CN111598481A - Shared bicycle flow system, automatic scheduling system and method based on sub-area division - Google Patents

Abstract

The present disclosure proposes a shared bicycle flow system, an automatic dispatching system and method based on sub-area division, and the shared bicycle flow system includes an above-ground conveying device arranged at each bicycle pick-and-place point, and an underground conveying device connected to the above-ground conveying device at each bicycle pick-and-place point. The device, and the multi-layer storage device that can provide bicycles for the above-ground conveying device or the underground conveying device; the adjacent bicycle pick-and-place points and the above-ground storage device are connected by the above-ground conveying device or the underground conveying device, forming a mobile transportation network of shared bicycles. The proposed flow system realizes the linkage of stations in a certain area, predicts the demand of each station through a comprehensive demand forecast method, and then divides dynamic sub-areas to form a demand scheduling scheme for each station in the sub-area. Finally, the flow system is realized according to the scheduling scheme. The automatic transportation of shared bicycles provides users with efficient and convenient car access services to the greatest extent when they have needs.

Description

Shared bicycle flow system, automatic dispatching system and method based on sub-area division

technical field

The present disclosure relates to the technical field of shared bicycles, and in particular, to a shared bicycle flow system, and an automatic dispatching system and method based on sub-area division.

Background technique

The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

In recent years, the emergence of shared bicycles has improved the public transportation system, solved the "last mile" problem of citizens' travel, and conformed to the concept of green and environmental protection. However, with the rapid increase in the number of shared bicycles, a series of problems have arisen. In the streets and alleys of the city, the problem of random parking of bicycles has gradually become prominent. The phenomenon of "no way to go, nowhere to park" has attracted attention from all walks of life, and a series of measures such as standardizing parking spots and promoting electronic fences have been implemented. Although the parking problem has been regulated to a certain extent, it has relatively weakened the convenience and randomness of shared travel, and it is difficult to find a car and park, resulting in a poor user experience. Currently, all shared bicycle sites are scattered, which is not conducive to coordination. Control, it is very difficult to centralize management.

The inventors found that at present, in the field of shared bicycle transportation, there are mainly the following problems:

First, all need to rely on manpower to participate in transportation. Shared bicycles cover a wide area, so it will consume a lot of human resources, and there is a problem of untimely scheduling; although some inventions propose some shared bicycle carriers and some handling devices, but the carriers are in When automatic transportation is realized, there are great unsafe factors affected by the surrounding environment. Although there is a handling device, it still requires personnel to realize the transportation between the shared bicycle sites, which consumes a lot of manpower and has the problems of limited scheduling personnel and untimely scheduling, which cannot well meet the needs of users.

Second, the imbalance between the number of shared bicycles placed at various sites and the actual demand is relatively common, and it cannot well meet the needs of users. In the field of demand forecasting of shared bicycles, the existing technology mainly uses some algorithms of machine learning to analyze the historical data of shared travel to establish models for forecasting, without fully considering the actual needs of users. From the perspective of user needs, the demand forecasting can be improved to a certain extent. Accuracy, although the existing method takes into account the demand forecasting method for user reservations, it does not fully tap the real needs of users, and only relying on reservation data for forecasting lacks consideration of changing factors, making the forecasting results inaccurate; at the same time, the factors considered are not accurate. Comprehensive, without fully considering the changing factors of the surrounding environment of the site, ignoring the influence of the attraction points around the site on the change in demand.

Third, in the scheduling method of shared bicycles, it mainly considers the internal correlation between each station, and does not fully consider the inherent characteristics of each station itself and the influence of the surrounding environment characteristics, which cannot meet the effectiveness of scheduling, resulting in continuous ineffective scheduling work. , resulting in a lot of waste of resources.

SUMMARY OF THE INVENTION

In order to solve the above problems, the present disclosure proposes a shared bicycle flow system, an automatic scheduling system and method based on sub-area division, and the proposed flow system realizes the linkage of stations in a certain area, and predicts the demand of each station through a comprehensive demand forecasting method. Then, the dynamic sub-area is divided to form the demand scheduling scheme of each station in the sub-area. Finally, the mobile system realizes the automatic transportation of shared bicycles according to the scheduling scheme, and provides users with efficient and convenient car access services to the greatest extent when they have needs.

In order to achieve the above object, the present disclosure adopts the following technical solutions:

The first object of the present disclosure is to provide a shared bicycle flow system, including an above-ground conveying device arranged at each bicycle pick-and-place point, an underground conveying device connected to the above-ground conveying device at each bicycle pick-and-place point, and an above-ground conveying device or an underground conveying device. Provide a multi-layer storage device for bicycles; adjacent bicycle pick-and-place points and above-ground storage devices are connected by above-ground transportation devices or underground transportation devices to form a mobile transportation network for shared bicycles.

The second object of the present disclosure is to provide an automatic scheduling method based on sub-area division, including the following steps:

Obtain the bicycle pick-and-place data at the bike pick-and-place point, and predict the demand for each bike pick-and-place point based on the random forest algorithm that integrates user needs and the attractiveness of shared travel;

According to the forecast result of the demand, based on the tree branch combined with internal and external factors, the bicycle pick-and-place point is dynamically divided into sub-areas, and the scheduling plan is generated according to the division result;

The control of scheduling is performed according to the scheduling scheme.

The third object of the present disclosure is to provide an automatic dispatching system based on sub-area division, including the above-mentioned shared bicycle flow system, and a control platform for sending dispatch instructions to the shared bicycle flow system; the control platform includes a shared bicycle demand prediction system and a dynamic sub-area Division scheduling system;

The shared bicycle demand forecasting system is configured to execute the shared bicycle demand forecasting method in the above-mentioned automatic scheduling method based on sub-area division;

Alternatively, the dynamic sub-area division scheduling system is configured to perform the dynamic sub-area division scheduling method in the above-mentioned automatic sub-area division-based scheduling method.

Compared with the prior art, the beneficial effects of the present disclosure are:

(1) The shared bicycle flow system of the present disclosure combines the use of above-ground and underground space to form a vehicle transportation network in conditional areas such as non-isolation of machines and non-isolation of people, basically covering all the places where shared bicycles are required in a certain area, and as needed Transport the vehicles on the storage device or the transport track to each bicycle pick-up and drop-off point. The bicycle pick-up and drop-off point does not need to store a large number of bicycles for a long time. There are multiple continuous bicycle pick-and-place points, users can easily and quickly access the bicycle in the area along the line; at the same time, the storage device is set to a multi-layer structure, which can reduce the footprint of bicycle storage. Breaking through the limitations of the original human participation in dispatching and transportation, it can avoid problems such as limited dispatchers and untimely dispatching; it can effectively regulate users' parking behavior, avoid the problem of random parking, and at the same time dispatch vehicles efficiently, which can alleviate the problem of difficulty in using vehicles and parking. .

