CN111178948A - Method for realizing sharing of dynamic automobile borrowing - Google Patents
Method for realizing sharing of dynamic automobile borrowing Download PDFInfo
- Publication number
- CN111178948A CN111178948A CN201911312049.XA CN201911312049A CN111178948A CN 111178948 A CN111178948 A CN 111178948A CN 201911312049 A CN201911312049 A CN 201911312049A CN 111178948 A CN111178948 A CN 111178948A
- Authority
- CN
- China
- Prior art keywords
- user
- borrowing
- data
- network
- 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.)
- Granted
Links
Images
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 sharing of dynamic automobile borrowing, which comprises the following steps: building a vehicle borrowing demand prediction model; establishing a borrowing time prediction model; obtaining contact data, network point data and automobile data; whether the order can be created or not is obtained 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 required time by utilizing a vehicle borrowing time prediction model; and judging whether the user requirements are met or not by combining the order establishing result, the user requirement confirming result, the scheduling time and the required time, thereby judging whether to carry out automobile scheduling or not. Compared with the prior art, the problem of unbalanced supply and demand of the network is fully considered, the user characteristics and the preference are fully considered, the problem of sharing the automobile dynamic borrowing is solved in an all-round and multi-angle manner, a more accurate effect can be obtained, better feasibility and practicability are achieved, more users can be met and attracted, the service quality of the system can be improved, and more profits can be generated.
Description
Technical Field
The invention relates to the field of shared automobile demand prediction and scheduling, in particular to a method for realizing dynamic automobile borrowing of a shared automobile.
Background
On one hand, the development scale of the automobile sharing system is gradually enlarged, on the other hand, for providing better user experience, the one-way station car returning system which does not need to borrow and return vehicles from the same station is increasingly popularized, and more automobile sharing systems have the phenomenon of unbalanced station supply and demand, such as: tidal phenomena exist between stations, single station borrowing and borrowing imbalances, and the like. In response to these problems, the features and requirements of the car sharing system are being explored, and the research on the car sharing system is mainly divided into the following three aspects: system characteristic analysis, operation model strategy and demand prediction. The characteristic analysis comprises the automobile sharing system site borrowing and returning characteristic analysis and the user behavior analysis; the operation model strategy comprises strategic planning, tactical guidance and execution optimization level, such as strategic system planning and evaluation model method, stock distribution and scheduling research of tactical level and scheduling and user incentive strategy of execution optimization level; demand forecasting includes system long-term static demand and short-term dynamic demand forecasting. 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 excavate various characteristics of system sites and users and clarify user requirements, so that dynamic short-time demand prediction serving operation optimization is urgently needed to be solved in order to meet matching of the users and system vehicles to the maximum extent.
The existing research of the automobile sharing system is mainly focused on the research of macroscopic static long-term prediction, the analysis of the site layout, the charging pricing, the income condition and the like of the system, and the research of mining the short-time site supply and demand rule characteristics for serving the site supply and demand imbalance condition is still insufficient.
Besides establishing quantitative description research and rule mining of the supply and demand characteristics of the site in the face of the current situation of unbalanced supply and demand of the site, preference analysis is carried out on the vehicle utilization characteristics of users in the system through a user level in order data, the internal rules of user behaviors are analyzed instead of a simple classification set, the borrowing and returning behaviors of the users are described by adopting a statistical probability method, and a research basis 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 the sharing of the dynamic automobile borrowing.
The purpose of the invention can be realized by the following technical scheme:
a method for realizing sharing of dynamic automobile borrowing comprises the following steps:
step S1: obtaining multi-source data, and establishing a borrowing demand prediction model based on the Logit;
step S2: establishing a borrowing time prediction model based on multi-source data and multi-linear regression;
step S3: obtaining contact data, network point data and automobile data;
step S4: whether the order can be created or not is obtained by using a discrimination algorithm based on the contact data and the network point data;
step S5: predicting a user demand confirmation result by using a vehicle borrowing demand prediction model based on the contact data and the network point data;
step S6: obtaining scheduling time through a scheduling algorithm based on the contact data, the network point data and the automobile data;
step S7: predicting the demand time of the user by utilizing a vehicle borrowing time prediction model based on the contact data and the network point data;
step S8: and judging whether the user requirements are met or not according to the establishment result of the order, the user requirement confirmation result, the scheduling time and the requirement time, if so, performing automobile scheduling to realize dynamic automobile borrowing, and if not, ending.
