CN111178948B - Method for realizing dynamic borrowing of shared automobile - Google Patents
Method for realizing dynamic borrowing of shared automobile Download PDFInfo
- Publication number
- CN111178948B CN111178948B CN201911312049.XA CN201911312049A CN111178948B CN 111178948 B CN111178948 B CN 111178948B CN 201911312049 A CN201911312049 A CN 201911312049A CN 111178948 B CN111178948 B CN 111178948B
- Authority
- CN
- China
- Prior art keywords
- data
- user
- borrowing
- demand
- automobile
- 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
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for realizing dynamic vehicle borrowing of a shared vehicle, which comprises the following steps: establishing a vehicle borrowing demand prediction model; establishing a borrowing time prediction model; acquiring contact data, website data and automobile data; obtaining whether the order can be created or not by using a discrimination algorithm; predicting a user demand confirmation result by using a vehicle borrowing demand prediction model; obtaining scheduling time through a scheduling algorithm; predicting the demand time by using a borrowing time prediction model; and judging whether the user demand is satisfied by combining the order creation result, the user demand confirmation result, the scheduling time and the demand time, thereby judging whether the automobile scheduling is performed. Compared with the prior art, the method fully considers the problem of unbalanced supply and demand of the network points, fully considers the characteristics and preferences of users, comprehensively solves the problem of dynamic vehicle borrowing of the shared vehicle in multiple angles, can obtain more accurate effects, has better feasibility and practicability, can meet and attract more users, and can improve the service quality of the system and generate larger profits.
Description
Technical Field
The invention relates to the field of shared automobile demand prediction and scheduling, in particular to a shared automobile dynamic borrowing realization method.
Background
On one hand, the development scale of the automobile sharing system is gradually enlarged, on the other hand, in order to provide better user experience, the one-way station automobile returning system which does not need to borrow and return automobiles from the same station is increasingly popular, and more automobile sharing systems have the phenomenon of unbalanced supply and demand of the station, such as: there are tidal phenomena between sites, unbalanced phenomena of individual sites, etc. In view of these problems, the characteristics and demands of the automobile sharing system are being mined, and the researches on the automobile sharing system are mainly divided into the following three aspects: system feature analysis, operation model strategy and demand prediction. The feature analysis comprises a vehicle sharing system site borrowing and returning feature analysis and a user behavior analysis; the operation model strategies comprise strategic planning, tactical guidance and execution optimization levels, such as strategic system planning and evaluation model methods, inventory allocation and scheduling research at the tactical level, and scheduling and user incentive strategies at the execution optimization level; demand predictions include long-term static demand and short-term dynamic demand predictions of the system. For automobile sharing, how to effectively realize operation optimization and meet user requirements is an important problem of improving service quality and controlling system cost, and the basis of operation optimization is to mine various characteristics of system stations and users and clear user requirements, so that dynamic short-time demand prediction for serving operation optimization is needed to be solved in order to meet matching of users and system vehicles to the greatest extent.
The existing research of the automobile sharing system is concentrated on research of macroscopic static long-term prediction, site layout, charging pricing and income conditions of the analysis system and the like, and the research of short-time site supply and demand rule feature mining for serving the site supply and demand unbalance condition is insufficient.
Besides establishing quantitative description research and rule mining of supply and demand characteristics of the sites in the presence of unbalanced supply and demand of the sites, preference analysis should be carried out on the user vehicle characteristics in the system through the user layer in order data instead of a simple class set meter, the internal rules of user behaviors are analyzed, and a statistical probability method is adopted to describe the borrowing and returning behaviors of the users, so that a research foundation is laid for further dynamic demand prediction.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method for realizing dynamic vehicle borrowing of a shared vehicle.
The aim of the invention can be achieved by the following technical scheme:
a method for realizing dynamic borrowing of a shared automobile comprises the following steps:
step S1: obtaining multi-source data, and establishing a logic-based vehicle borrowing demand prediction model;
step S2: establishing a borrowing time prediction model based on multiple linear regression based on the multiple source data;
step S3: acquiring contact data, website data and automobile data;
step S4: based on the contact data and the dot data, obtaining whether the order can be created or not by utilizing a discrimination algorithm;
step S5: based on the contact data and the website data, predicting a user demand confirmation result by using a vehicle borrowing demand prediction model;
step S6: obtaining scheduling time through a scheduling algorithm based on the contact data, the website data and the automobile data;
step S7: based on the contact data and the website data, predicting the demand time of the user by utilizing a borrowing time prediction model;
step S8: and judging whether the user demand is satisfied by combining the order creation result, the user demand confirmation result, the scheduling time and the demand time, if so, carrying out automobile scheduling to realize dynamic vehicle borrowing, and if not, ending.
