CN114897656A - Shared bicycle tidal area parking dispersion method, electronic equipment and storage medium - Google Patents
Shared bicycle tidal area parking dispersion method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114897656A CN114897656A CN202210830958.8A CN202210830958A CN114897656A CN 114897656 A CN114897656 A CN 114897656A CN 202210830958 A CN202210830958 A CN 202210830958A CN 114897656 A CN114897656 A CN 114897656A
- Authority
- CN
- China
- Prior art keywords
- tidal
- electronic fence
- point location
- scheduling
- electronic
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Abstract
The invention provides a shared bicycle tidal area parking dispersion method, electronic equipment and a storage medium, and belongs to the technical field of machine learning. S1, identifying peak time periods according to time distribution of order data of taking and returning the vehicles by the vehicles; s2, expanding an electronic fence; s3, obtaining multi-dimensional bicycle flow characteristics in peak periods; s4, determining an electronic fence cluster; s5, determining a tidal point location set according to the electronic fence cluster; s6, expanding a tidal point location set; s7, searching non-tidal point locations; s8, determining an integral balance increment limiting value of tidal point location scheduling, and scheduling the flow of tidal point location flowing into non-tidal point locations; s9, counting inflow of each electronic fence set in different time periods after scheduling, and finishing the parking diversion in the tidal area. The problem of parking point position can not satisfy the demand, the calculation cost is high, tide fence's discernment is not accurate enough is solved. The effects of high response speed, low calculation cost and accurate identification of the tide electronic fence are realized.
Description
Technical Field
The application relates to a dispersion method, in particular to a shared bicycle tidal area parking dispersion method, electronic equipment and a storage medium, and belongs to the technical field of machine learning.
Background
The shared bicycle is an important component of urban slow traffic and an effective solution to the problem of 'last kilometer' of urban public traffic. The fixing piles are adopted for throwing the early-stage shared bicycle, the parking management problem can be effectively avoided in the mode, and the problems of lack of flexibility and low utilization rate are solved. After the Internet shared bicycle is put on the market, the use characteristics of the Internet shared bicycle are convenient and flexible, and the use characteristics of the Internet shared bicycle are returned along with borrowing and deeply bound with the application of the mainstream mobile phone, so that the user acquisition threshold is further reduced, and the Internet shared bicycle is favored by the market in a short time. Meanwhile, the management problem associated with the release of a large number of shared bicycles is also increasingly the crux of further improving the utilization rate of the shared bicycles and giving consideration to social benefits.
The current management to sharing bicycle mainly combines fence to come to the user and still to the car and restrict, because sharing bicycle user demand is the unbalanced characteristic in space-time, needs to spend transportation and human cost to allocate the bicycle resource. Particularly, in peak periods, due to the phenomenon of 'no borrowing, no entering' caused by the unbalanced resource distribution problem of the shared bicycle, not only is the resource utilization efficiency lost, but also the accumulation problem of the tidal point location shared bicycle has great pressure on city management. Dynamic supply and demand changes cannot be considered by using the electronic fence only, and effective restriction on user return cannot be carried out in a tidal region.
User-oriented shared bicycle scheduling optimization needs to fully combine real-time dynamic characteristics on one hand, and needs to balance the acceptance degree of users to a scheduling algorithm on the other hand, so that the scheduling distance cannot be too far, the scheduling algorithm is ensured not to generate obvious influence on the whole demand, and the profit of enterprises is reduced. In summary, the solution to the problem needs to be dedicated to satisfy the balance of social benefit, user utility and enterprise income, and have sufficient feasibility.
To solve the above problems, researchers have proposed the following two solutions:
firstly, realizing the TOP-K method based on total reserve density by adopting a tide point location identification algorithm
The method considers the electronic fence with obvious tide phenomenon in the peak period, the density of reserved vehicles is high, therefore, the whole research range is divided into P areas, each area comprises a plurality of shared bicycle electronic fences, the total reserved quantity density of all the electronic fences in the area in a specified time window (usually one week) is used as a unique index for descending order sequencing, the first K positions are taken as the areas with obvious tide phenomenon, and the electronic fences in the first K positions are the tide electronic fences.
remainp represents the net inflow in the p-region within a specified time window, Np represents the number of geofences within the p-region, nonce _ area represents the area of the geofences, and remaindenyp represents the net retention density in the p-region.