(2) The shared bicycle demand forecasting method of the present disclosure, based on the random forest algorithm, integrates user needs and shared travel attractiveness, can accurately obtain user needs, improve the accuracy of scheduling, reduce or avoid the execution of invalid scheduling, reduce the number of scheduling, and improve the System scheduling execution efficiency.

(3) The dynamic sub-area division and scheduling method of the present disclosure performs dynamic sub-area division and scheduling based on the principle of tree-like branching by synthesizing internal and external factors, combined with the second aspect of the present disclosure based on the random forest algorithm to fuse user needs and shared bicycle demand for shared travel attractiveness The prediction method supplements and optimizes the shared bicycle flow system based on non-isolation of people or non-isolation of machines described in the first aspect of the present disclosure, and can form a demand scheduling scheme in each sub-region to meet the user's scheduling needs to the greatest extent.

Description of drawings

The accompanying drawings, which constitute a part of the present disclosure, are used to provide further understanding of the present disclosure, and the exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure, but not to limit the present disclosure.

1 is a schematic structural diagram of a flow system according to Embodiment 1 of the present disclosure;

2 is a schematic structural diagram of a storage device according to Embodiment 1 of the present disclosure;

3 is a schematic structural diagram of each storage layer in the storage device according to Embodiment 1 of the present disclosure;

FIG. 4 is a schematic diagram of the arrangement position of the flow system device in the flow system according to Embodiment 1 of the present disclosure;

5 is a schematic structural diagram of the above-ground conveying device according to Embodiment 1 of the present disclosure;

6 is a schematic structural diagram of an underground conveying device according to Embodiment 1 of the present disclosure;

7 is a schematic structural diagram of a bicycle carrying device according to Embodiment 1 of the present disclosure;

8 is a schematic structural diagram of an intelligent induction electronic lock in the bicycle carrier according to Embodiment 1 of the present disclosure;

9 is a block diagram of an automatic scheduling system based on sub-region division according to Embodiment 2 of the present disclosure;

10 is a flowchart of a method for predicting demand for shared bicycles according to Embodiment 3 of the present disclosure;

11 is a flowchart of a dynamic sub-area division scheduling method according to Embodiment 4 of the present disclosure;

12 is a control method for execution scheduling according to Embodiment 5 of the present disclosure;

Among them: 1. Guardrail, 2. Ground transportation track, 3. Position sensor, 4. Automatic retractable door, 5. Door opening button, 6. Pick-up button, 7. Parking button, 8. Bicycle carrier, 9. Induction Smart Lock, 10, Reed Switch, 11, Magnet, 12, Drive Motor, 13, Positioning Device, 14, Electronic Lock Fixing Base, 15, Solar Panel, 16, Induction Device, 17, Storage Device, 18, Bicycle Entrance, 19, Bicycle exit, 20, First storage level, 21, Second storage level, 22, Third storage level, 23, Spiral ascending track, 24, Entry and exit track, 25, Vehicle storage area, 26, Underground conveyance Device, 27, Underground transportation track, 28, Fixed platform, 29, Telescopic drive power unit, 30, Pressure telescopic device, 31, Bicycle bearing part, 32, Pressure sensor, 33, Machine non-isolated green belt, 34, Road, 35 , control module, 36, column, 37, device for fixing bicycles in the vehicle storage area, 38, telescopic device, 39, main controller.

Detailed ways:

The present disclosure will be further described below with reference to the accompanying drawings and embodiments.

It should be noted that the following detailed description is exemplary and intended to provide further explanation of the present disclosure. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

It should be noted that the terminology used herein is for the purpose of describing specific embodiments only, and is not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural as well, furthermore, it is to be understood that when the terms "comprising" and/or "including" are used in this specification, it indicates that There are features, steps, operations, devices, components and/or combinations thereof. It should be noted that the various embodiments in the present disclosure and the features of the embodiments may be combined with each other without conflict. The embodiments will be described in detail below with reference to the accompanying drawings.

Example 1

In the technical solutions disclosed in one or more embodiments, as shown in FIGS. 1-8 , the shared bicycle flow system includes an above-ground conveying device arranged at each bicycle pick-and-place point, and a ground conveying device connected to each bicycle pick-and-place point Underground conveying devices, and multi-layer storage devices 17 capable of providing bicycles for above-ground conveying devices or underground conveying devices; adjacent bicycle pick-up and drop-off points and above-ground storage devices 17 are connected by above-ground conveying devices or underground conveying devices to form the flow of shared bicycles Shipping network.

The storage device 17 is used for storing bicycles, and the above-ground conveying device and the underground conveying device are used for conveying the bicycles to various bicycle pick-up and drop-off points according to the needs of the bicycles.

In this embodiment, the above-ground and underground spaces are combined to form a vehicle transport network, and the storage device 17 or the vehicles in the transport track are transported to each bicycle pick-up and drop-off point as needed. The area can meet the area requirements of the bicycle pick-up and drop-off point. Setting the storage device 17 as a multi-layer structure can reduce the floor space for bicycle storage, and at the same time, the above-ground storage device 17 is used for unified storage. Put down a certain number of bikes.

As shown in Fig. 4, taking a conventional intersection as an example, the above-ground conveying device is arranged at the non-isolated green belt 33, and the underground conveying device can be arranged below the road 34. At the same time, the above-ground conveying device and the underground conveying device can effectively avoid this problem. The impact of flow systems on road traffic.

Optionally, the storage device 17 is used for storing bicycles, and can be arranged underground or on the ground. Preferably, the storage device is arranged on the ground, which can effectively reduce the construction cost.

Optionally, the location of the storage device 17 can be set as required, the storage device 17 can be arranged near a bicycle access point with a large number of vehicles, and one or more bicycle access points share a ground storage device 17 . Specifically, it can be set in a suitable area near the non-isolation of aircraft or people, such as green belts on both sides of the road.

