Parking point recommendation method and recommendation system for shared electric bicycles and computing equipment

Abstract

The invention discloses a parking spot recommendation method and recommendation system for a shared electric bicycle and a computing device, and belongs to the technical field of electric digital data processing. Taking at least one parking point near the destination as a candidate parking point; obtaining a route between the electric bicycle and the candidate parking spot; screening candidate routes from the routes according to the parking condition of the parking point, the distance of the routes, the riding duration and the congestion condition; determining a target parking point according to the candidate route; and recommending the target parking spot to the user. The parking condition, the saturation condition, the riding distance and the riding duration of the parking point and the recommended parking point are comprehensively considered; the accumulation phenomenon of the parking spots due to too many vehicles is avoided, and the utilization rate of the parking spots is increased; the user is prevented from consuming plenty of time to find the parking spot, and the vehicle use experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a method and system for recommending parking spots for shared electric bicycles, and a computing device. Background Art

[0002] Shared electric bicycles have entered various large and small cities, bringing convenience to travelers and solving the problem of the last mile. Electric bicycles have become an important means of transportation, bringing traffic convenience. Currently, users need to park the electric bicycle at a parking spot or parking zone in a specified area before returning the vehicle. These parking spots are usually provided with parking lines and electronic fences.

[0003] This parking and returning method brings some troubles to users. The destination of the user is usually not the same as the parking spot, or the parking zone at the destination is already full of electric bicycles. At this time, the user needs to find a suitable parking spot, which is very inconvenient and consumes a lot of time of the user. After the user's order starts, the situation of the parking spots near the destination cannot be determined, resulting in a decline in the user experience. Summary of the Invention

[0004] In view of the above technical problems existing in the prior art, the present invention provides a method and system for recommending parking spots for shared electric bicycles, and a computing device, which recommend a parking spot for the user according to the destination, and improve the efficiency of parking and returning the vehicle.

[0005] The first aspect of the present invention discloses a method for recommending a parking spot for a shared electric bicycle, including the following steps: obtaining the riding destination; taking at least one parking spot near the destination as a candidate parking spot; obtaining the route between the electric bicycle and the candidate parking spot; screening candidate routes from the routes according to the parking situation of the parking spot, as well as the distance, riding duration, and congestion situation of the route; determining a target parking spot according to the candidate routes; and recommending the target parking spot to the user.

[0006] Preferably, the method for screening candidate routes includes:

[0007] Normalizing the number of parked vehicles, riding distance, riding duration, and congestion duration of the parking spot to obtain a saturation degree, a distance value, a riding duration value, and a congestion duration value respectively;

[0008] After normalization, constructing an objective function;

[0009] Obtaining the objective value of the route through the objective function;

[0010] Sorting the routes from small to large according to the objective value, and taking the first Q routes as candidate routes, where Q is a natural number.

[0011] Preferably, the objective function is expressed as:

[0012] f = w1·d′ + w2·t′ + w3·c′ + w4·(1 - s′) (3)

[0013] Wherein, w1, w2, w3, and w4 are weights, d′ represents a distance value, t′ represents a duration value, c′ represents a congestion duration value, and s′ represents a saturation degree;

[0014] Wherein, w1 + w2 + w3 + w4 = 1.

[0015] Preferably, the method for standardizing the indicators of the number of parked vehicles, cycling distance, cycling duration, and congestion duration is as follows:

[0016] In = (Vi - Vmin) / (Vmax - Vmin) (1)

[0017] Wherein, In represents the standardized value of the indicator, Vi represents the value of the indicator, Vmin represents the minimum value, and Vmax represents the maximum value.

[0018] Preferably, by minimizing the objective function value, the best candidate route is obtained, and the corresponding parking points, distance, cycling duration, and congestion duration are obtained.

[0019] Preferably, the calculation method of the saturation degree is expressed as:

[0020]

[0021] Wherein, s represents the saturation degree, Ui represents the current number of parked vehicles or the predicted number of parked vehicles, max(U) represents the maximum number of parked vehicles, and min(U) represents the minimum number of parked vehicles.

[0022] Preferably, the method for predicting the number of parked vehicles includes:

[0023] Obtain historical data and establish a time series according to the vehicle usage time period;

[0024] Predict the number of parked vehicles based on the average value of the unlocking quantity and locking quantity within K days, where K is a natural number.