Secondly, sharing a single vehicle scheduling algorithm:
(1) merchant scheduling model based on VRPSPD
The VRPSPD problem refers to the problem of vehicle paths taken and sent at the same time, the method divides a research range, a dispatching center is established in each area, and a reasonable dispatching plan is arranged by sensing the dynamic requirements of each node in each area. The essence of the method is to establish an objective function representing the scheduling cost, wherein the objective function generally comprises fixed cost, scheduling cost and penalty cost, a series of constraint conditions (in order to meet model assumption) are set, and the optimal scheduling path is solved by utilizing statistical learning methods such as machine learning and deep learning.
An objective function:
constraint conditions are as follows:
(2) nearest neighbor electronic fence matching based on TOP-K
And for each identified tidal electronic fence, solving K non-tidal electronic fences closest to the fence by using a linear scanning algorithm, and then eliminating the electronic fences which cross the street and have the density of the single vehicles exceeding the critical density to obtain the recommended dispatching point.
The above technique still has the following problems:
1. in the TOP-K method based on the total reserve density in the tidal point location identification algorithm, the method ignores the time sequence characteristic data of vehicle taking and returning in a small time window, so that the identification of the tidal electronic fence is not accurate enough, and the electronic fence with obvious tidal phenomena in a certain shorter time window cannot be identified.
2. The scheduling algorithm based on the optimization theory in the shared bicycle scheduling algorithm is as follows: the main service object of the algorithm is a merchant, a dispatching vehicle with large capacity is needed, the dispatching distance is long, more assumed conditions are needed for constructing the model, the closer the model is to the real dispatching condition, the more constraint conditions are, the smaller the feasible region is, the higher the solving complexity is, and the calculation cost and the calculation resource consumption are huge.
3. The scheduling algorithm based on the nearest neighbor theory of TOP-K in the shared bicycle scheduling algorithm is as follows: the algorithm only refers to the space position (such as distance and whether the vehicles cross the street) and the vehicle density of the non-tidal electronic fence for the matching criterion of the tidal electronic fence and the non-tidal electronic fence, and does not consider the supply and demand characteristic complementarity of the call-out area and the call-in area under different time sequences, so that the recommended new parking point position can not meet the user requirement.
Disclosure of Invention
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to determine the key or critical elements of the present invention, nor is it intended to limit the scope of the present invention. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.
In view of the above, to solve the technical problems in the prior art, the present invention provides a shared bicycle tidal area parking grooming method, an electronic device and a storage medium.
According to the first scheme, the shared bicycle tidal area parking dredging method comprises the following steps:
s1, identifying peak time periods according to time distribution of order data of vehicle taking and returning of a single vehicle;
s2, expanding an electronic fence;
s3, acquiring single-vehicle flow data in the buffer area to obtain multi-dimensional single-vehicle flow characteristics in peak periods;
s4, clustering by using the single-vehicle flow characteristics in each electronic fence buffer area in the peak period as model input to determine an electronic fence cluster group;
s5, determining a tidal point location set according to the electronic fence cluster;
s6, expanding a tidal point location set;
s7, searching a non-tidal point location according to the tidal point location of S6;
s8, determining an integral balance increment limiting value of tidal point location scheduling, and scheduling the flow of tidal point location flowing into non-tidal point locations;
s9, counting inflow of each electronic fence set in different time periods after scheduling, and finishing the parking diversion in the tidal area.
Preferably, the buffer is: with the electronic fence as the center, the boundary is expanded outwards to form a 25m area; the bicycle flow data is as follows: data of car taking/returning; the multi-dimensional single car flow characteristics are: and (4) counting the vehicle borrowing and returning data of the single vehicle every 15 minutes.
Preferably, the method for determining the electric fence group is as follows: the clustering effect was evaluated using the Calinski _ harabaz index and the inertia value.
Preferably, the method for determining the tidal point location set according to the electronic fence clustering group is as follows: and calculating the average number of the vehicles taken by the single vehicles and the average number of the vehicles returned by the single vehicles at the peak time according to the number of the electronic fences, sorting by combining the total number of the vehicles returned by the single vehicles and the total number of the vehicles taken by the single vehicles at the peak time, and selecting 20% of clustering groups with the highest unbalance coefficients as a tide point position set.