As shown in FIG. 1 , it is a schematic structural diagram of the above-ground conveying device connected to the storage device 17 , and FIG. 5 is a structural schematic diagram of a separate above-ground conveying device.

The storage device 17 can be a structure as shown in FIG. 1 and FIG. 2 , including a device casing that constitutes a bicycle accommodating space, a plurality of storage layers in the casing, and a transport track capable of moving and transporting the bicycle between the storage layers. , the transport track is respectively provided with the transport track in each storage layer to the entrance and the outlet of the storage layer.

In this embodiment, three layers may be set as an example, and a first storage layer 20 , a second storage layer 21 , and a third storage layer 22 are set.

It can be understood that the lowest storage layer is provided with a bicycle entrance 18 and a bicycle outlet 19, which are respectively connected to the above-ground conveying device or the underground conveying device for moving the bicycles to the storage device 17, or transporting the bicycles of the storage device 17 to each bicycle pickup. Put some.

In some embodiments, the specific structure of the transport track may be: a spiral-type ascending rotating track structure, including a column 36 disposed in the housing and a spiral-type ascending track 23 fixed on the column.

Optionally, as shown in FIG. 3 , each storage layer includes an access rail 24 connected to the spirally ascending rail 23 , and a vehicle storage area 25 connected to the access rail 24 through a rail.

In order to increase the storage area of vehicles in the storage area, place as many bicycles as possible. The vehicle storage area 25 is set as a slope with a certain radian and angle, and a bicycle fixing device 37 is arranged on the slope; optionally, the bicycle fixing device 37 can be set as Clamping device, set up two clamping blocks, and control the movement of the clamping blocks by pneumatic or electric device.

In order to realize the transportation of bicycles between the above-ground conveying device, the underground conveying device and the storage device 17, a fixed device for placing the bicycle can be installed in each device. It may be a bicycle carrier 8 that is free to move relative to each device.

As an achievable structure, all bicycle pick-and-place points are also provided with a control module 35. As shown in Figures 7 and 8, the bicycle carrying device 8 includes a bottom plate, a drive device disposed on the bottom plate for driving the bottom plate to move, and a bicycle fixing device , the bicycle information identification device, the main controller 39 and the wireless communication module, the main controller 39 is respectively connected with the driving device, the bicycle fixing device, the bicycle information identification device and the wireless communication module, and the main controller 39 is connected with the control module 35 wirelessly.

Specifically, the driving device can be driven by electricity, including a driving motor 12, a power supply battery connected to the driving motor 12, and a moving mechanism connected to the driving motor 12. Preferably, a solar cell panel 15 can also be provided, and the solar cell panel 15 It is electrically connected with the power supply battery to provide power for the driving motor. The moving mechanism may be wheels, tracked wheels, or tracks.

Optionally, the control module 35 may use a single-chip microcomputer.

Optionally, the bicycle fixing device may include an inductive smart lock 9 and an inductive device 16 fixed on the bottom plate, and the inductive smart lock 9 and the inductive device 16 are respectively electrically connected to the main controller 39 for transmitting inductive information to the main controller 39 . Control module 35 . When sensing that a shared bicycle is placed on the carrier device 8, the inductive smart lock 9 is automatically locked.

Inductive smart locks can be set to any shape, such as arcs or polygons.

The sensing device 16 can be a pressure sensor, which is used to determine whether a bicycle is placed on the bottom plate, so as to improve the reliability of the bicycle carrying device 8 and the accuracy of providing information on the placement of the bicycle.

It can be understood that the electronic lock fixing base 14 is also included for fixing the lock body of the inductive smart lock 9 .

Optionally, the information identification device includes a reed switch 10 arranged on the shared bicycle, a telescopic device 38 arranged on the bottom plate of the bicycle carrier 8 opposite to the reed switch 10, a magnet 11 arranged at the top of the telescopic device 38, The telescopic device 38 is electrically connected to the main controller 39, and the reed switch 10 is wirelessly connected to the main controller.

After the sensing device 16 senses the signal, it transmits the sensing signal to the main controller 39 of the transportation device, and controls the telescopic device 38 to pop up to a certain height, so that the magnet 11 on the top is close to the reed switch 10 in the bottom shell near the pedal of the shared bicycle. When the tube 10 is closed, it can be connected to the central control unit of the shared bicycle. The central control unit transmits the lock signal to the main controller 39 through the wireless mobile communication module, and then controls the inductive smart lock 9 to lock, and the telescopic assembly automatically retracts back into the transport device. .

Further, the lock information of the inductive smart lock 9 on the bicycle carrier 8 of this embodiment is linked with the shared bicycle background system, and the shared bicycle background system receives the closing information of the lock on the shared bicycle and receives the inductive smart lock 9 . If the lock information is received, the return of the bicycle is successful; when the user closes the lock on the bicycle and does not receive the lock information of the inductive smart lock 9, the return operation fails.

After the shared bicycle is fixed, the shared bicycle is controlled to be locked to realize the return operation, which can regulate the user's parking behavior, so that the shared bicycle can be parked on the transportation device in the mobile system, and the circulation of the shared bicycle can be realized.

Optionally, in order to determine the specific position of the bicycle carrying device 8 , the bicycle carrying device 8 may further include a positioning module 13 . The positioning module 13 may be a GPS positioning module.

In some embodiments, the above-ground conveying device may be configured as a track structure. As shown in FIG. 1 or 5 , the above-ground conveying device includes a control module 35 and a ground transportation track 2 laid on the ground, and guards provided on both sides of the ground transportation track 2 Column 1, and the bicycle access port provided on the guardrail to provide the bicycle access channel, and the access vehicle interaction device for receiving the interactive information provided at the bicycle access port, the control module 35 is respectively carried by the communication module with the bicycle. The device 8 is connected in communication with the access vehicle interaction device.

The control module 35 receives the information from the access vehicle interaction device and controls the bicycle carrying device 8 to carry the bicycle to the corresponding position. The access vehicle interaction device is used for receiving information about the user's access bicycle.

Optionally, the protective fence 1 may be a fence or a fence.

In some embodiments, the access vehicle interaction device includes an automatic retractable door 4 provided at the access port of a bicycle, and a button for controlling the switch of the retractable door, which may include a door opening button 5 , a vehicle retrieval button 6 and a vehicle storage button 7 .

