner is a single female driver, no other electric bicycles can be used as alternative vehicles in a family, and the commuting distance is 20 kilometers, sensitivity analysis can be carried out on the parking bidding behavior of the parking owner from the position entropy and economic incentive change through the Cox risk model formula.
FIG. 2(a) shows the result of the risk rate change of the duration of the parking bid for the group of motorists (i.e., motorists meeting the same occupation location condition) when the entropy of the home or unit location is initially set to 3 and when the entropy of the other party location is adjusted to change from 3 to 5. When the entropy of the home location changes from 3 to 5, the risk rate gradually decreases from 39.6% to 27.79%; while when the entropy of unit location changes from 3 to 5, the risk rate will gradually decrease from 39.6% to 30.29%. Therefore, it can be said that improving the infrastructure service level of the parking lot of the parking owner can effectively assist the implementation effect of the flexible parking incentive mechanism, and when the entropy of the parking lot can be improved by 2 points, the continuity of the parking lot owner participating in the parking bidding can be improved by about 10% to 15%. As can be seen from fig. 2(b), if the flexible parking incentive scheme bid amount is adjusted from 20 to 30 dollars, the risk of disruption in parking bidding activity by the parking owner is reduced from 39.6% to 16.25%. This is because the mental travel costs associated with selecting other vehicles can be more efficiently hedged if the parking owner can submit a higher bid amount during parking bidding, thereby continuously encouraging them to participate in parking space sharing. Fig. 2(c) is a corresponding relationship diagram of the total number of times of participation of the parking position owner in bidding and the persistence of the parking bidding behavior, and the expressed meaning is consistent with the actual results of investigation: that is, the more aggressiveness the parking owner is in participating in parking sharing, the more times the parking bid is engaged, and the lower the risk rate at which the parking bid activity is interrupted.
And 5, based on the supply and demand conditions of the current berth number, adjusting the value of the corresponding factor according to the influence rule of each factor on the evolution of the bidding behavior of the berth owner, improving the probability of participation of the berth owner in bidding, and sharing the berth given by bidding to other owners with requirements.
With the influence of various external factors, the usage right evaluation value of the parking space owner group to each parking space in different periods has difference, and the difference is finally reflected in the bid amount of the parking space owner group. After the policy maker or the manager acquires the individual travel behavior characteristics and modes of the parking owner, the evolution rule of each influence factor on the bidding behavior of the parking owner is analyzed according to the bidding application of the parking owner, and the service level of the infrastructure of the parking area of the parking owner with poor parking area conditions can be improved according to the calculation result; the most suitable elastic parking excitation strength can be found according to the calculation result. Finding the most appropriate influence factor adjusting value according to the influence rule not only ensures the enthusiasm of each driver for participating in parking sharing, but also reduces the influence caused by the operation cost of the elastic incentive mechanism, naturally attracts more parking owners to actively participate in parking sharing, and improves the parking turnover rate.
Although the embodiments of the present invention have been disclosed above, it should be further explained that the above embodiments are only used for illustrating the technical solutions of the present invention, and are not limited to the implementation methods of the present invention, for example, the specific variables obtained according to the travel tracks of different individuals of the berth owners may be different, but this does not affect the implementation process of the present invention. And one of ordinary skill in the art will understand that modifications and additions may still be made to the relevant rules or methods mentioned in the present disclosure; all such modifications and variations are intended to be included herein within the scope of this disclosure and the present invention and protected by the following claims.
Claims (5)
1. A shared parking method oriented to a flexible parking incentive mechanism, the method comprising the steps of:
(1) obtaining an individual travel behavior track of a berth owner, obtaining individual activity travel behavior characteristics from the travel behavior track through a machine learning algorithm, and performing correlation analysis by taking each item of travel behavior characteristics as an observation variable to obtain influence factors influencing the travel decision of the berth owner;
(2) obtaining a bidding request of a parking owner, taking the parking bidding duration as an analysis variable, taking each influence factor obtained in the step (1) as an independent variable, constructing a Cox risk model, and fitting coefficients of each variable;
(3) analyzing each influencing factor sub-variable through significance test and collinearity diagnosis and screening;
(4) obtaining a Cox risk prediction model of parking bidding according to the coefficient fitting result of the model, and analyzing the screened influence factors by applying a sensitivity analysis method to obtain the influence rule of each factor on the evolution of the bidding behavior of the parking owner;
(5) based on the supply and demand conditions of the current berth number, the value of the corresponding factor is adjusted according to the influence rule of each factor on the evolution of the bidding behavior of the berth owner, the probability of participation of the berth owner in bidding is improved, and the berth given by bidding is shared to other owners with requirements.