Preferably, the method of extending the set of tidal point sites is: the method comprises the following steps:
s61, generating buffer areas by all the electronic fences in the tide point position set, wherein the range of the buffer areas is expanded outwards by the boundary of each electronic fence, and the distance range of the outward expansion is defined according to the actual situation;
s62, regarding the electronic fence with the intersection condition in the buffer zones on the same side of the road as the electronic fence of the same point location group;
s63, repeating the steps S61-S62 until no new electronic fence can be searched.
Preferably, the method of searching for non-tidal sites is: and with the tidal point location set of S6 as a central point and r as a radius area for searching, wherein r is not less than 100 meters, establishing a one-to-many non-tidal point location index table for each electronic fence in the tidal point location set, and calculating the scheduling straight line distance between the tidal point location and the associated non-tidal point location.
Preferably, the method for determining the integral balance increment limiting value (modulation value) of the tidal point location scheduling and scheduling the flow of the tidal point location into the non-tidal point location comprises the following steps: determining an integral balance increment limiting value of a tidal point location scheduling area according to historical data of tidal point locations:
wherein the content of the first and second substances,is the tidal pointiIn a period of timetThe historical demand record in the internal storage device,indicating non-tidal sitesIn a period of timetHistorical demand records within.
Preferably, the method for counting the inflow of each electronic fence set in different time periods after scheduling and completing the tidal area parking diversion comprises the following steps: introducing a time weight matrixAWeighting different time periods corresponding to the characteristic data in a mode from near to far and from large to small, and then combining the result obtained by cosine similarity calculation to be used as the tide point electronic fenceAnd non-tidal point fencesWeighted supply and demand complementarity between、When the supply and demand are mutually complemented,、the larger the included angle in space is, the smaller the calculated value is, and the calculation formula is as follows:
wherein the content of the first and second substances,i, jelectronic fence for indicating tidal point locationiAnd a non-tidal point location fence located within an allowable dispatching distance rangej,tWhich represents the corresponding statistical time period of the time,P the electronic fence time-interval flow characteristics of the tidal point location and the non-tidal point location are shown,qindicating the net flow of the electronic fence over a set period of time,Arepresents a time weight matrix in whichIndicating that recent features correspond to higher weights, encouraging the algorithm to prioritize recent supply-demand balances for tidal sites and non-tidal sites,representing electronic fenceiAnd electronic fencejA weighted supply-demand complementarity between;
introducing a distance adjustment factorR:
Wherein the content of the first and second substances,represents a distance sensitivity factor satisfying,The larger, the more sensitive the algorithm is to distance,representing electronic fenceiAnd electronic fencejThe scheduling distance between the first and second antennas,a threshold value of a parking dispatch distance is indicated,the smaller the scheduling distance is, the smaller the utility loss caused by the single-vehicle user is, and the closer electronic fence is preferentially selected for scheduling and distribution under the condition of equal weighted supply and demand complementarity;
and (3) combining the weighted supply and demand complementarity and a distance adjusting factor R to obtain a scheduling matching goodness M:
and the electronic equipment comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the step of the shared bicycle tidal area parking dispersion method in the first scheme.
And the third scheme is a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the shared bicycle tidal area parking evacuation method in the first scheme is realized.
The invention has the following beneficial effects:
1. fault tolerance, using an electronic fence buffer to associate vehicles within a certain distance of the vicinity of the electronic fence, taking into account the bias of the GPS positioning;
2. the method has space-time multi-dimensionality, and is characterized in that the method comprehensively considers the time sequence characteristics of returning/taking the vehicles in different time periods and the space aggregation relationship to screen the electronic fence with the tide characteristics, and further searches the tide electronic fence which is possibly missed to judge based on the neighbor relationship;
3. the parking guidance algorithm has light weight, is moderate in calculation complexity based on the parking guidance algorithm of a user angle, and can perform real-time quick response in a short time;
4. the method has balance, the problem of single-vehicle guidance scheduling of each tide point position in early peak is solved by considering the overall requirements of the area near each tide electronic fence and the supply and demand complementation degree of the called fence and the called fence, the macroscopic balance and the microscopic balance are comprehensively considered, and the reasonability of a scheduling guidance path in space and time is ensured to the maximum extent;
5. the method has interpretability, the cosine similarity is used for representing the supply and demand complementation degree between the called fence and the called fence, the weight parameters in the time weight matrix correspond to the long-term and short-term characteristics, the dispatching and returning cost brought by the returning distance is based, and the distance adjusting factor R is introduced and combined with the user portrait, so that different users can be subjected to differentiated parameter adjustment.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flow chart of a shared bicycle tidal area parking grooming method;
FIG. 2 is a schematic view of an extended tidal site aggregation process;
FIG. 3 is a schematic view of an extended tidal site set;
FIG. 4 is a schematic diagram of searching for non-tidal sites;
fig. 5 is a schematic view of a tidal area parking break.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example 1, the present embodiment is described with reference to fig. 1 to 5, and a shared bicycle tidal area parking evacuation method includes the following steps:
s1, identifying peak time periods according to time distribution of order data of vehicle taking and returning of a single vehicle;
s2, expanding the electronic fence, establishing a 25m buffer area with the boundary outwards for all the electronic fences, and performing centralized counting on vehicle taking/returning data in the time-interval buffer area at intervals of 15 minutes to obtain the multi-dimensional vehicle taking/returning characteristic in the early peak time interval.