It also includes a position sensor 3 arranged at the bicycle access port, the position sensor 3 is wirelessly connected with the main controller, when the bicycle carrier 8 moves to the position sensor 3, the position sensor 3 transmits the action signal to the main controller 39, the main controller 39. The controller controls the bicycle carrier 8 to stop. The position sensor 3 can also use an RFID tag, and an RFID reader is provided on the bicycle carrier 8. When the RFID reader detects the corresponding tag information, the vehicle stops.

The underground conveying device 26 is used to provide an underground transportation channel for vehicle transfer between various bicycle pick-up points or vehicle transfer between the storage device 17 and each bicycle pick-and-place point, and is arranged in a position where it is inconvenient to set the conveyor device from the road surface, Such as set in some intersections under the ground.

The underground conveying device can realize the transportation of shared bicycles from the ground to the underground and from the underground to the ground. In some embodiments, as shown in FIG. 6 , the underground conveying device may include an underground transportation track 27, and a pressure expansion and contraction device 30 disposed at the connection between the ground and underground. When the pressure expansion and contraction device 30 is extended to the first position, the pressure expansion and contraction device 30 expands. The upper end surface of the device 30 is flush with the ground and docked. When the pressure expansion device 30 is compressed to the second position, the upper end surface of the pressure expansion device 30 is flush with and docked with the underground transportation rail 27 .

Optionally, the pressure telescopic device 30 may include a bicycle carrying portion 31 arranged in sequence from top to bottom, a telescopic mechanism fixedly connected to the bicycle carrying portion 31 , a fixed platform 28 , and a telescopic drive provided on the fixed platform 28 and electrically connected to the telescopic mechanism. Powerplant 29. The bicycle carrying part 31 can be a carrying plate or a carrying plate with a track, and the track shape and structure of the track matches the underground transportation track 27 . Fixed platform 28 provides stable support. A pressure sensor 32 may also be disposed on the bicycle carrying portion 31 to detect whether a bicycle or a bicycle carrying device 8 is placed on the bicycle carrying portion 31 .

Specifically, the telescopic drive power device 29 may be a hydraulic drive device, and the telescopic mechanism presses the telescopic rod.

Further, the system may also include a control platform that is in communication with the control module 35 in the flow system.

The working principle of the above flow system is as follows:

The user's car needs can be obtained through the car access interaction device, and the car can be accessed directly by pressing the door open button. When there is no car at the current site, you can press the car pickup button. If the current site does not have a car, you can press the save button; the storage device 17, including normal vehicle storage and vehicle storage to be repaired, according to the number of shared bicycles in the system and the demand, necessary supplementation and storage of vehicles in the system; control module 35, real-time receiving and analyzing the operation information in the system, output control The instruction dispatches the bicycle and the bicycle carrying device 8 in the entire flow system; the bicycle carrying device 8 transports the bicycle according to the control dispatching instruction of the control module 35 . In addition, the bicycle carrier 8 is used to determine whether the parking is regulated. When the user cannot directly access the vehicle, the control module 35 schedules the shared bicycles or parked bicycle carriers in nearby stations or the storage device 17 in real time according to the situation of each site and the needs of the user. 8. To meet the needs of users to access the car to the greatest extent.

Example 2

This embodiment provides an automatic dispatching system based on sub-area division, divides shared bicycle sub-areas according to user requirements, and automatically dispatches the shared bicycle mobile system described in Embodiment 1, which is used to dispatch each shared bicycle or bicycle in the mobile system. Bicycle Carrier 8.

The automatic dispatching system based on sub-area division, as shown in FIG. 9 , includes the shared bicycle flow system described in Embodiment 1, and a control platform that sends dispatch instructions to the shared bicycle flow system. The control platform includes a shared bicycle demand prediction system and a dynamic sub-system. Zone division scheduling system;

Shared bicycle demand forecasting system: It is configured to predict the demand of users at different time periods at each site, and obtain the predicted demand for each bicycle pick-up and drop-off point; it provides a theoretical basis for the number of vehicles distributed in the entire mobile system.

Dynamic sub-area division scheduling system: It is configured to divide dynamic sub-areas according to the obtained predicted demand of each bicycle pick-and-place point, and schedule according to the bicycle demand ratio of each bicycle pick-and-place point in the sub-area to generate a schedule. The protocol is sent to the control module 35 to cause the control module 35 to control the bicycle or bicycle carrier 8 in the mobility system.

Example 3

The shared bicycle demand prediction method, based on the random forest algorithm, integrates user needs and shared travel attractiveness, and can accurately obtain user needs. This method can be implemented on the control platform connected to the control module, and can be specifically implemented by the shared bicycle demand prediction system, such as As shown in Figure 10, it includes the following steps:

Step 1, user demand statistics: obtain user travel information and travel reservation information, and count the first bicycle demand X ₁ at the bicycle pick-up and release point;

Step 2. Demand prediction based on the attractiveness of shared travel: determine the attraction points in the vicinity of the bicycle pick-up and drop-off point, and calculate the second bicycle demand X ₂ of the bicycle pick-up and drop point according to the attractiveness of each attraction point;

Step 3. Calculate and obtain the third bicycle demand X ₃ of the bicycle pick-and-place point based on the random forest algorithm;

Step 4: Weighted summation of the demand obtained in the above steps to obtain the demand of each bicycle pick-and-place point.

In step 1, the travel information of the user can be obtained by way of incentive feedback. Incentive feedback can be in the form of points incentives, sending travel questionnaires, the questionnaires include the starting and ending points of the main cycling routes, travel time periods and user opinions, receiving questionnaire survey information, adding points to the accounts that fill in the questionnaires, and ensuring the reliability of data. If the user's riding information is seriously inconsistent with the content of the questionnaire, a certain amount of points will be deducted from the user. Users mainly include fixed users with weekly, monthly or annual cards, as well as some ordinary users.

In step 2, the method of determining the attraction points in the vicinity of the bicycle pick-and-place point, and calculating the demand for the second bicycle according to the attraction force of each attraction point, includes the following steps:

Step 21. Divide the attraction level of the attraction point;

The attraction points are public places with a relatively large flow of people, such as hospitals, schools, parks, bus stations, subway stations, etc. Attraction points refer to places that attract people to share travel.

Optionally, it can be divided according to the flow of people, Level 1: bus station, subway station, Level 2: community, supermarket, school, Level 3: restaurant, park square, Level 4: others;

Step 22, determine the attraction point in the bicycle pick-and-place point setting area, and determine the attraction reduction coefficient λ _x of each attraction point according to the attraction level;

For example, the setting area of the bicycle pick-up and drop-off point can be set as an area within one kilometer around the bicycle pick-and-place point. The greater the flow of people, the greater the reduction coefficient and the greater the demand. The reduction coefficient λ _x can be set according to the proportion of the flow of people.