The step S1 comprises the following steps:
step S11: obtaining user multi-source data;
step S12: screening the multi-source data through correlation analysis and a random forest algorithm;
step S13: and establishing a Logit-based vehicle borrowing demand prediction model by using the screening result.
The multi-source data includes user application log data, historical order data, site data, and user characteristic data.
The vehicle borrowing demand prediction model is as follows:
wherein P (Y) b =1) for confirming the probability of user demand generation, return shift is the number of return points, bourenum is the frequency of the most frequently borrowed points, touchinusfirst is the duration of user joining, touchNum is the total number of contacts of the user, orderTouchRatio is the proportion of valid orders generated after user history contacts, aveinerval is the average interval time of the history orders, distnearestimreshop is the distance between the contact position and the nearest moment difference order borrowing point, distneareshop is the distance between the contact position and the nearest point, distneareshop is the frequency of the history orders generated by the nearest point, distnearestorder is the minimumAnd the space is poor.
The time prediction model of the borrowing is as follows:
wherein Y is bt For how long a user contact passes will generate an order, distnearsttshop is the distance between the contact position and the nearest website, nearest derFre is the user history order proportion of the nearest website, avemule is the user history order mileage, distneaderFrenum is the minimum spatial difference, nearest derFrenum is the user history order number of the nearest website, borrowShopmum is the number of the vehicle website, boFre is the frequency of the most commonly borrowed website, boFrenum is the frequency of the most commonly borrowed website, freFre is the frequency of the most commonly returned website, ordernum is the history order number, nearest tshopF is the history order frequency of the nearest website, touctshopF is the history order frequency of whether an order is generated within 30 minutes before and after the contact, touchmin_touch is the time of user's joining, boFremer_touch is the average order number of times generated by the contact, and the average number of times of contact points generated by the user is the contact, and the nearest presswork is the average time difference of the contact points generated by the user.
The discrimination algorithm comprises the following steps:
whether the distance between the contact and the nearest net point is smaller than the walking range;
whether available automobiles exist at the network points in the walking range;
whether the endurance mileage of the available automobile is greater than the user acceptance.
The scheduling algorithm comprises the following steps:
judging whether the difference between the existing number of cars at the network point and the demand number of the borrowed cars is greater than or equal to the number of cars minus one, if so, calling out the cars is needed, and if not, calling out the cars is not needed;
judging whether the difference between the existing automobile number of the network points and the automobile borrowing demand number is less than or equal to one, if so, calling the automobile, and if not, calling the automobile;
and selecting the mesh point closest to the dispatcher from mesh points needing to call the automobile as a final call-in mesh point, selecting the mesh point closest to the final call-in mesh point from the mesh points needing to call the automobile as a final call-in mesh point, and obtaining the dispatching time through automobile data.
The contact data and the dot data are updated every 5 minutes.
Compared with the prior art, the invention has the following advantages:
(1) Predicting a user demand confirmation result by using a vehicle borrowing demand prediction model, obtaining a order creation result by using a discrimination algorithm, obtaining scheduling time by using a scheduling algorithm, predicting the demand time by using the vehicle borrowing demand prediction model, fully considering the problem of unbalanced supply and demand of network points, and realizing the scheduling of the vehicle by using the scheduling algorithm; the user characteristics and the preference are fully considered by the vehicle demand prediction model, so that a more accurate effect can be obtained; the method combines a discrimination algorithm, a vehicle-borrowing demand prediction model, a scheduling algorithm and a vehicle-borrowing time prediction model, solves the problem of dynamic vehicle-borrowing of the shared vehicle in an omnibearing and multi-angle manner, and has better feasibility and practicability.
(2) Short-time dynamic demand prediction can be provided for large-scale automobile sharing systems, so that the system is effectively assisted to formulate a passive or active operation optimization strategy to meet the demands of users, and the service quality of the system is improved.