S3, acquiring single-vehicle flow data in the buffer area to obtain multi-dimensional single-vehicle flow characteristics in peak periods;
the buffer area is: an area which is expanded outwards by 25m by taking the electronic fence as a center;
the bicycle flow data is as follows: data of car taking/returning; the multi-dimensional bicycle flow characteristics are: single car flow data was collected every 15 minutes.
S4, clustering by using the single-vehicle flow characteristics in each electronic fence buffer area in the peak period as model input, and evaluating the clustering effect by using a Calinski-harabaz index and an insertia value to determine an electronic fence cluster group;
s5, determining a tidal point location set according to the electronic fence cluster, wherein the method comprises the following steps: and calculating the average number of the vehicles taken by the single vehicles and the average number of the vehicles returned by the single vehicles at the peak time according to the number of the electronic fences, sorting by combining the total number of the vehicles returned by the single vehicles and the total number of the vehicles taken by the single vehicles at the peak time, and selecting 20% of clustering groups with the highest unbalance coefficients as a tide point position set.
S6, referring to FIG. 2, expanding the tidal point set, because the electronic fences exist in a group mode when being set, and correlation exists in space, the invention uses a clustering method to screen out the tidal point basic set, further combines with the space neighbor relation among the electronic fences, expands the electronic fences which are in the same group with the identified tidal fences but are not identified as tidal points in the clustering process into the tidal point set to form a final tidal point expanded set, after screening out the tidal point electronic fences (referring to the electronic fence selected in FIG. 3) by combining a clustering algorithm, supposes that the fence number N =2 of the selected tidal point (referring to 1 in FIG. 3), generates a buffer zone (not less than 1 m) by using the central points of all the selected electronic fences with a specified radius, and accommodates the electronic fences which are adjacent to and intersected with the buffer zone into the buffer zone (referring to 2 in FIG. 3), and defining a tidal point location buffer selection set of the iteration, and comparing the tidal point location buffer selection set with the tidal point location buffer selection set of the previous iteration so as to judge whether a new condition is added as the termination condition of the iteration. And continuously iterating according to the method until the newly added electronic fence can not be searched any more.
S7, considering macro balance, taking the electronic fence group as an object, and combining the electronic fence group single-vehicle increment balancing method of historical demand data, referring to fig. 4, according to the tidal point location described in S6, searching for a non-tidal point location, the method is: and (4) with the tidal point location set of S6 as a central point and r as a radius area for searching, wherein r is not less than 100 meters, a one-to-many non-tidal point location index table (table-tidal point location index table) is established for each electronic fence in the tidal point location set, and the scheduling straight line distance between the tidal point location and the associated non-tidal point location is calculated.
Table-tide point index table
Tidal Point location ID | Non-tidal |
1 | 10 |
1 | 11 |
1 | 12 |
2 | 13 |
2 | 14 |
2 | 15 |
… | … |
The radius r is allowed to be adjusted by combining the actual point position distribution condition of the urban electronic fence.
S8, determining an integral balance increment limiting value (namely a scheduling value, according to net inflow of the electronic fence, calculating by using an increment balance method) of the tidal point location scheduling, scheduling the flow of the tidal point location flowing into a non-tidal point location, and calculating by using historical data in the time segment corresponding to the point location to obtain the integral balance increment limiting value of the corresponding tidal point scheduling area:
wherein the content of the first and second substances,is the tidal pointiIn a period of timetThe historical demand record in the internal storage device,indicating non-tidal sitesIn a period of timetHistorical demand records within.