The step S1 includes:
step S11: obtaining user multi-source data;
step S12: screening multi-source data through correlation analysis and a random forest algorithm;
step S13: and establishing a borrowing demand prediction model based on the Logit by utilizing the screening result.
The multi-source data comprises user application log data, historical order data, site data and user characteristic data.
The borrowing demand prediction model comprises the following steps:
wherein, P (Y)b1) probability generated for confirming user requirements, return shop is the number of car returning network points, BoFreNum is the frequency of the most frequently borrowed network points, BoFre is the frequency of the most frequently borrowed network points, touchministart is the time length of user joining, TouchNum is the total number of user contacts, OrderTouchRatio is the proportion of valid orders generated after the user history contacts, aventerval is the average interval time of the history orders, distneresttiming is the distance between the contact position and the latest time difference order borrowing network point, distnerestshop is the distance between the contact position and the latest network point, nerestshop is the frequency of the latest orders generated by the latest network points, distnerestshop is the minimum space difference.
The borrowing time prediction model is as follows:
wherein, YbtOrder is generated for a user when contact points of the user occur for a long time, distnerestshop is the distance between the contact point position and the nearest network point, nearestorderFre is the user historical order proportion of the minimum spatial difference vehicle borrowing network point, aveme is the historical order mileage of the user, distnerestorder is the minimum spatial difference, nearestorderFrem is the user historical order number of the minimum spatial difference vehicle borrowing network point, borowShopnum is the number of the vehicle borrowing network points, boFre is the frequency of the most frequently borrowed network points, boFreum is the frequency of the most frequently borrowed network points, ReFre is the frequency of the most frequently returned network points, ordernum is the historical order number, nearshopkFreum is the historical order frequency of the nearest network points, nearshopsopop is the historical order frequency of the nearest network points, whhether 30 is whether the order is generated in 30min before and after the contact points of the user, Touchmins is the user's added, while the contact points of the average contact points of the user and the effective time of the user order, and the average of the contact points of the effective time of the user, and the average of the user order of the contact points of the user, wherein the average of the user order of the nearest network points are generated by the nearest network points, logickTimes is the number of consecutive contacts by the user.
The discrimination algorithm comprises the following steps:
whether the distance between the contact and the nearest lattice point is smaller than the walking range or not;
whether the network points in the walking range have available automobiles or not;
whether the endurance mileage of the available automobile is greater than the user acceptance level.
The scheduling algorithm comprises the following steps:
judging whether the difference between the current number of automobiles and the demand number of borrowing automobiles of the network points is more than or equal to the number of parking spaces minus one, if so, calling out the automobiles, and if not, calling out the automobiles is not needed;
judging whether the difference between the current number of automobiles and the demand number of borrowing automobiles of the network points is less than or equal to one, if so, calling the automobiles, and if not, not calling the automobiles;
and selecting the network point closest to the dispatcher from the network points needing to call the automobile as a final call-out network point, selecting the network point closest to the final call-out network point from the network points needing to call the automobile as a final call-in network point, and obtaining the dispatching time through the automobile data.
The contact data and the network data are updated every 5 minutes.
Compared with the prior art, the invention has the following advantages:
(1) the method comprises the steps of predicting a user demand confirmation result by using a vehicle borrowing demand prediction model, obtaining a result whether an order can be created or not by using a discrimination algorithm, obtaining scheduling time by using a scheduling algorithm, predicting the demand time by using a vehicle borrowing time 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 vehicle borrowing demand prediction model fully considers the characteristics and the preference of the user, and a more accurate effect can be obtained; the problem of sharing the dynamic automobile borrowing is solved in an all-round and multi-angle mode by combining a discrimination algorithm, an automobile borrowing demand prediction model, a scheduling algorithm and an automobile borrowing time prediction model, and the method has better feasibility and practicability.
(2) The method can provide short-time dynamic demand forecast for the automobile sharing system with a large scale, thereby effectively helping the system to make a passive or active operation optimization strategy, meeting the user demand and improving the service quality of the system.