Step 23: Calculate the second bicycle demand X ₂ at the shared bicycle pick-and-place point according to the attractiveness reduction coefficient λ _x ;

To solve the second bicycle demand X ₂ , the following calculation formula can be used:

Among them, X ₂ is the demand for shared bicycles; S is _the area of one kilometer near the attraction point; S _i is the area of a nearby attraction point, i is the i-th bicycle pick-up point; K is the attraction point for slow travel Proportion, for sites with obvious time characteristics and age characteristics, the travel proportion can be divided according to age levels; N is the number of attraction points; λ _x is the attraction reduction coefficient determined according to different levels of shared travel attraction points.

Step 3. The method for calculating and obtaining the third bicycle demand X ₃ at the bicycle pick-and-place point based on the random forest algorithm includes the following steps:

Step 31: Obtain a sample data set.

Take the historical data on the number of access vehicles and the corresponding relevant characteristic data of all bicycle pick-up and drop-off points in the entire regional system, including geographical location, time, season, holidays, working days, weather, temperature, humidity, wind speed and other characteristic data, As well as the running trajectories of shared bicycles in the area and the starting and ending data as the original data set.

Step 32 , perform sample extraction on the sample data set to obtain training subsets of multiple decision trees.

The bootsrap resampling method is adopted to extract S subsets of training samples from the total samples to construct S regression trees. The extracted training samples are the training set, and the samples that are not extracted from the total samples are used as the test set.

Step 33. Decision tree construction: Based on the principle of loss minimization, each training subset is trained to obtain a decision tree. During the decision tree training process, a set number of feature variables with greater correlation are selected to participate in the decision tree node splitting. A training subset is trained to obtain a random forest regression model;

For each training sample subset, a decision tree is generated based on the loss minimization principle. The S training sample subsets generate S decision trees in total to form a random forest. In order to solve the over-fitting phenomenon caused by too many characteristic variables, select The characteristic variables of are set to no more than log ₂ M+1, where M is the number of associated characteristic variables, and the participating characteristic variables are selected according to the principle of correlation, sorted according to the size of the correlation, and the correlation G is selected. The larger part of the feature variables participate in the decision tree node splitting process.

The correlation determination method can be as follows:

Among them, X is the demand variable, Y _i is a characteristic variable, G is the correlation between the demand variable and a characteristic value, A is the sum of the data of all demand variables X and all characteristic variables Y, and A _i is a certain All data of the feature corresponds to the number of data in A.

After the S decision trees are constructed, the test set data is used for simulation, the error of the decision tree is estimated, and the parameters of the decision tree are optimized. The error estimates of the S decision trees are averaged to obtain the random forest generalization error estimates, and the model parameters are optimized.

Step 34. Prediction results of the random forest regression model: obtain the bicycle trip data and the corresponding characteristic variable data of the bicycle pick-and-place point in real time, input them into the random forest regression model, obtain the voting results of each decision tree, and obtain the weighted random forest regression prediction results. The demand for the third bicycle at the bicycle pick-up and drop-off point X ₃ ;

The prediction results output by the random forest regression prediction model are generated by the voting results of each decision tree. The random forest regression prediction results are as follows:

Among them, Y _i is the relevant characteristic factor data, H _ik is the prediction model of a single decision tree, S is the total number of decision trees constructed, and X _Y is the regression prediction result of the demand for shared bicycles.

In step 3, the number of feature variables for constructing the decision tree is limited according to the correlation size, and the random forest algorithm is optimized, so as to more accurately predict the demand X ₃ .

Through steps 1-3, the result of obtaining the entire demand forecast consists of three parts, and the weighted summation of the demand obtained in the above steps is as follows:

X=λ ₁ X ₁ +λ ₂ X ₂ +λ ₃ X ₃

Among them, λ ₁ , λ ₂ and λ ₃ represent the corresponding weights; X is the total demand of the station; X ₁ is the first bicycle demand; X ₂ is the second bicycle demand obtained based on the attraction of shared travel; X ₃ The third bicycle demand obtained for the prediction based on the random forest algorithm.

This embodiment integrates user needs, shared travel attraction and random forest algorithm, deeply mines user needs, starts from the perspective of user's own economy and convenience, provides incentive feedback services, and mainly mines fixed users (weekly, monthly, annual card) within a certain period of time. Users) car demand, and at the same time integrate the reservation information of some ordinary users to improve the accuracy of demand forecast; introduce the index of shared travel attraction, fully consider the impact of changes in demand caused by attraction points around the site; it can be more convenient to analyze For the historical data of each site, a high-precision random forest algorithm is used, and through the correlation analysis of characteristic variables, the number of characteristic variables for building a decision tree is limited, and the accuracy of random forest forecasting is increased, thereby improving the accuracy of demand forecasting.

Example 4

The dynamic sub-area division scheduling method can adjust the sub-area range in real time through dynamic sub-area division, and improve the flexibility and timeliness of scheduling. The method can be implemented on a control platform connected to the control module, and specifically can be implemented by a dynamic sub-area division and scheduling system, as shown in Figure 11, including the following steps:

Step 1. Obtain the bicycle access data and the trajectory information of the bicycles at each bicycle pick-up and drop-off point;

Step 2. According to the obtained data, classify the bicycle pick-and-place points according to different characteristics;

Step 3. According to the classification result, the adjacent bicycle pick-and-place points are dynamically divided according to the dynamic change of the demand to form a plurality of sub-areas;

Step 4. Schedule each sub-area according to the sub-area division result: if the scheduling cannot meet the bicycle demand of the sub-area, perform the above steps 1-3 to re-divide the sub-area.

In step 1, the historical data information and real-time dynamic access information of the access vehicles at each site are collected. By using the flow system of Embodiment 1, the data information of each bicycle pick-and-place point can be obtained more conveniently and quickly, so that the inherent characteristics of the access vehicle at each site can be accurately analyzed.

In step 2, according to the acquired data, classify the bicycle pick-and-place points according to different characteristics;

The classification of bicycle pick-and-place points according to different characteristics may include classification according to time characteristics, classification according to demand level, and the like.