S9, considering microscopic optimization, combining with a real-time scheduling algorithm of weighted cosine similarity and riding distance, guiding returning behaviors of individual bicycle users on a microscopic level, and constructing a scheduling matching goodness index by combining with an actual scheduling distance on the basis of giving priority to supply and demand balance. In the calculation process, firstly, the one-to-one matching is carried out on the orders of the past week (working day) within the range of 25m of the electronic fence according to the actual distance from the record points to the electronic fence, and the characteristic data of the average net vehicle in-out amount (the vehicle returning amount minus the vehicle borrowing amount) of the shared vehicles associated with the electronic fence in different time intervals (15 min intervals) is obtained. And forming estimated characteristic data of the electronic fence one hour in the future. And calculating the matching goodness between the current tidal point location fence and the alternative non-tidal point location balance fence at the initial moment of each time period. And preferentially assign orders that need to be scheduled to the higher priority areas. After the scheduling calculation is completed, the characteristic data of the tide point location electronic fence set in the group and the associated non-tide point location electronic fence set allowed to be scheduled need to be updated in real time according to the scheduled result. And the updated result is used as the matching goodness calculation input of the next scheduling.
Referring to fig. 5, the inflow of each electronic fence set in different time periods after scheduling is counted to complete the tidal area parking diversion, and the method comprises the following steps: introducing a time weight matrixAWeighting different time periods corresponding to the characteristic data in a mode from near to far and from large to small, and then combining the result obtained by cosine similarity calculation to be used as the tide point electronic fenceAnd non-tidal point fencesWeighted supply and demand complementarity between、When the supply and demand are mutually complemented,、the larger the included angle in space is, the smaller the calculated value is, and the calculation formula is as follows:
wherein the content of the first and second substances,i, jelectronic fence for indicating tidal point locationiAnd a non-tidal point location fence located within an allowable dispatching distance rangej,tWhich represents the corresponding statistical time period of the time,P the electronic fence time-interval flow characteristics of the tidal point location and the non-tidal point location are shown,qindicating the net flow of the electronic fence over a set period of time,Arepresenting time weightsA weight matrix of whichIndicating that recent features correspond to higher weights, encouraging the algorithm to prioritize recent supply and demand balances for tidal sites and non-tidal sites,representing electronic fenceiAnd electronic fencejA weighted supply-demand complementarity between;
introducing a distance adjustment factorR:
Wherein the content of the first and second substances,represents a distance sensitivity factor satisfying,The larger, the more sensitive the algorithm is to distance,representing electronic fenceiAnd electronic fencejThe scheduling distance between the first and second antennas,a threshold value of a parking dispatch distance is indicated,the smaller the scheduling distance is, the smaller the utility loss caused by the single-vehicle user is, and the closer electronic fence is preferentially selected for scheduling and distribution under the condition of equal weighted supply and demand complementarity;
and (3) combining the weighted supply and demand complementarity and a distance adjusting factor R to obtain a scheduling matching goodness M:
goodness of matchMAnd the input characteristic vector is continuously updated along with the change of the scheduling result in the scheduling process, so that the minimization of the utility loss of the user on a microscopic level is ensured, and meanwhile, the optimal result of the balanced algorithm is continuously iterated towards the whole region.
The invention can adjust the scheduling effect by combining the management target, the region balance threshold and the setting of the initial characteristic vector in the scheduling matching goodness calculation process in the near term and the medium term. Due to the use of tidal sites and the parking requirements are stable from a long term perspective. In the near term, the algorithm is better than balance adjustment in parameter setting, and a fixed parking habit is formed by guiding a user to adjust the expected parking, so that the amount of orders to be dispatched is reduced. In the long term, the algorithm prefers to keep the area balance, and the intervention on the user is reduced as much as possible to reduce the utility loss.
In embodiment 2, the computer device of the present invention may be a device including a processor, a memory, and the like, for example, a single chip microcomputer including a central processing unit, and the like. And the processor is used for implementing the steps of the recommendation method capable of modifying the relationship-driven recommendation data based on the CREO software when executing the computer program stored in the memory.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The computer readable storage medium of the present invention may be any form of storage medium that can be read by a processor of a computer device, including but not limited to non-volatile memory, ferroelectric memory, etc., and the computer readable storage medium has stored thereon a computer program that, when the computer program stored in the memory is read and executed by the processor of the computer device, can implement the above-mentioned steps of the CREO-based software that can modify the modeling method of the relationship-driven modeling data.