[0025] Preferably, the calculation method for predicting the number of parked vehicles is:

[0026]

[0027] Wherein, Ui represents the predicted number of parked vehicles, K i represents the unlocking quantity on the i-th day, L i represents the locking quantity on the i-th day, and N represents the current number of parked vehicles at the return point.

[0028] The second aspect of the present invention provides a recommendation system for implementing the above-mentioned parking point recommendation method. The recommendation system includes a collection module, a parking point preselection module, a route planning module, a parking point screening module, and a recommendation module.

[0029] The collection module is used to obtain the cycling destination.

[0030] The parking point preselection module is used to obtain at least one parking point near the destination as candidate parking points.

[0031] The route planning module is used to obtain the route between the electric bicycle and the candidate parking points.

[0032] The parking point screening module is used to screen the candidate routes according to the parking situation of the parking points, as well as the distance, cycling duration, and congestion situation of the routes, and determine the target parking point.

[0033] The recommendation module is used to recommend the target parking point and the corresponding route to the user.

[0034] The third aspect of the present invention provides a computing device, including a memory that stores code. When the code is processed, the above-mentioned parking point recommendation method is executed.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows: By comprehensively considering the parking situation, saturation situation, cycling distance, and cycling duration of the parking points, the recommended parking points can be ensured that there will be no accumulation phenomenon due to too many vehicles, improving the utilization rate of the parking points; avoiding users spending a lot of time looking for parking points and improving the vehicle usage experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flowchart of the parking point recommendation method for shared electric bicycles of the present invention;

[0037] Figure 2 is a flowchart of the method for screening candidate routes;

[0038] Figure 3 is a logic block diagram of the recommendation system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] The present invention will be further described in detail below with reference to the accompanying drawings:

[0041] Overview: Shared electric bicycles generally refer to bicycles or electric bicycles put on the market in the form of rental. Electronic fence: It is a closed area enclosed by coordinates where shared bicycles or electric bicycles are parked within the specified area. The user side refers to the terminal application used by users who use shared electric bicycles. The ground area corresponding to the electronic fence is called a parking zone or a parking spot. Shared electric bicycles rely on being within the parking spot.

[0042] After riding to the destination, the user of the electric bicycle returns the electric bicycle to the designated location for return. The return can be completed in various ways such as judging the parking position coordinates, Bluetooth ground nails, intelligent footrests, RFID landmarks, photo return, camera return, etc.

[0043] The first aspect of the present invention provides a method for recommending a parking spot for a shared electric bicycle, as Figure 1 shown, including the following steps:

[0044] Step 101: Obtain the riding destination.

[0045] The riding destination can be selected or input by the user.

[0046] Step 102: Use at least one parking spot near the destination as a candidate parking spot.

[0047] Parking spots within a certain range of the destination can be used as parking spots. Parking spots within a certain distance range can be screened, such as within a range of 100 - 200 meters; or parking spots within a certain walking time range can be screened, such as within a walking range of 2 - 8 minutes.

[0048] Step 103: Obtain the route between the electric bicycle and the candidate parking spot.

[0049] The method of planning the current position of the electric bicycle and the candidate parking spot is a prior art and will not be elaborated in the present invention.

[0050] Step 104: Screen candidate routes from the said routes according to the saturation situation / parking situation of the parking spot, as well as the distance, riding duration, and congestion situation of the route.

[0051] Step 105: Determine the target parking spot according to the said candidate routes.

[0052] Step 106: Recommend the said target parking spot to the user.

[0053] For the recommended parking spot, the parking situation, saturation situation, riding distance, and riding duration of the parking spot are comprehensively considered; it is ensured that there will be no accumulation phenomenon due to too many vehicles at the parking spot, and the utilization rate of the parking spot can also be improved; it is avoided that users consume a large amount of time to find a parking spot, and the vehicle usage experience is improved.

[0054] AsFigure 2 , in step 104, candidate routes can be screened by constructing an objective function. Specifically, it includes the following steps:

[0055] Step 401: Standardize the number of parked vehicles, riding distance, riding duration, and congestion duration at the parking points to obtain the saturation, vacancy, distance value, riding duration value, and congestion duration value respectively.