Step 21, classify according to time characteristics, can be divided into including:

Time-based stations: There is a relatively large demand for bicycles in certain specific time periods, such as the morning peak and evening peak hours.

All-time sites: sites with relatively large demand in all time periods;

Ordinary site: no obvious temporal characteristics.

Step 22: Divide the common sites according to the demand level: according to the predicted demand of each bicycle pick-and-place point, divide according to the demand level.

Step 3. According to the classification result, the adjacent bicycle pick-and-place points are dynamically divided according to the dynamic change of the demand to form a plurality of dynamic sub-areas. Specifically, it can be as follows:

Step 31. According to the time characteristics of the time-based sites and the full-time sites, combined with the dynamic demand conditions of the surrounding sites, form complementary sub-regions with the surrounding sites and form a corresponding scheduling plan;

Step 32: The division and scheduling of dynamic sub-areas for common sites may include the following steps:

Step 321: Merge the sites with high complementarity among the common sites as a pick-and-place point; the complementarity is that the high demand does not overlap in time, and the time periods of the high demand are staggered.

Step 322, dynamically selecting the pick-and-place point with the largest real-time demand and stable demand within the set area as the main site;

Pick-and-place points are geographically continuous. According to the principle of stratified sampling, a major site is selected every certain number of sites. The demand is relatively high relative to the surrounding stations, and the pick-and-place point of the bicycle with the greatest demand is dynamically selected according to the real-time demand;

Step 333: Divide sub-regions according to the principle of tree-like branching: take the main site as the center, adopt the principle of complementarity and the principle of shared travel attraction, select the most suitable sites around and merge to form a sub-region;

The tree-like branching principle is fully combined with the characteristics of the station linkage of the flow system. First, the main station is selected as the root, and then grows according to the principle of a branch upward. When the growth requirements cannot be met, other nodes in this branch are selected to continue. grow. The system in this embodiment is in the form of a strip or a road network. When dividing sub-areas, the main site is divided in a line according to the division conditions, and when the division conditions are not met, other sites on the line are selected for division.

If the current site continues to be merged downward, if the division principle is not satisfied, the merge of this site will be terminated, and then it will be searched whether the previously merged sites still have the possibility of continuing to merge. ) to end the division of the current sub-area. Specifically, it can be as follows:

Calculate the demand difference of a site within a certain period of time, the specific method is as follows:

Q= _Qnow + _Qreturn - _Qneed

Among them, Q is the demand difference; Q _is the current number of vehicles at the site; Q _{is also} the number of vehicles returned at the site within a certain period of time; Q _needs to be the number of vehicles demanded by the site within a certain period of time.

Satisfy the principle of complementarity: After a site is merged with the main site, the total demand difference Q shows a decreasing trend. The specific method for determining the complementarity of needs is as follows:

Among them, K is the reduction coefficient; Q ₁ is the demand difference of the sub-area before the site is merged; Q ₂ is the demand difference of the sub-area after the site is merged; H is the demand complementarity after the merged site.

Satisfy the principle of shared travel attractiveness: If the current sub-district demand difference is negative, indicating that the supply is in short supply, select the site with less shared travel attractiveness when merging sites. If the demand difference is positive, indicating that the supply exceeds demand, select the shared travel attractiveness 's site.

The method for determining the attractiveness of shared travel is as follows:

Among them, A represents the attractiveness of shared travel at a certain site; D _i represents the distance from the site to a certain attraction point in the nearby attraction area; λ _x is the attractiveness reduction coefficient determined according to different levels of shared travel attraction points; R _{i attracts} Represents the radius of an attraction point in the attraction area; S _total represents the total area of the attraction area.

In step 4, scheduling is performed according to the sub-area division result: for the obtained sub-area, the bicycle adjustment between each pick-and-place point within the sub-area is performed. If the sub-area level cannot meet the demand requirement, perform steps 1-4 to re-divide the sub-area.

In this embodiment, scheduling is performed in each sub-area first, and the correlation degree of the sub-areas is fully considered, thereby improving the accuracy of scheduling and the efficiency of scheduling.

Scheduling between bicycle pick-and-place points in the sub-area, specifically: adjusting the distribution of bicycles in each bicycle pick-and-place point in the sub-area according to the demand ratio.

If the demand difference of a certain sub-area exceeds a certain threshold, the scheduling between the sub-areas is performed, and if the adjustment cannot be effectively adjusted, the division of the current sub-area is adjusted.

The current scheduling scheme cannot meet the needs of users, and the dynamic sub-area division is re-divided to form a new scheduling adjustment scheme, which can realize the dynamic adjustment of the sub-area division and improve the flexibility of scheduling.

The dynamic sub-area division method of this embodiment fully combines the characteristics of site linkage in the flow system, adopts the principle of tree branching to select and divide points, and fully considers the influence of internal and external factors in the division conditions, and uses the principle of demand complementarity and sharing. The selection of stations is based on the principle of travel attractiveness, which not only considers the influence of surrounding factors, but also considers the different inherent time characteristics of each station. It is divided into full-time points, sub-period points and ordinary points, and the corresponding sub-areas are divided. Scheduling, each sub-region implements demand proportional scheduling, which can better meet user scheduling needs.

Example 5

This embodiment provides an automatic scheduling method based on sub-area division. The method is implemented in the control platform in the system described in Embodiment 2. The shared bicycle sub-areas are divided according to user needs. The system automatically dispatches each shared bicycle or bicycle carrier 8 in the mobile system.

The automatic scheduling method based on sub-area division includes the following steps:

S1. Obtain the bicycle pick-and-place data of the bike pick-and-place point, and predict the demand of each bike pick-and-place point based on the method of integrating user needs and the attractiveness of shared travel based on the random forest algorithm;

S2. According to the prediction result of the demand, based on the principle of tree-like branching combined with internal and external factors, dynamically divide the bicycle pick-and-place point into sub-areas, and generate a scheduling plan according to the division result;

S3. Execute scheduling control according to the scheduling scheme.

Step 1 adopts the shared bicycle demand forecasting method described in Embodiment 3, and Step 2 adopts the dynamic sub-area division scheduling method described in Embodiment 4 to obtain a scheduling scheme; it also includes a control method executed by the control module 35 according to the scheduling scheme.

The control method performed by the control module 35, as shown in FIG. 12, includes the following:

Step 1. Conveying control between bicycle storage points: According to the scheduling scheme, the number of bicycles at each station is adjusted by controlling the carrier 8 between adjacent stations;

The carrier 8 receives a signal from the control module 35 and moves to a designated position according to the above-ground conveying device and the underground conveying device 26 .