(3) The contact data and the network point data are updated once every 5 minutes, so that the real-time performance is better, and the dynamic vehicle borrowing of the shared vehicle is better realized.
(4) And the profit is realized through prediction, more users can be satisfied and attracted, the service quality of the system can be improved, and larger profit can be generated.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of modeling of the time-of-day prediction model of the present invention;
FIG. 3 is a flowchart of a discrimination algorithm according to the present invention;
fig. 4 is a data structure diagram of the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. The present embodiment is implemented on the premise of the technical scheme of the present invention, and a detailed implementation manner and a specific operation process are given, but the protection scope of the present invention is not limited to the following examples.
Examples
The embodiment provides a method for realizing dynamic vehicle borrowing of a shared vehicle, which is shown in fig. 1 and comprises the following steps:
step S1: obtaining multi-source data, and establishing a logic-based vehicle borrowing demand prediction model;
step S2: establishing a borrowing time prediction model based on multiple linear regression based on the multiple source data;
step S3: acquiring contact data, website data and automobile data;
step S4: based on the contact data and the dot data, obtaining whether the order can be created or not by utilizing a discrimination algorithm;
step S5: based on the contact data and the website data, predicting a user demand confirmation result by using a vehicle borrowing demand prediction model;
step S6: obtaining scheduling time through a scheduling algorithm based on the contact data, the website data and the automobile data;
step S7: based on the contact data and the website data, predicting the demand time of the user by utilizing a borrowing time prediction model;
step S8: and judging whether the user demand is satisfied by combining the order creation result, the user demand confirmation result, the scheduling time and the demand time, if so, carrying out automobile scheduling to realize dynamic vehicle borrowing, and if not, ending.
Specifically:
the process for establishing the Logit-based vehicle borrowing demand prediction model comprises the following steps: obtaining user multi-source data; screening multi-source data through correlation analysis and random forest algorithm, and analyzing correlation among independent variables, independent variables and dependent variable Y through correlation analysis b Correlation between the two, selecting and dependent variable significantlyRelated independent variables, eliminating the independent variables with strong mutual correlation in order to avoid the problem of multiple collinearity in the subsequent model establishment; meanwhile, due to the requirement of actual engineering, the dependent variable Y is obtained by a random forest method b Importance of each argument; the correlation analysis and the random forest algorithm are combined, 11 independent variables are screened and reserved in the embodiment, and the correlation analysis and the random forest method are common methods; and establishing a Logit-based vehicle borrowing demand prediction model by using the screening result.
The multi-source data includes user application log data, historical order data, site data, and user characteristic data.
The contact data is obtained through an EAPP (electronic application submission system) log.
Once the EAPP log exists, a vehicle borrowing demand prediction model is triggered, and the vehicle borrowing demand prediction model is as follows:
the meanings of the variables are shown in Table 1.
The borrowing time prediction model is as follows:
the meanings of the variables are shown in Table 2.
The discrimination algorithm comprises: whether the distance between the contact and the nearest net point is smaller than the walking range; whether available automobiles exist at the network points in the walking range; whether the endurance mileage of the available automobile is greater than the user acceptance. Dividing the result of the discrimination algorithm into two types, namely that orders can be generated and orders can not be generated; for the inability to generate order classes, there are three possible scenarios: there is a vehicle but no need, there is no vehicle but no need.
The scheduling algorithm comprises the following steps: judging whether the difference between the existing number of cars at the network point and the demand number of the borrowed cars is greater than or equal to the number of cars minus one, if so, calling out the cars is needed, and if not, calling out the cars is not needed; judging whether the difference between the existing automobile number of the network points and the automobile borrowing demand number is less than or equal to one, if so, calling the automobile, and if not, calling the automobile; and selecting the mesh point closest to the dispatcher from mesh points needing to call the automobile as a final call-in mesh point, selecting the mesh point closest to the final call-in mesh point from the mesh points needing to call the automobile as a final call-in mesh point, and obtaining the dispatching time through automobile data.