(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 automobile dynamic borrowing sharing is better realized.
(4) By realizing profit through prediction, more users can be met 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 the modeling of the borrowing time prediction model according to the present invention;
FIG. 3 is a flow chart of a discrimination algorithm of the present invention;
fig. 4 is a data structure diagram of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Examples
The embodiment provides a method for realizing dynamic vehicle borrowing of a shared vehicle, as shown in fig. 1, comprising the following steps:
step S1: obtaining multi-source data, and establishing a borrowing demand prediction model based on the Logit;
step S2: establishing a borrowing time prediction model based on multi-source data and multi-linear regression;
step S3: obtaining contact data, network point data and automobile data;
step S4: whether the order can be created or not is obtained by using a discrimination algorithm based on the contact data and the network point data;
step S5: predicting a user demand confirmation result by using a vehicle borrowing demand prediction model based on the contact data and the network point data;
step S6: obtaining scheduling time through a scheduling algorithm based on the contact data, the network point data and the automobile data;
step S7: predicting the demand time of the user by utilizing a vehicle borrowing time prediction model based on the contact data and the network point data;
step S8: and judging whether the user requirements are met or not according to the establishment result of the order, the user requirement confirmation result, the scheduling time and the requirement time, if so, performing automobile scheduling to realize dynamic automobile borrowing, and if not, ending.
Specifically, the method comprises the following steps:
the process of establishing the borrowing demand prediction model based on the Logit comprises the following steps: obtaining user multi-source data; screening multi-source data through correlation analysis and a random forest algorithm, and analyzing the correlation among independent variables, the independent variables and dependent variables Y through the correlation analysisbThe correlation between independent variables is selected, independent variables which are obviously correlated with dependent variables are selected, and in order to avoid the problem of multiple collinearity in the subsequent model building, the removed parts are mutually strongly correlated independent variables; meanwhile, due to the requirement of actual engineering, a dependent variable Y is obtained by a random forest methodbThe importance of each independent variable; by combining correlation analysis and a random forest algorithm, 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 borrowing demand prediction model based on the Logit by utilizing the screening result.
The multi-source data includes user application log data, historical order data, site data, and user characteristic data.
The touch data is obtained by EAPP (electronic application submission system) logs.
Once the EAPP log exists, a vehicle borrowing demand prediction model is triggered, and the vehicle borrowing demand prediction model is as follows:
the meaning of each variable is shown in table 1.
The borrowing time prediction model is as follows:
the meaning of each variable is shown in table 2.
The discrimination algorithm comprises the following steps: whether the distance between the contact and the nearest lattice point is smaller than the walking range or not; whether the network points in the walking range have available automobiles or not; whether the endurance mileage of the available automobile is greater than the user acceptance level. Dividing the result of the discrimination algorithm into two types of orders which can be generated and orders which cannot be generated; for the failure to generate an order class, there are three possible cases: the vehicle is not required, and the vehicle is not required.
The scheduling algorithm comprises the following steps: judging whether the difference between the current number of automobiles and the demand number of borrowing automobiles of the network points is more than or equal to the number of parking spaces minus one, if so, calling out the automobiles, and if not, calling out the automobiles is not needed; judging whether the difference between the current number of automobiles and the demand number of borrowing automobiles of the network points is less than or equal to one, if so, calling the automobiles, and if not, not calling the automobiles; and selecting the network point closest to the dispatcher from the network points needing to call the automobile as a final call-out network point, selecting the network point closest to the final call-out network point from the network points needing to call the automobile as a final call-in network point, and obtaining the dispatching time through the automobile data.