[0056] Among them, the vacancy = 1 - saturation, and the saturation and vacancy are calculated based on the number of parked vehicles at the parking point. The calculation method of the standardized value of each index is shown in formula 1:

[0057] In = (Vi-Vmin) / (Vmax-Vmin) (1)

[0058] Among them, In represents the standardized value, Vi represents the value of the index, Vmin represents the minimum value, and Vmax represents the maximum value.

[0059] Step 402: Construct the objective function of the route according to the vacancy / saturation, distance value, and duration value.

[0060] The duration value includes the estimated riding duration value and congestion duration value. The standard value of the distance or walking duration between the parking point and the destination can also be used as an index of the objective function.

[0061] The objective function is expressed as:

[0062]

[0063] Among them, f represents the objective function, m is the number of indexes, w j represents the weight of the jth index, and Inj represents the standardized value of the jth index.

[0064] In a specific embodiment, the objective function is:

[0065] f=w1·d′+w2·t′+w3·c′+w4(1-s) (3)

[0066] Among them, w1, w2, w3, and w4 are weights, d′ represents the distance value, t′ represents the duration value, c′ represents the congestion duration value, and s represents the saturation. The duration value is the sum of the riding duration value and the congestion duration value.

[0067] Among them, w1+w2+w3+w4=1(4).

[0068] 1-s is the vacancy, indicating the availability of the parking point; the higher the saturation s, the lower the availability.

[0069] Step 403: Obtain the objective values of each route through the objective function. The objective value reflects the passing cost under this route.

[0070] Step 404: Sort the routes from small to large according to the objective value, and take the first Q routes as candidate routes, where Q is a natural number.

[0071] After screening the candidate routes, recommend the candidate routes and their corresponding parking points to the user. However, this is not limited to this, and the best candidate route can also be obtained by minimizing the objective function, and only one best candidate route is recommended to the user.

[0072] The sum index combination of the best candidate route can be expressed as: arg min(f), and return the index value corresponding to the objective function of the candidate route.

[0073] Embodiment 1

[0074] The index values include: distance: di, duration: ti, congestion duration: ci; the set of parking points near the destination: P = {P1, P2,...}. The saturation si of the parking point; weights: w1, w2, w3, and w4; the route set is R = {R1, R2, R3}.

[0075] Step 501: Standardize the distance, time, and congestion of the driving route.

[0076]

[0077] Among them, di′ represents the distance value, which is the standard value of the route distance, di represents the route distance, max(d) represents the maximum route distance, and min(d) represents the minimum route distance; ci′ represents the congestion duration value, ci represents the congestion duration, max(c) represents the maximum congestion duration, and min(c) represents the minimum congestion duration; s represents the saturation, Ui represents the current number of parked vehicles or the predicted number of parked vehicles, max(U) represents the maximum number of parked vehicles, and min(U) represents the minimum number of parked vehicles.

[0078] Step 502: Calculate the objective function value.

[0079] There is at least one route between the current electric bicycle and a parking belt near the target area.

[0080] Step 503: Obtain the best candidate route by minimizing the objective function value, and obtain the corresponding parking point, distance, riding duration, congestion duration, etc. Or, sort the objective function values from small to large, take the first 3 candidate routes, and recommend the candidate routes to the user for the user to choose.

[0081] In specific implementation, refer to Table 1 for the route. w1 = 0.3 (distance), w2 = 0.4 (time), w3 = 0.2 (congestion situation), w4 = 0.1 (availability of parking spaces).

[0082] Table 1

[0083]

[0084] The objective function value of Route 1 to Parking Point 1 is 0.5, that of Route 2 is 0.53, and that of Route 3 is 0.6; the objective function value of Route 4 to Parking Point 2 is 0.45, that of Route 5 is 0.48, and that of Route 6 is 0.55; the objective function value of Route 7 to Parking Point 3 is 0.4, that of Route 8 is 0.43, and that of Route 9 is 0.5.

[0085] The minimum value is the objective function value of Route 7 to Parking Point 3; followed by Route 8 and Route 4.

[0086] The method for obtaining the predicted parking number Ui includes:

[0087] Step 601: Obtain historical data and establish a time series according to the vehicle usage time period.