2. The shared parking method oriented to the flexible parking incentive mechanism of claim 1, wherein the step (1) of performing correlation analysis by using various trip behavior characteristics and patterns as observation variables to obtain influencing factors influencing the trip decision of the parking space owner comprises:
carrying out correlation analysis on the behavior characteristics and the patterns of each individual activity trip by using the Pearson correlation coefficient in the SPSS Statistics 22.0, wherein the formula is as follows:
ρX,Yrepresenting the degree of linear correlation between the variables X and Y, cov (X, Y) being the covariance, σX、σYRespectively, standard deviation;
according to the calculation result, eliminating the variables with the coefficients lower than the specified standard value to obtain the influence factors of the activity trip decision of the berth owner, wherein the influence factors comprise the following six types: social and economic attributes, outside trip weather, position characteristics of the working and living areas, activity schedule arrangement, parking bid decision and trip mode decision.
3. The shared parking method oriented to the flexible parking incentive mechanism of claim 1, wherein the step (2) constructs the Cox risk model as follows:
h(t,u)＝h0(t)eβu
wherein u ═ u (u)1,u2,...,un)TRepresenting various influencing factors; h is0(t) is the baseline risk function, β ═ β1,β2,...,βn)TIs a regression coefficient vector corresponding to each influence factor.
4. The shared parking method oriented to the elastic parking incentive mechanism according to claim 1, wherein in the step (3), the sub-variables with the significance check value larger than 0.1 are removed through the significance check, then the sub-variables with the variance expansion factor larger than 5 are removed in the collinearity diagnosis, and the factors with the variance expansion factor smaller than 5, including sex, number of family people, number of electric vehicles, entropy of family area, entropy of unit area, commuting distance, bid amount and total number of bids, are obtained through multiple screening and fitting as parameters of the Cox risk model.
5. The shared parking method oriented to the elastic parking incentive mechanism according to claim 4, wherein the Cox risk prediction model of parking bid in step (4) is as follows:
wherein the content of the first and second substances,
μiis the variable screened in the step (3).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811558514.3A CN109767291B (en) | 2018-12-19 | 2018-12-19 | Shared parking method facing elastic parking incentive mechanism |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811558514.3A CN109767291B (en) | 2018-12-19 | 2018-12-19 | Shared parking method facing elastic parking incentive mechanism |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109767291A CN109767291A (en) | 2019-05-17 |
| CN109767291B true CN109767291B (en) | 2020-08-25 |
Family
ID=66451405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811558514.3A Active CN109767291B (en) | 2018-12-19 | 2018-12-19 | Shared parking method facing elastic parking incentive mechanism |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767291B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855773A (en) * | 2012-09-13 | 2013-01-02 | 东南大学 | Short-term prediction method for occupancy of effective parking space of parking lot |
| CN107299129A (en) * | 2016-04-15 | 2017-10-27 | 昆山市工业技术研究院小核酸生物技术研究所有限责任公司 | Circle nucleic acid as breast cancer biomarker application |
| CN107341968A (en) * | 2017-07-26 | 2017-11-10 | 李丹 | One kind parking shared system |
| CN107958610A (en) * | 2017-11-21 | 2018-04-24 | 同济大学 | A kind of function area of mixed usage parking stall predictor method shared based on berth |
| CN108133613A (en) * | 2017-12-19 | 2018-06-08 | 深圳先进技术研究院 | A kind of real-time release road-surface concrete Service Index method and system |
| CN108346087A (en) * | 2018-02-08 | 2018-07-31 | 南京交通职业技术学院 | Dynamic based on location information shares parking service system |
| CN109003128A (en) * | 2018-07-07 | 2018-12-14 | 太原理工大学 | Based on improved random forest public bicycles website Demand Forecast method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050216384A1 (en) * | 2003-12-15 | 2005-09-29 | Daniel Partlow | System, method, and computer program for creating and valuing financial instruments linked to real estate indices |