When there is a demand for car pickup or parking, the drive motor 12 of the carrier device 8 is started, and then the shared bicycle is controlled to be transported to the corresponding retractable door 4; when the system does not need to access the car, the system detects that all doors are closed, control The module 35 realizes the equidistant discharge of shared bicycles in each site according to the positioning data of the bottom positioning device 3 of each carrier device 8;

When dispatching through the underground conveying device 26 when passing through the intersection, when the shared bicycle and its carrying device 8 are transported to the pressure sensor 32 of the underground conveying device, the pressure sensor 32 transmits a signal to the telescopic drive power device 29 to activate the pressure telescopic rod 30, and then The shared bicycle is controlled by the bicycle carrying part 31 to be transported downward, and finally the pressure telescopic rods are all retracted into the fixed platform 28. After the shared bicycle is transported to the underground, it is transported through the underground transportation track 27, and when it reaches the designated place, it passes through and downward. In the same way of transportation, the shared bicycle is transported to the ground through the pressure expansion device 30, and the scheduling task is continued.

Step 2. Access control of the access vehicle: obtain the user demand information of the access vehicle interactive device;

When the user needs to pick up the car, it receives the car pick-up information and controls the retractable door to open; dispatches the nearest bicycle to the retractable door position;

When the user needs to park, the parking information is received, and the telescopic door is controlled to open; the carrier 8 with the closest distance is dispatched to the position of the telescopic door;

After the user parks the vehicle, the sensing devices (16) located at both ends of the carrier device sense that a vehicle is placed and automatically lock the vehicle to complete the parking.

Wherein, the nearest bicycle or carrier 8 may be at the current site, and there is no bicycle or carrier 8 that can be dispatched at the current site, and may be in an adjacent site or in the storage device 17 .

Step 3. Storage control of bicycles: count the number of bicycles in the sub-area, including normal vehicles and vehicles to be maintained, and place normal vehicles and maintenance vehicles separately;

When the quantity does not meet the demand requirement, replenish the bicycles to the storage device 17 of the sub-area;

When the number of bicycles is greater than the demand, the excess bicycles in the storage device of the sub-area are dispatched to the sub-area where the demand is not met.

In order to facilitate maintenance by maintenance personnel, if the vehicle needs to be repaired, it will be stored in the first storage layer 20 of the storage device. Maintenance instructions to the maintenance personnel's terminal.

A first storage layer 20, a second storage layer 21 and a third storage layer 22 are provided.

When the vehicle does not need maintenance, the shared bicycle is transported and stored upward along the spiral rising track 23. During storage, it is first transported upward through the spiral rising track 23, and when passing through the second storage layer 21, it passes through the second storage layer 21 and the spiral. The entrance and exit 24 connected to the spiral ascending track 23 enter the second floor. The shared bicycle storage and fixing devices are arranged around the center. The vehicles arriving from the spiral ascending track 23 are stored through continuous rotation. When the storage layer 21 is used, then the first storage layer 20 and the third storage layer 22 are successively stored; when the shared bicycle is dispatched from the storage device 17, the vehicles in the first storage layer 20 are dispatched first, and when the underlying vehicles are not enough to be dispatched, the The shared bicycles of the upper storage device are dispatched in turn.

According to the real-time user needs, the system performs scheduling adjustments in a timely manner according to the above steps and methods to meet the user needs to the greatest extent.

The above descriptions are only preferred embodiments of the present disclosure, and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included within the protection scope of the present disclosure.

Although the specific embodiments of the present disclosure have been described above in conjunction with the accompanying drawings, they do not limit the protection scope of the present disclosure. Those skilled in the art should understand that on the basis of the technical solutions of the present disclosure, those skilled in the art do not need to pay creative efforts. Various modifications or variations that can be made are still within the protection scope of the present disclosure.

Claims (10)

1. Shared bicycle flow system, characterized by: the system comprises an overground conveying device arranged at each single-vehicle taking and placing point, an underground conveying device connected with the overground conveying device at each single-vehicle taking and placing point, and a multi-layer storage device capable of providing single vehicles for the overground conveying device or the underground conveying device; the adjacent bicycle taking and placing points and the ground storage devices are connected through the ground conveying device or the underground conveying device to form a mobile conveying network sharing the bicycles.

2. The shared bicycle flow system as claimed in claim 1, wherein: the storage device comprises a device shell forming a bicycle accommodating space, a plurality of storage layers arranged in the shell, and a transportation rail capable of moving and transporting a bicycle between the storage layers, wherein the transportation rail is provided with an inlet and an outlet of the transportation rail to the storage layer at each storage layer;

or

The transportation track of the storage device comprises a stand column arranged in the shell and a spiral type ascending track fixed on the stand column.

3. The shared bicycle flow system as claimed in claim 1, wherein: the mobile system also comprises a single vehicle carrying device which can move freely relative to each device, each single vehicle storage point is also provided with a control module, each single vehicle carrying device comprises a bottom plate, a driving device and a single vehicle fixing device which are arranged on the bottom plate and used for driving the bottom plate to move, a single vehicle information identification device, a main controller and a wireless communication module, the main controller is respectively connected with the driving device, the single vehicle fixing device, the single vehicle information identification device and the wireless communication module, and the main controller is in wireless connection with the control module;

or

The bicycle fixing device comprises an inductive intelligent lock and an inductive device which are fixed on the bottom plate, wherein the inductive intelligent lock and the inductive device are respectively and electrically connected with the main controller and are used for transmitting inductive information to the control module; or

The information identification device comprises a reed switch arranged on the shared bicycle, a telescopic device arranged on a bottom plate of the bicycle carrying device and opposite to the reed switch in position, and a magnet arranged at the top end of the telescopic device, wherein the telescopic device is electrically connected with the main controller, and the reed switch is wirelessly connected with the main controller.