[0088] For example, on weekdays, establish the first time series from 8 to 9 o'clock; establish the second time series from 9 to 10 o'clock; however, the granularity of the time period division is not limited to this, and data can also be divided every 5 minutes, such as the historical data from 9:00 to 9:05, and collect the historical data within the past 7 days to establish a time series. The indicators of each time series include the unlocking quantity, locking quantity, current number of vehicles, and maximum carrying capacity, etc.

[0089] Step 701: Predict the parking number according to the average values of the unlocking quantity and locking quantity within K days, where K is a natural number.

[0090] The calculation method for predicting the parking number is:

[0091]

[0092] where K i represents the unlocking quantity on the i-th day, L i represents the locking quantity on the i-th day, N represents the current parking number at the return point. Ui < C, where C represents the maximum carrying capacity.

[0093] i = 0 represents today, i = -1 represents yesterday, and so on. Take the average unlocking quantity in the past 7 days minus the average locking quantity in the past 7 days plus the number of vehicles at the current return point, and compare it with the maximum carrying capacity of this return point set in the system. If the former is greater than the latter, the vehicle saturation at this return point is too high and parking is not recommended; otherwise, if the former is less than the latter, this parking point is selected.

[0094] The screening route of the present invention has the most suitable distance, the shortest driving time, the closest distance, and excludes routes with congestion, construction, etc. It can not only ensure that there is no accumulation of vehicles at the parking points due to too many vehicles, but also improve the utilization rate of the parking points. It has more advantages than the independent and closed operation of each automobile enterprise.

[0095] In another specific embodiment, there are multiple enterprises operating shared electric bicycles. The information of the parking points (electronic fences) reported by each enterprise and the corresponding return vehicle solutions (RFID, Bluetooth, electronic footrests, high-precision GPS, etc.) of these parking points can be received. The number of vehicles at the current parking point is monitored in real time to calculate the saturation degree. When the user clicks the return vehicle button after riding to the destination, the unsaturated parking points available for parking near the user are pushed to the automobile enterprises, and the automobile enterprises then prompt the user through the user terminal.

[0096] The process of calculating the unsaturated parking points available for parking is as follows: The supervision platform obtains the return vehicle capabilities (one or more of RFID, Bluetooth, electronic footrests, high-precision GPS, etc.) of the shared electric bicycle ridden by the user, as well as the return vehicle capabilities, the distance between the parking point and the user, the saturation degree, and the saturation trend (decrease and increase) in the next 5 minutes of the parking points near the user. Based on the above parameters, a list of parking points suitable for the user to park, the number of vehicles allowed to be parked at each parking point, and the number of vehicles currently parked are calculated, and these data are pushed to the automobile enterprises. The automobile enterprises can prompt the user with the list of parking points at the vehicle use end to select a parking point suitable for themselves.

[0097] At the same time, in order to improve the user experience and the operation efficiency of the automobile enterprises, the search destination submitted by the user to the automobile enterprises is received, combined with the road conditions information between the departure place and the destination, and the most suitable parking points near the destination (calculated by combining the number of vehicles, saturation trend, and scanning code unlocking volume trend of the parking points near the destination), and a driving route is planned and pushed to the automobile enterprises. The automobile enterprises can display this route and the most suitable parking points to the user for use.

[0098] The second aspect of the present invention provides a recommendation system for shared electric bicycle parking points, as Figure 3 , including a collection module 1, a parking point preselection module 2, a route planning module 3, a parking point screening module 4, and a recommendation module 5,

[0099] The collection module 1 is used to obtain the riding destination;

[0100] The parking point preselection module 2 is used to obtain at least one parking point near the destination as a candidate parking point;

[0101] The route planning module 3 is used to obtain the route between the electric bicycle and the candidate parking point;

[0102] The parking point screening module 4 is used to screen candidate routes and determine the target parking point according to the saturation / parking situation of the parking point, as well as the distance, riding duration, and congestion situation of the route;

[0103] The recommendation module 5 is used to recommend the target parking point and the corresponding route to the user.

[0104] A third aspect of the present invention provides a computing device, which includes a processor and a memory. The memory stores code that, when processed, executes the above-mentioned parking point recommendation method.