TABLE 1 significance of variables of demand forecasting model for borrowing vehicles
| Symbol | Variable names |
| P(Yb＝1) | Confirming probability of user demand generation |
| returnShopnum | Number of car return points |
| BoFreNum | Frequency of most frequently borrowed points |
| BoFre | Frequency of most frequently borrowed dots |
| Touchminusfirst | Duration of user's joining |
| TouchNum | Total number of contacts of subscriber |
| OrderTouchRatio | Proportion of valid orders generated after user historical contact |
| aveinterval | Average interval time of historical orders |
| distnearesttimeshop | Distance between contact position and nearest time difference order borrowing network point |
| distnearestshop | Distance of contact position from nearest net point |
| nearestshopFreNum | Historical order frequency of recent network sites |
| distnearestorder | Minimum spatial difference |
TABLE 2 meaning of variables of the prediction model by time of day
| Symbol | Variable names |
| Ybt | User's demand time |
| distnearestshop | Distance of contact position from nearest net point |
| nearestorderFre | User historical order proportion of minimum spatial difference vehicle borrowing network |
| avemile | User historical order mileage (average) |
| distnearestorder | Minimum spatial difference |
| nearestorderFreNum | User historical order number of minimum spatial difference vehicle borrowing network |
| borrowShopnum | Number of borrowing network points |
| BoFre | Frequency of most frequently borrowed dots |
| BoFreNum | Frequency of most frequently borrowed points |
| ReFre | Frequency of most frequently still dots |
| ordernum | Historical order quantity |
| nearestshopFreNum | Historical order frequency of recent network sites |
| nearestshopFre | Historical order frequency of recent network site occurrences |
| whether30 | Whether an order is generated within 30min before and after the contact |
| Touchminusfirst | Duration of user's joining |
| Bointer_touchorder | Difference between contact time and previous order borrowing time |
| aveCliInterval | Average touch point time for a user to generate a valid order |
| aveClickNum | Average number of contacts for a user to generate a valid order |
| ClickTimes | Number of successive contacts of user |
The specific working process of the method for realizing the dynamic vehicle borrowing of the shared vehicle comprises the following steps:
firstly, updating contact data, network point data and automobile data every 5 minutes, confirming whether the contact data, the network point data and the automobile data are required by a user by using a borrowing demand prediction model, and judging whether an order can be generated by using a discrimination algorithm; filtering contact information with the prediction probability larger than 0.8, and performing a scheduling algorithm under the condition that an order can be generated; obtaining the predicted demand time by using a borrowing time prediction model, determining whether the demand can be met or not by comparing the scheduling time with the demand time, if so, scheduling the vehicle from the final dispatch station to the final dispatch station, and if not, scheduling and ending; the conditions for determining whether the demand is satisfied may be: the required time +10 is more than or equal to the scheduling time.
The method simulates the sharing automobile operation mode of three modes, namely, the automobile is 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. Scheduling without prediction can improve satisfaction and profit, but can cause certain waste because redundant scheduling not only increases labor cost and electricity charges, but also occupies the existing vehicle. When using the predictive scheduling of the present embodiment, the satisfaction is improved by about 10%, which corresponds to 243 potential orders per week between 10 sites. In addition, compared with a non-scheduling mode, the waste rate is reduced to zero, and the profit is increased by thirty-thousand yuan, which is very meaningful. In addition, the improvement of the parking space saturation rate and the parking space non-vehicle rate shows that the service level can be improved on the original basis. Table 3 compares the results of the three modes.
TABLE 3 comparison of results for three modes
Therefore, if the implementation method for sharing dynamic automobile borrowing is applied to practice, an active operation optimization strategy which can meet the user requirements, improve the system service quality and generate larger profits can be made. These results show that it is very important to satisfy and attract more users in the car sharing system to realize profitability by predicting the providing site network.
Claims (8)
1. A method for realizing sharing of dynamic automobile borrowing is characterized by comprising the following steps:
step S1: obtaining multi-source data, and establishing a borrowing demand prediction model based on the Logit;
step S2: establishing a borrowing time prediction model based on multi-source data and multi-linear regression;
step S3: obtaining contact data, network point data and automobile data;
step S4: whether the order can be created or not is obtained by using a discrimination algorithm based on the contact data and the network point data;
step S5: predicting a user demand confirmation result by using a vehicle borrowing demand prediction model based on the contact data and the network point data;
step S6: obtaining scheduling time through a scheduling algorithm based on the contact data, the network point data and the automobile data;
step S7: predicting the demand time of the user by utilizing a vehicle borrowing time prediction model based on the contact data and the network point data;
step S8: and judging whether the user requirements are met or not according to the establishment result of the order, the user requirement confirmation result, the scheduling time and the requirement time, if so, performing automobile scheduling to realize dynamic automobile borrowing, and if not, ending.