The computer program comprises computer program code which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The present invention has been disclosed in an illustrative rather than a restrictive sense, and the scope of the present invention is defined by the appended claims.
Claims (10)
1. The shared bicycle tidal area parking dredging method is characterized by comprising the following steps:
s1, identifying peak time periods according to time distribution of order data of vehicle taking and returning of a single vehicle;
s2, expanding an electronic fence;
s3, acquiring single-vehicle flow data in the buffer area to obtain multi-dimensional single-vehicle flow characteristics in peak periods;
s4, clustering by using the single-vehicle flow characteristics in each electronic fence buffer area in the peak period as model input to determine an electronic fence cluster group;
s5, determining a tidal point location set according to the electronic fence cluster;
s6, expanding a tidal point location set;
s7, searching a non-tidal point location according to the tidal point location of S6;
s8, determining an integral balance increment limiting value of tidal point location scheduling, and scheduling the flow of tidal point location flowing into non-tidal point locations;
s9, counting inflow of each electronic fence set in different time periods after scheduling, and finishing the parking diversion in the tidal area.
2. The shared bicycle tidal area parking break out method of claim 1, wherein the buffer is: with the electronic fence as the center, the boundary is expanded outwards to form a 25m area; the bicycle flow data is as follows: data of car taking/returning; the multi-dimensional bicycle flow characteristics are: and (4) counting the vehicle borrowing and returning data of the single vehicle every 15 minutes.
3. The shared bicycle tidal area parking break method of claim 2, wherein the method for determining the electronic fence cluster group is: the clustering effect was evaluated using the Calinski _ harabaz index and the inertia value.
4. The shared bicycle tidal area parking break method of claim 3, wherein the method for determining the set of tidal point locations from the electronic fence cluster group is: and calculating the average number of the vehicles taken by the single vehicles and the average number of the vehicles returned by the single vehicles at the peak time according to the number of the electronic fences, sorting by combining the total number of the vehicles returned by the single vehicles and the total number of the vehicles taken by the single vehicles at the peak time, and selecting 20% of clustering groups with the highest unbalance coefficients as a tide point position set.
5. The shared bicycle tidal area parking break method of claim 4, wherein the method of extending the tidal point location set is: the method comprises the following steps:
s61, generating buffer areas by all the electronic fences in the tide point position set, wherein the range of the buffer areas is expanded outwards by the boundary of each electronic fence, and the distance range of the outward expansion is defined according to the actual situation;
s62, regarding the electronic fence with the intersection condition in the buffer zones on the same side of the road as the electronic fence of the same point location group;
s63, repeating the steps S61-S62 until no new electronic fence can be searched.
6. The shared bicycle tidal area parking break method of claim 5, wherein the method of searching for non-tidal points is: and with the tidal point location set of S6 as a central point and r as a radius area for searching, wherein r is not less than 100 meters, establishing a one-to-many non-tidal point location index table for each electronic fence in the tidal point location set, and calculating the scheduling straight line distance between the tidal point location and the associated non-tidal point location.
7. The shared bicycle tidal area parking break method of claim 6, wherein the overall balance increment limit value for the tidal site location scheduling is determined, and the method for scheduling the flow of tidal sites into non-tidal sites is: determining an integral balance increment limiting value of a tidal point location scheduling area according to historical data of tidal point locations:
8. The shared bicycle tidal area parking break and break away method of claim 7, wherein the inflow of each fence set in different time periods after scheduling is counted, and the method for completing the tidal area parking break and break away is as follows: introducing a time weight matrixAWeighting different time periods corresponding to the characteristic data in a mode from near to far and from large to small, and then combining the result obtained by cosine similarity calculation to be used as the tide point electronic fenceAnd non-tidal point fencesWeighted supply and demand complementarity between、When the supply and demand are mutually complemented,、the larger the included angle in space is, the smaller the calculated value is, and the calculation formula is as follows:
wherein the content of the first and second substances,i, jelectronic fence for indicating tidal point locationiAnd a non-tidal point location fence located within an allowable dispatching distance rangej,tWhich represents the corresponding statistical time period of the time,P the electronic fence time-interval flow characteristics of the tidal point location and the non-tidal point location are shown,qindicating the net flow of the electronic fence over a set period of time,Arepresents a time weight matrix in whichIndicating that recent features correspond to higher weights, encouraging the algorithm to prioritize recent supply and demand balances for tidal sites and non-tidal sites,representing electronic fenceiAnd electronic fencejA weighted supply-demand complementarity between;
introducing a distance adjustment factorR:
Wherein the content of the first and second substances,represents a distance sensitivity factor satisfying,The larger, the more sensitive the algorithm is to distance,representing electronic fenceiAnd electronic fencejThe scheduling distance between the first and second antennas,a threshold value of a parking dispatch distance is indicated,20m, the smaller the scheduling distance is, the smaller the utility loss caused by the single-vehicle user is, and the closer electronic fence is preferentially selected for scheduling and distribution under the condition of equal weighted supply and demand complementarity;
and (3) combining the weighted supply and demand complementarity and a distance adjusting factor R to obtain a scheduling matching goodness M:
9. electronic device, characterized in that it comprises a memory and a processor, the memory storing a computer program which when executed by the processor implements the steps of the shared bicycle tidal area parking grooming method of any of claims 1-8.