TABLE 1 meaning of variables of the demand forecast model for borrowing
(symbol) | Variable name |
P(Y b =1) | Confirming probability of user demand generation |
returnShopnum | Number of vehicle returning net points |
BoFreNum | Frequency of most frequently borrowed net points |
BoFre | The frequency of the most frequently borrowed net point |
Touchminusfirst | Duration of user joining |
TouchNum | Total number of contacts of user |
OrderTouchRatio | Proportion of valid orders generated after user history contacts |
aveinterval | Historical order average interval time |
distnearesttimeshop | Contact position and nearest moment difference order borrowing network point distance |
distnearestshop | Distance between contact position and nearest net point |
nearestshopFreNum | Historical order frequency of recent website occurrences |
distnearestorder | Minimum space difference |
TABLE 2 meaning of various variables of prediction model at time of borrowing
(symbol) | Variable name |
Y bt | Demand time of user |
distnearestshop | Distance between contact position and nearest net point |
nearestorderFre | Minimum space difference vehicle-borrowing network point user history order proportion |
avemile | User history order mileage (average) |
distnearestorder | Minimum space difference |
nearestorderFreNum | Minimum space difference vehicle-borrowing network point user history order number |
borrowShopnum | Number of vehicle-borrowing net points |
BoFre | The frequency of the most frequently borrowed net point |
BoFreNum | Frequency of most frequently borrowed net points |
ReFre | Frequency of most frequently still dots |
ordernum | Historical order quantity |
nearestshopFreNum | Historical order frequency of recent website occurrences |
nearestshopFre | Historical order frequency of recent dot occurrences |
whether30 | Whether or not an order is generated within 30 minutes before and after the contact point |
Touchminusfirst | Duration of user joining |
Bointer_touchorder | Contact time and previous order borrowing time difference |
aveCliInterval | Average contact time for user generated valid order |
aveClickNum | Average number of contacts for user to generate valid order |
ClickTimes | Number of consecutive contacts by the user |
The specific working process of the shared automobile dynamic borrowing implementation method is as follows:
firstly, updating contact data, website data and automobile data once every 5 minutes, determining whether the contact data, the website data and the automobile data are user requirements by utilizing a vehicle borrowing requirement prediction model, and judging whether an order can be generated by utilizing a judging algorithm; filtering contact information with prediction probability larger than 0.8, and carrying out a scheduling algorithm under the condition that orders can be generated; the method comprises the steps of obtaining predicted demand time by utilizing a borrowing time prediction model, determining whether the demand can be met by comparing the scheduling time with the demand time, if so, scheduling vehicles from a final scheduling station to a final scheduling station, and if not, not scheduling and ending; the condition for judging whether the requirement is met may be: the demand time is more than or equal to 10 and the scheduling time is more than or equal to the demand time.
The three modes of shared automobile operation modes are analogized, namely, the automobiles are not scheduled, the prediction model is not used for scheduling, and the prediction model is used for scheduling. Without scheduling, a satisfaction rate of about 80% is achieved. If scheduling is performed without prediction, satisfaction and profits can be improved, but certain waste is caused, because redundant scheduling can increase labor cost and electricity charge and occupy the existing vehicles. When using the predictive schedule of the present embodiment, the satisfaction is improved by about 10%, corresponding to 243 potential orders per week between 10 sites. In addition, the waste rate is reduced to zero and the profit is increased by thirty thousand yuan compared with the non-scheduling mode, which is very significant. In addition, the improvement of the parking space saturation rate and the parking space vehicle-free rate shows that the service level can be improved on the basis of the original service level. Table 3 shows a comparison of the results of the three modes.
Table 3 comparison of the results for the three modes
Therefore, if the method for realizing dynamic vehicle borrowing of the shared vehicle in the embodiment is applied to practice, an active operation optimization strategy which can meet the requirements of users, improve the service quality of the system and generate larger profits can be formulated. These results indicate that in an automobile sharing system, it is very important to meet and attract more users by predicting the provision of a site network to realize a profit.