2. The method as claimed in claim 1, wherein the step S1 includes:
step S11: obtaining user multi-source data;
step S12: screening multi-source data through correlation analysis and a random forest algorithm;
step S13: and establishing a borrowing demand prediction model based on the Logit by utilizing the screening result.
3. The method as claimed in claim 1, wherein the multi-source data includes user application log data, historical order data, site data and user characteristic data.
4. The method for realizing the dynamic vehicle borrowing of the shared vehicle according to claim 1, wherein the model for forecasting the vehicle borrowing requirement is as follows:
ln(P(Yb＝1)/(1-P(Yb＝1)))
＝1.0448+0.2700returnShopnum+0.0480BoFreNum+2.5257BoFre+0.0415Tauchminusfirst+0.0175TouchNum+17.5478OrderTouchRatio+0.1680aveinterval+0.0807nearestshopFreNum-0.01920distnearesttimeshop-3.1522distnearestshop-0.0603distnearestorder
wherein, P (Y)b1) probability generated for confirming user requirements, return shop is the number of car returning network points, BoFreNum is the frequency of the most frequently borrowed network points, BoFre is the frequency of the most frequently borrowed network points, touchminisfirst is the time length of user joining, TouchNum is the total number of user contacts, OrderTouchRatio is the proportion of valid orders generated after historical contacts of the user, avennerval is the average interval time of the historical orders, distnerestartTimeshop is the distance between the contact position and the nearest time difference order borrowing network point, distnerestshop is the distance between the contact position and the nearest network point, nerestshop is the historical order frequency generated by the nearest network point, distnerestarder is the minimum space difference.
5. The method for realizing the dynamic borrowing of the shared automobile according to the claim 1, wherein the borrowing time prediction model is as follows:
Ybt＝11.32+0.0001avemile+0.0854borrowShopnum+0.0643Bointertouchor·der·+0.6065nearesttimeFre+1.2250whetherFre+2.2640distnearestshop+0.0452distnearestorder+0.0163maxCliInterval+0.1425aveCliInterval-0.0388ordernum-0.0342BoFreNum-0.8537BoFre-0.4820ReFre-0.0068Touchminusfirst-5.8630OrderTouchRatio-0.6218whether30-0.0336nearestshopFreNum-0.6673nearestshopFre-0.6282nearestorderFre-0.1498aveClickNum-0.2020ClickTimes
wherein, YbtOrder is generated for a user when contact points of the user occur for a long time, distnerestshop is the distance between the contact point position and the nearest network point, nearestorderFre is the user historical order proportion of the minimum spatial difference vehicle borrowing network point, aveme is the historical order mileage of the user, distnerestorder is the minimum spatial difference, nearestorderFrem is the user historical order number of the minimum spatial difference vehicle borrowing network point, borowShopnum is the number of the vehicle borrowing network points, boFre is the frequency of the most frequently borrowed network points, boFreum is the frequency of the most frequently borrowed network points, ReFre is the frequency of the most frequently returned network points, ordernum is the historical order number, nearshopkFreum is the historical order frequency of the nearest network points, nearshopsopop is the historical order frequency of the nearest network points, whhether 30 is whether the order is generated in 30min before and after the contact points of the user, Touchmins is the user's added, while the contact points of the average contact points of the user and the effective time of the user order, and the average of the contact points of the effective time of the user, and the average of the user order of the contact points of the user, wherein the average of the user order of the nearest network points are generated by the nearest network points, ClickTimes is the number of consecutive contacts by the user.
6. The method as claimed in claim 1, wherein the discrimination algorithm comprises:
whether the distance between the contact and the nearest lattice point is smaller than the walking range or not;
whether the network points in the walking range have available automobiles or not;
whether the endurance mileage of the available automobile is greater than the user acceptance level.
7. The method as claimed in claim 1, wherein the scheduling algorithm comprises:
judging whether the difference between the current number of automobiles and the demand number of borrowing automobiles of the network points is more than or equal to the number of parking spaces minus one, if so, calling out the automobiles, and if not, calling out the automobiles is not needed;
judging whether the difference between the current number of automobiles and the demand number of borrowing automobiles of the network points is less than or equal to one, if so, calling the automobiles, and if not, not calling the automobiles;
and selecting the network point closest to the dispatcher from the network points needing to call the automobile as a final call-out network point, selecting the network point closest to the final call-out network point from the network points needing to call the automobile as a final call-in network point, and obtaining the dispatching time through the automobile data.