4. The shared bicycle flow system as claimed in claim 1, wherein: the ground conveying device comprises a control module, a ground conveying track laid on the ground, guard rails arranged on two sides of the ground conveying track, a single-vehicle access opening arranged on the guard rails and used for providing a single-vehicle access channel, and a vehicle access interaction device arranged at the single-vehicle access opening and used for receiving interaction information, wherein the control module is in communication connection with the single-vehicle carrying device and the vehicle access interaction device through communication modules respectively;

or

The parking and taking interaction device comprises an automatic retractable door arranged at a bicycle parking and taking port and buttons for controlling the retractable door to open and close, and can comprise a door opening button, a car taking button and a car parking button;

or

The underground conveying device comprises an underground conveying track and a pressure telescopic device arranged at an underground and overground joint, when the pressure telescopic device extends to a first position, the upper end surface of the pressure telescopic device is flush with the ground and is in butt joint with the ground, and when the pressure telescopic device is compressed to a second position, the upper end surface of the pressure telescopic device is flush with and is in butt joint with the underground conveying track;

the pressure telescopic device comprises a bicycle bearing part, a telescopic mechanism and a fixed platform which are sequentially arranged from top to bottom, and a telescopic driving power device which is electrically connected with the telescopic mechanism and arranged on the fixed platform.

5. The automatic scheduling method based on the sub-area division is characterized by comprising the following steps:

acquiring single vehicle taking and placing data of the single vehicle taking and placing points, and predicting the demand quantity of each single vehicle taking and placing point based on a method for fusing user demands and sharing travel attraction by a random forest algorithm;

according to the prediction result of the demand, based on the tree branch and the combination of internal and external factors, performing dynamic division on the sub-area of the single-vehicle pick-and-place point, and generating a scheduling scheme according to the division result;

the control of the scheduling is performed according to a scheduling scheme.

6. The method of claim 5, wherein the method comprises: the method for forecasting the demand of each single vehicle pick-and-place point based on the method for fusing the user demand and the shared travel attraction by the random forest algorithm is a method for forecasting the demand of the shared single vehicle, and comprises the following steps;

acquiring user travel information and travel reservation information, and counting first bicycle demand of a bicycle pick-and-place point;

determining attraction points of an area near the bicycle picking and placing points, and calculating to obtain a second bicycle demand of the bicycle picking and placing points according to the attraction force of each attraction point;

calculating and obtaining a third bicycle demand of the bicycle pick-and-place point based on a random forest algorithm;

and weighting and summing the demand obtained in the steps to obtain the demand of each single vehicle pick-and-place point.

7. The method of claim 6, wherein the method comprises: in the shared bicycle demand forecasting method, the method for determining the attraction points of the area near the bicycle pick-and-place point and calculating and obtaining the second bicycle demand according to the attraction force of each attraction point comprises the following steps:

dividing the attraction level of the attraction points;

determining attraction points in the setting area of the picking and placing points of the bicycle, and determining the attraction reduction coefficient of each attraction point according to the attraction grade;

calculating and obtaining a second bicycle demand of the shared bicycle pick-and-place point according to the attraction reduction coefficient;

or

The method for calculating and obtaining the third bicycle demand of the bicycle pick-and-place point based on the random forest algorithm comprises the following steps:

acquiring a sample data set;

sample extraction is carried out on the sample data set to obtain training subsets of a plurality of decision trees;

and (3) decision tree construction: on the basis of a minimization principle, each training subset is trained correspondingly to obtain a decision tree, in the training process of the decision tree, a set number of characteristic variables with high correlation are selected to participate in node splitting of the decision tree, and a plurality of training subsets are trained to obtain a random forest regression model;

predicting a result by a random forest regression model: and acquiring the bicycle travel data of the bicycle pick-and-place points and the corresponding characteristic variable data in real time, inputting the data into a random forest regression model, acquiring the voting results of each decision tree, and weighting to obtain a random forest regression prediction result, namely the third bicycle demand of the bicycle pick-and-place points.

8. The method of claim 5, wherein the method comprises:

the control of executing the scheduling according to the scheduling scheme comprises the conveying control among the storage points of the single vehicles, the access control of accessing the vehicles and the storage control of the single vehicles;

or

Based on tree branches combined with internal and external factors, the method for dynamically dividing the sub-areas of the single vehicle pick-and-place points and generating the scheduling scheme according to the division result is the dynamic sub-area division scheduling method, and comprises the following steps:

acquiring the bicycle storing and taking data of each bicycle taking and taking point and the track information of the bicycle;

classifying the single vehicle pick-and-place points according to different characteristics according to the acquired data;

according to the classification result, dynamically dividing the adjacent bicycle picking and placing points according to the dynamic change of the demand quantity to form a plurality of sub-areas;

scheduling according to the result of the division of the subareas: and if the dispatching can not meet the single-vehicle requirement of the subarea, executing the subarea division again.

9. The method of claim 8, wherein the method for automatic scheduling based on subdivision comprises: in the dynamic sub-division scheduling method, classifying the single-vehicle pick-and-place points according to different characteristics can comprise classifying according to time characteristics and required levels to obtain time-share stations, full-time-share stations and common stations;

or

According to the classification result, the adjacent bicycle taking and placing points are dynamically divided according to the dynamic change of the requirement to form a plurality of dynamic subareas, which specifically comprises the following steps:

aiming at the time characteristics of time-sharing sites and full-time sites, combining the dynamic demand conditions of surrounding sites to form sub-regions with the surrounding sites;

merging stations with high complementarity in common stations to serve as a pick-and-place point;

dynamically selecting a pick-and-place point with the largest real-time demand and stable demand within a set area range as a main station;

and (3) carrying out subarea division according to the tree branch principle: selecting the most suitable surrounding sites by taking the main site as the center and adopting a complementarity principle and a shared travel attraction principle to combine to form a sub-area;

or

Scheduling according to the result of the division of the subareas, specifically: and aiming at the obtained sub-regions, carrying out bicycle adjustment between each taking and placing point in the sub-regions, carrying out bicycle adjustment between sub-region layers when the internal adjustment can not meet the requirement of the demand, and carrying out sub-region division again when the sub-region layers can not meet the requirement of the demand.

10. The automatic scheduling system based on the subregion partition is characterized in that: comprising the shared bicycle flow system according to any one of claims 1-4, and a control platform for sending scheduling instructions to the shared bicycle flow system; the control platform comprises a shared bicycle demand prediction system and a dynamic subarea division scheduling system;

the shared single-vehicle demand prediction system is configured to perform the shared single-vehicle demand prediction method in the subdivision-based automatic scheduling method according to any one of claims 5 to 9;

alternatively, the dynamic subdivision scheduling system is configured to perform the dynamic subdivision scheduling method of the subdivision based automatic scheduling method of any of claims 5-9.

Images