Claims (1)
1. The method for realizing the dynamic borrowing of the shared automobile is characterized by comprising the following steps:
step S1: obtaining multi-source data, and establishing a logic-based vehicle borrowing demand prediction model;
step S2: establishing a borrowing time prediction model based on multiple linear regression based on the multiple source data;
step S3: acquiring contact data, website data and automobile data;
step S4: based on the contact data and the dot data, obtaining whether the order can be created or not by utilizing a discrimination algorithm;
step S5: based on the contact data and the website data, predicting a user demand confirmation result by using a vehicle borrowing demand prediction model;
step S6: obtaining scheduling time through a scheduling algorithm based on the contact data, the website data and the automobile data;
step S7: based on the contact data and the website data, predicting the demand time of the user by utilizing a borrowing time prediction model;
step S8: judging whether the user demand is satisfied by combining the order creation result, the user demand confirmation result, the scheduling time and the demand time, if so, carrying out automobile scheduling to realize dynamic borrowing, and if not, ending;
the step S1 comprises the following steps:
step S11: obtaining user multi-source data;
step S12: screening the multi-source data through correlation analysis and a random forest algorithm;
step S13: establishing a logic-based vehicle borrowing demand prediction model by using the screening result;
the multi-source data comprises user application log data, historical order data, site data and user characteristic data;
the vehicle borrowing demand prediction model is as follows:
ln(P(Y b =1)/(1-P(Y b =1)))
=1.0448+0.2700returnShopnum+0.0480BoFreNum+2.5257BoFre+0.0415Touchminusfirst+0.0175TouchNum+17.5478OrderTouchRatio+0.1680aveinterval+0.0807nearestshopFreNum-0.01920distnearesttimeshop-3.1522distnearestshop-0.0603distnearestorder
wherein P (Y) b =1) probability generated for confirming user demand, return shift number is number of return vehicle dots, bourdon is frequency of most frequently borrowed dots, touchmapt is the time length of user joining, touchNum is the total number of contacts of the user, orderTouchRatio is the proportion of effective orders generated after the user makes a historical contact, aveinerval is the average interval time of the historical orders, distnearesttimesh is the distance between the contact position and the nearest moment of difference order borrowing net point, distnearestshop is the distance between the contact position and the nearest net point, nearest tshopfrenum is the frequency of the historical orders generated by the nearest net point, distnearestorder is the minimum space difference;
the time prediction model of the borrowing is as follows:
Y bt =11.32+0.0001avemile+0.0854borrowShopnum+0.0643Bointer_touchorder+0.6065nearesttimeFre+1.2250whetherFre+2.2640distnearestshop+0.0452distnearestorder+0.0163maxCliInterval+0.1425aveCliInterval-0.0388ordernum-0.0342BoFreNum-0.8537BoFre-0.4820ReFre-O.0068Touchminusfirst-5.8630OrderTouchRatio-0.6218whether30-0.0336nearestshopFreNum-0.6673nearestshopFre-0.6282nearestorderFre-0.1498aveClickNum-0.2020ClickTimes
wherein Y is bt For how long a user contact passes can generate an order, distnearsttshop is the distance between the contact position and the nearest website, nearest derFre is the user history order proportion of the nearest website, avemule is the user history order mileage, distneaderFrenum is the minimum spatial difference, nearest derFrenum is the user history order quantity of the nearest website, borrowShopmum is the number of the vehicle website, borre is the frequency of the nearest website, boFrenum is the number of the nearest website, refrestshopF is the history order frequency of the nearest website, nearest tshopF is the history order frequency of the nearest website, touch is the order generated within 30min before and after the contact, touch is the time length of user joining, bointer_touch is the average order time difference between the contact point and the nearest website, touch is the average time of the contact, and the average number of times of the contact points is generated by the user;
the discrimination algorithm comprises the following steps:
whether the distance between the contact and the nearest net point is smaller than the walking range;
whether available automobiles exist at the network points in the walking range;
whether the endurance mileage of the available automobile is greater than the user acceptance;
the scheduling algorithm comprises the following steps:
judging whether the difference between the existing number of cars at the network point and the demand number of the borrowed cars is greater than or equal to the number of cars minus one, if so, calling out the cars is needed, and if not, calling out the cars is not needed;
judging whether the difference between the existing automobile number of the network points and the automobile borrowing demand number is less than or equal to one, if so, calling the automobile, and if not, calling the automobile;