8. The method as claimed in claim 1, wherein the contact data and the mesh point 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 true CN111178948A (en) | 2020-05-19 |
| CN111178948B 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) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011790A (en) * | 2021-04-23 | 2021-06-22 | 上海汽车集团股份有限公司 | Shared automobile scheduling simulation method and device, electronic equipment and storage medium |
| CN113807576A (en) * | 2021-08-30 | 2021-12-17 | 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 (6)
| Title |
|---|
| GUANGYU CAO: "Determination of the vehicle relocation triggering threshold in electric car-sharing system", 《CHINESE INTELLIGENT SYSTEMS CONFERENCE》 * |
| 何流等: "公共自行车动态调度系统需求预测模型研究", 《武汉理工大学学报(交通科学与工程版)》 * |
| 刘畅: "共享单车需求预测及调度研究", 《中国优秀硕士学位论文全文数据库经济与管理科学辑》 * |
| 王宁等: "电动汽车共享站点间车辆人工调度策略", 《同济大学学报(自然科学版)》 * |
| 金会平: "《网络生活》", 31 March 2019 * |
| 陈小鸿: "共享汽车用户及出行时空特征分析", 《同济大学学报(自然科学版)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011790A (en) * | 2021-04-23 | 2021-06-22 | 上海汽车集团股份有限公司 | Shared automobile scheduling simulation method and device, electronic equipment and storage medium |
| CN113807576A (en) * | 2021-08-30 | 2021-12-17 | 华南理工大学 | New energy automobile scheduling method based on multi-source data association |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111178948B (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pevec et al. | A data‐driven statistical approach for extending electric vehicle charging infrastructure | |
| Faridimehr et al. | A stochastic programming approach for electric vehicle charging network design | |
| Hua et al. | Joint infrastructure planning and fleet management for one-way electric car sharing under time-varying uncertain demand | |
| Bayram et al. | Electric power allocation in a network of fast charging stations | |
| Khoo et al. | Statistical modeling of Electric Vehicle electricity consumption in the Victorian EV Trial, Australia | |
| Li et al. | Electric vehicle behavior modeling and applications in vehicle-grid integration: An overview | |
| Alfian et al. | A simulation tool for prioritizing product-service system (PSS) models in a carsharing service | |
| CN111010426A (en) | Message pushing method and device | |
| CN108966148A (en) | Prediction technique, server and the storage medium of trip information | |
| Cocca et al. | Free floating electric car sharing: A data driven approach for system design | |
| Yao et al. | Service operations of electric vehicle carsharing systems from the perspectives of supply and demand: A literature review | |
| CN112700017B (en) | Property maintenance resource allocation method and device, computer equipment and storage medium | |
| CN112330341A (en) | Order allocation method and device, computer equipment and storage medium | |
| Cich et al. | Modeling demand responsive transport using SARL and MATSim | |
| Akter et al. | DaTask: A decomposition-based deadline-aware task assignment and workers’ path-planning in mobile crowd-sensing | |
| Shipman et al. | Learning capacity: predicting user decisions for vehicle-to-grid services | |
| Tolomei et al. | Benefits of relocation on e-scooter sharing-a data-informed approach | |
| CN111178948B (en) | Method for realizing dynamic borrowing of shared automobile | |
| Tran et al. | Adaptive passenger-finding recommendation system for taxi drivers with load balancing problem | |
| CN109618281A (en) | A kind of recognition methods of high-speed rail cell and device | |
| La Rocca et al. | Heuristics for electric taxi fleet management at Teo Taxi | |
| Maruthasalam et al. | Modelling driver's reactive strategies in e-hailing platforms: an agent-based simulation model and an approximate analytical model | |
| Moradipari et al. | Pricing differentiated services in an electric vehicle public charging station network | |
| Yang et al. | Configuration, deployment, and scheduling models for management and optimization of patrol services | |
| CN113409571B (en) | Judging method and device for setting bus lane, storage medium and terminal |
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 |