[0105] The processor can be a multi-core processor or can include multiple processors. In some embodiments, the processor can include a general main processor and one or more special coprocessors, such as a graphics processing unit (GPU), a digital signal processor (DSP), etc. In some embodiments, the processor can be implemented using custom circuits, such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0106] The memory may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage. Among them, ROM can store static data or instructions required by the processor or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0107] A fourth aspect of the present invention provides a server, wherein the server is deployed with a processor and a memory, wherein the memory stores a code, and when the code is processed, the above-mentioned parking point recommendation method is executed.

[0108] The flowcharts and block diagrams in the accompanying drawings show possible implementations of systems and methods according to various embodiments of the present invention.

[0109] The present system architecture, function and operation. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] In some of the processes described in the specification, claims, and the above-mentioned drawings of this application, there are multiple operations that occur in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any order of execution. Additionally, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0111] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for recommending parking spots for shared electric bicycles, characterized in that, It includes the following steps: Obtain the cycling destination; Take at least one parking point near the destination as the candidate parking point; Obtain the route between the electric bicycle and the candidate parking point; According to the parking situation of the parking point, as well as the distance, cycling duration, and congestion situation of the route, screen the candidate routes from the said routes; Determine the target parking point according to the said candidate routes; Recommend the said target parking point to the user.

2. The parking spot recommendation method according to claim 1, wherein The method for screening candidate routes includes: Standardize the number of parked vehicles, cycling distance, cycling duration, and congestion duration of the parking point to obtain the saturation, distance value, cycling duration value, and congestion duration value respectively; After standardization, construct the objective function; Obtain the objective value of the said route through the objective function; Sort the routes from small to large according to the objective value, and take the first Q routes as the candidate routes, where Q is a natural number.

3. The parking point recommendation method according to claim 2, wherein The objective function is expressed as: f = w1·d′ + w2·t′ + w3·c′ + w4(1 - s) (3) Where w1, w2, w3, and w4 are weights, d′ represents the distance value, t′ represents the duration value, c′ represents the congestion duration value, and s represents the saturation; Where w1 + w2 + w3 + w4 = 1.

4. The parking point recommendation method according to claim 2, characterized in that, The method for standardizing the indicators of the number of parked vehicles, cycling distance, cycling duration, and congestion duration: In = (Vi - Vmin) / (Vmax - Vmin) (1) Where In represents the standardized value of the indicator, Vi represents the value of the indicator, Vmin represents the minimum value, and Vmax represents the maximum value.

5. The parking spot recommendation method according to claim 4, characterized in that Obtain the best candidate route by minimizing the objective function value, and obtain the corresponding parking point, distance, cycling duration, and congestion duration.

6. The parking point recommendation method according to claim 4, characterized in that The calculation method of saturation is expressed as: Where s represents the saturation, Ui represents the current number of parked vehicles or the predicted number of parked vehicles, max(U) represents the maximum number of parked vehicles, and min(U) represents the minimum number of parked vehicles.

7. The parking point recommendation method according to claim 6, characterized in that The method for predicting the number of parked vehicles includes: Obtain historical data and establish a time series according to the vehicle usage time period; Predict the number of parked vehicles according to the average value of the unlocking and locking quantities within K days in the time series, where K is a natural number.

8. The parking point recommendation method according to claim 7, wherein, The calculation method for predicting the number of parked vehicles is: Among them, Ui represents the predicted number of parked vehicles, and K i represents the unlocking volume on the i-th day, and L i represents the locking volume on the i-th day, and N represents the current number of parked vehicles at the return point.

9. A recommendation system, characterized in that, For implementing the parking point recommendation method described in any one of claims 1 - 8, The recommendation system includes an acquisition module, a parking point preselection module, a route planning module, a parking point screening module, and a recommendation module, The said acquisition module is used to obtain the cycling destination; The said parking point preselection module is used to obtain at least one parking point near the destination as the candidate parking point; The route planning module is used to obtain the route between the electric bicycle and the candidate parking point; The said parking point screening module is used to screen the candidate routes according to the parking situation of the parking point, as well as the distance, cycling duration, and congestion situation of the route, and determine the target parking point; The said recommendation module is used to recommend the said target parking point and the corresponding route to the user.

10. A computing device, characterized in that, It includes a memory, and the memory stores code, which when processed, executes the parking point recommendation method described in any one of claims 1 - 8.

Images