10. A computer-readable storage medium, having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the shared bicycle tidal area parking grooming method of any of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210830958.8A CN114897656B (en) | 2022-07-15 | 2022-07-15 | Shared bicycle tidal area parking dredging method, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210830958.8A CN114897656B (en) | 2022-07-15 | 2022-07-15 | Shared bicycle tidal area parking dredging method, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114897656A true CN114897656A (en) | 2022-08-12 |
CN114897656B CN114897656B (en) | 2022-11-25 |
Family
ID=82729571
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210830958.8A Active CN114897656B (en) | 2022-07-15 | 2022-07-15 | Shared bicycle tidal area parking dredging method, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114897656B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115482627A (en) * | 2022-08-17 | 2022-12-16 | 宁波美喵科技有限公司 | Shared bicycle positioning method, device, equipment and storage medium |
CN115577306A (en) * | 2022-12-07 | 2023-01-06 | 中南大学 | Shared bicycle trip tide area detection method based on adaptive density clustering |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103556590A (en) * | 2013-11-17 | 2014-02-05 | 应国珍 | Movable motor way isolation barrier |
WO2018072240A1 (en) * | 2016-10-20 | 2018-04-26 | 中国科学院深圳先进技术研究院 | Direction-variable lane control method for tidal traffic flow on road network |
CN108197793A (en) * | 2017-12-27 | 2018-06-22 | 南京邮电大学 | A kind of shared bicycle concocting method based on tidal model and particle cluster algorithm |
CN108734952A (en) * | 2018-04-26 | 2018-11-02 | 苏州科技大学 | A kind of shared bicycle specification parking management system based on fence |
CN110225457A (en) * | 2019-04-17 | 2019-09-10 | 阿里巴巴集团控股有限公司 | Monitoring and managing method, device, server and the readable storage medium storing program for executing of shared bicycle |
CN111461500A (en) * | 2020-03-12 | 2020-07-28 | 北京航空航天大学 | Shared bicycle system tide phenomenon control method based on dynamic electronic fence and reinforcement learning |
CN112884327A (en) * | 2021-02-25 | 2021-06-01 | 湖南喜宝达信息科技有限公司 | Electric bicycle tide scheduling method, server system and readable storage medium |
CN113095406A (en) * | 2021-04-14 | 2021-07-09 | 国能智慧科技发展(江苏)有限公司 | Electronic fence effective time period management and control method based on intelligent Internet of things |
CN113553482A (en) * | 2021-09-18 | 2021-10-26 | 深圳市城市交通规划设计研究中心股份有限公司 | Stay point identification and trip chain construction system, algorithm, equipment and storage medium |
CN113850310A (en) * | 2021-09-16 | 2021-12-28 | 杭州电子科技大学 | Shared bicycle electronic fence planning method based on block subdivision and maximum area coverage |
-
2022
- 2022-07-15 CN CN202210830958.8A patent/CN114897656B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103556590A (en) * | 2013-11-17 | 2014-02-05 | 应国珍 | Movable motor way isolation barrier |
WO2018072240A1 (en) * | 2016-10-20 | 2018-04-26 | 中国科学院深圳先进技术研究院 | Direction-variable lane control method for tidal traffic flow on road network |
CN108197793A (en) * | 2017-12-27 | 2018-06-22 | 南京邮电大学 | A kind of shared bicycle concocting method based on tidal model and particle cluster algorithm |
CN108734952A (en) * | 2018-04-26 | 2018-11-02 | 苏州科技大学 | A kind of shared bicycle specification parking management system based on fence |
CN110225457A (en) * | 2019-04-17 | 2019-09-10 | 阿里巴巴集团控股有限公司 | Monitoring and managing method, device, server and the readable storage medium storing program for executing of shared bicycle |
CN111461500A (en) * | 2020-03-12 | 2020-07-28 | 北京航空航天大学 | Shared bicycle system tide phenomenon control method based on dynamic electronic fence and reinforcement learning |