-
2018
- 2018-12-19 CN CN201811558514.3A patent/CN109767291B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855773A (en) * | 2012-09-13 | 2013-01-02 | 东南大学 | Short-term prediction method for occupancy of effective parking space of parking lot |
| CN107299129A (en) * | 2016-04-15 | 2017-10-27 | 昆山市工业技术研究院小核酸生物技术研究所有限责任公司 | Circle nucleic acid as breast cancer biomarker application |
| CN107341968A (en) * | 2017-07-26 | 2017-11-10 | 李丹 | One kind parking shared system |
| CN107958610A (en) * | 2017-11-21 | 2018-04-24 | 同济大学 | A kind of function area of mixed usage parking stall predictor method shared based on berth |
| CN108133613A (en) * | 2017-12-19 | 2018-06-08 | 深圳先进技术研究院 | A kind of real-time release road-surface concrete Service Index method and system |
| CN108346087A (en) * | 2018-02-08 | 2018-07-31 | 南京交通职业技术学院 | Dynamic based on location information shares parking service system |
| CN109003128A (en) * | 2018-07-07 | 2018-12-14 | 太原理工大学 | Based on improved random forest public bicycles website Demand Forecast method |
Non-Patent Citations (3)
| Title |
|---|
| Survival analysis on the business types of small business using Cox"s proportional hazard regression model;Park等;《Journal of the Korean Data & Information Science Society》;20121231;第257-269页 * |
| 基于SPSS因子分析的肝细胞癌预后因素的Cox比例风险回归模型;李仕来等;《广西医学》;20150430;第439-444页 * |
| 基于泊位共享的区域停车场规划研究;刘松;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20130515;正文第1-6章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109767291A (en) | 2019-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lee et al. | Who is buying electric vehicles in California? Characterising early adopter heterogeneity and forecasting market diffusion | |
| Luan et al. | Better understanding the choice of travel mode by urban residents: New insights from the catchment areas of rail transit stations | |
| Xiao et al. | Evaluation of urban taxi-carpooling matching schemes based on entropy weight fuzzy matter-element | |
| Weiss et al. | A joint RP-off-SP survey to understand the impacts of autonomous vehicle on travel mode choices in the Greater Toronto Area | |
| Librino et al. | Home-work carpooling for social mixing | |
| Shmueli et al. | Neural network analysis of travel behaviour | |
| Bekka et al. | Impact of a ridesourcing service on car ownership and resulting effects on vehicle kilometers travelled in the Paris region | |
| Hamadneh et al. | Stakeholder viewpoints analysis of the autonomous vehicle industry by using multi-actors multi-criteria analysis | |
| Saiyad et al. | Exploring determinants of feeder mode choice behavior using Artificial Neural Network: Evidences from Delhi metro | |
| Shmueli | Applications of neural networks in transportation planning | |
| Fall | Analysis of social acceptability in the implementation of a congestion pricing area in Senegal | |
| CN109767291B (en) | Shared parking method facing elastic parking incentive mechanism | |
| Hamadneh et al. | Modeling travel behavior onboard of privately autonomous vehicle and shared autonomous vehicle | |
| Chen et al. | Household car and motorcycle ownership and transaction behavior through a life-course approach-A case in Taipei city | |
| Deng et al. | Campus relocation as a natural experiment to investigate the determinants of commuting satisfaction | |
| Rafiq et al. | A structural analysis of the work tour behavior of transit commuters | |
| Ong et al. | Utilizing a machine learning ensemble to evaluate the service quality and passenger satisfaction among public transportations | |
| CN113642841A (en) | Taxi service quality evaluation method | |
| Lim | Intra-household interactions in social-recreational activities and travel | |
| Nishida et al. | Modeling of a mode choice behavior toward agent-based mobility as a service simulation | |
| Khan et al. | Development of households’ vehicle choice models for travel accompanying arrangements | |
| de Dios Ortúzar et al. | Transport research needs | |
| Kopp | Success Factors for Future Growth of Car Sharing Services | |
| Shen et al. | Unveiling the influential factors for customized bus service reopening from naturalistic observations in Shanghai | |
| Anowar et al. | Joint Econometric Analysis of Temporal and Spatial Flexibility of Activities, Vehicle Type Choice, and Primary Driver Selection |
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 |