selecting the mesh point closest to the dispatcher from mesh points needing to call the automobile as a final call-in mesh point, selecting the mesh point closest to the final call-in mesh point from the mesh points needing to call the automobile as a final call-in mesh point, and obtaining the dispatching time through automobile data;
the contact data and the dot data are updated every 5 minutes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911312049.XA CN111178948B (en) | 2019-12-18 | 2019-12-18 | Method for realizing dynamic borrowing of shared automobile |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911312049.XA CN111178948B (en) | 2019-12-18 | 2019-12-18 | Method for realizing dynamic borrowing of shared automobile |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111178948A CN111178948A (en) | 2020-05-19 |
CN111178948B true CN111178948B (en) | 2023-08-04 |
Family
ID=70655559
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911312049.XA Active CN111178948B (en) | 2019-12-18 | 2019-12-18 | Method for realizing dynamic borrowing of shared automobile |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111178948B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113011790B (en) * | 2021-04-23 | 2024-06-21 | 上海汽车集团股份有限公司 | Shared automobile dispatching simulation method and device, electronic equipment and storage medium |
CN113807576B (en) * | 2021-08-30 | 2023-06-20 | 华南理工大学 | New energy automobile scheduling method based on multi-source data association |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105719019A (en) * | 2016-01-21 | 2016-06-29 | 华南理工大学 | Public bicycle peak time demand prediction method considering user reservation data |
CN109204586A (en) * | 2018-07-25 | 2019-01-15 | 智慧式控股有限公司 | The unmanned scooter of wisdom formula and shared system and business model |
CN109934649A (en) * | 2017-12-17 | 2019-06-25 | 北京嘀嘀无限科技发展有限公司 | A kind of motor bicycle car searching method, device and computer-readable medium |
-
2019
- 2019-12-18 CN CN201911312049.XA patent/CN111178948B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105719019A (en) * | 2016-01-21 | 2016-06-29 | 华南理工大学 | Public bicycle peak time demand prediction method considering user reservation data |
CN109934649A (en) * | 2017-12-17 | 2019-06-25 | 北京嘀嘀无限科技发展有限公司 | A kind of motor bicycle car searching method, device and computer-readable medium |
CN109204586A (en) * | 2018-07-25 | 2019-01-15 | 智慧式控股有限公司 | The unmanned scooter of wisdom formula and shared system and business model |
Non-Patent Citations (1)
Title |
---|
共享汽车用户及出行时空特征分析;陈小鸿;《同济大学学报(自然科学版)》;20180615;第796~803页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111178948A (en) | 2020-05-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Pevec et al. | A data‐driven statistical approach for extending electric vehicle charging infrastructure | |
US20210366287A1 (en) | System for providing big data-based artificial intelligence automatic allocation matching service using taxi demand prediction | |
Li et al. | Electric vehicle behavior modeling and applications in vehicle-grid integration: An overview | |
US20140119522A1 (en) | System and method for generating subscriber churn predictions | |
Daraghmi et al. | Negative binomial additive models for short-term traffic flow forecasting in urban areas | |
CN111178948B (en) | Method for realizing dynamic borrowing of shared automobile | |
Rong et al. | Mining efficient taxi operation strategies from large scale geo-location data | |
Zhang et al. | Mixed electric bus fleet scheduling problem with partial mixed-route and partial recharging | |
CN108966148A (en) | Prediction technique, server and the storage medium of trip information | |
Ferrero et al. | Car-sharing services–part a taxonomy and annotated review | |
Xiong et al. | An integrated and personalized traveler information and incentive scheme for energy efficient mobility systems | |
Wang et al. | Demand control model with combinatorial incentives and surcharges for one-way carsharing operation | |
CN111815095A (en) | Shared automobile scheduling method, electronic equipment and storage medium | |
CN109978241B (en) | Method and device for determining charging load of electric automobile | |
Mahmoodian et al. | Hybrid rebalancing with dynamic hubbing for free-floating bike sharing systems | |
Tran et al. | Adaptive passenger-finding recommendation system for taxi drivers with load balancing problem | |
Ning et al. | Robust and resilient equilibrium routing mechanism for traffic congestion mitigation built upon correlated equilibrium and distributed optimization | |
Büchel et al. | What do we know when? modeling predictability of transit operations | |
Nasiboglu | Dijkstra solution algorithm considering fuzzy accessibility degree for patch optimization problem | |
Wang et al. | A user-based adaptive joint relocation model combining electric car-sharing and bicycle-sharing | |
La Rocca et al. | Heuristics for electric taxi fleet management at Teo Taxi | |
Shen et al. | Vehicle scheduling based on variable trip times with expected on‐time performance | |
CN112232662A (en) | Service monitoring system and method | |
Yu et al. | Combining travel behavior in metro passenger flow prediction: A smart explainable Stacking-Catboost algorithm | |
Ruch et al. | The impact of fleet coordination on taxi operations |
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 |