CN112884327A (en) * | 2021-02-25 | 2021-06-01 | 湖南喜宝达信息科技有限公司 | Electric bicycle tide scheduling method, server system and readable storage medium |
CN113095406A (en) * | 2021-04-14 | 2021-07-09 | 国能智慧科技发展(江苏)有限公司 | Electronic fence effective time period management and control method based on intelligent Internet of things |
CN113850310A (en) * | 2021-09-16 | 2021-12-28 | 杭州电子科技大学 | Shared bicycle electronic fence planning method based on block subdivision and maximum area coverage |
CN113553482A (en) * | 2021-09-18 | 2021-10-26 | 深圳市城市交通规划设计研究中心股份有限公司 | Stay point identification and trip chain construction system, algorithm, equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
刘冰等: "杭州市自行车租还潮汐与街区用地模式关系研究", 《规划师》 * |
黄梦雪: "共享单车骑行特征分析及布局优化研究", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115482627A (en) * | 2022-08-17 | 2022-12-16 | 宁波美喵科技有限公司 | Shared bicycle positioning method, device, equipment and storage medium |
CN115482627B (en) * | 2022-08-17 | 2024-02-06 | 宁波美喵科技有限公司 | Shared bicycle positioning method, device, equipment and storage medium |
CN115577306A (en) * | 2022-12-07 | 2023-01-06 | 中南大学 | Shared bicycle trip tide area detection method based on adaptive density clustering |
Also Published As
Publication number | Publication date |
---|---|
CN114897656B (en) | 2022-11-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114897656B (en) | Shared bicycle tidal area parking dredging method, electronic equipment and storage medium | |
CN108648457B (en) | Method, device and computer readable storage medium for speed prediction | |
Caruso et al. | Spatial configurations in a periurban city. A cellular automata-based microeconomic model | |
CN106549772A (en) | Resource prediction method, system and capacity management device | |
CN108764555A (en) | A kind of shared bicycle based on Hadoop parks a site selecting method | |
CN109544690A (en) | Shared bicycle trip influence factor recognition methods, system and storage medium | |
Qiu et al. | The transformation of urban industrial land use: A quantitative method | |
CN106485348A (en) | A kind of Forecasting Methodology of transaction data and device | |
Li et al. | Effects of dockless bike-sharing system on public bike system: case study in Nanjing, China | |
CN110223502A (en) | A kind of method and device of crossing inlet track data canalization | |
CN101763600A (en) | Land use supply and demand prediction method based on model cluster | |
CN115099542B (en) | Cross-city commuting trip generation and distribution prediction method, electronic device and storage medium | |
CN112906950A (en) | Sponge city planning and designing system | |
CN109447319A (en) | A kind of Meshing Method, computer readable storage medium and terminal device | |
CN116437291A (en) | Cultural circle planning method and system based on mobile phone signaling | |
CN116882715B (en) | Pile-car linkage orderly safe power utilization method and system based on cloud server | |
CN104732760B (en) | The update method and device of a kind of category of roads | |
CN110543660A (en) | low-impact development simulation method, system and related device | |
CN108171532A (en) | A kind of user group distribution forecasting method and system | |
Zheng et al. | How Many Are Too Many? Analyzing Dockless Bike-Sharing Systems with a Parsimonious Model | |
CN110111001A (en) | A kind of Site planning method of electric automobile charging station, device and equipment | |
CN116227760B (en) | Method, device, storage medium and equipment for predicting influence of travel activities | |
Ikram et al. | The application of multi-attribute decision making methods in integrated watershed management | |
CN115640756A (en) | Parking demand prediction model and method based on multi-source data and application thereof | |
CN110175718A (en) | A kind of berth allocation method and terminal device |
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 |