A method, system, device and storage medium for calculating the usage efficiency of a shared electric bicycle system based on order data

Through in-depth mining based on real large sample order data, the riding and parking characteristics of shared electric bicycles are extracted, combined with time and space differences, and the regional similarity and vacancy rate are calculated, the shortcomings in the use efficiency evaluation of shared electric bicycle systems in the prior art are solved. More accurate regional division and space-time usage efficiency calculation are achieved.

CN118521371BActive Publication Date: 2024-11-29KUNMING UNIV OF SCI & TECH
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202410583949.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-11
Publication Date
2024-11-29
Estimated Expiration
2044-05-11

AI Technical Summary

Technical Problem

The prior art is difficult to accurately evaluate the efficiency of the use of shared electric bicycle systems, lacks reflection on the actual operation, failing to consider factors such as vehicle abandonment, maintenance or non-stationarity in space, resulting in abnormal and misjudgment of area.

Method used

Based on real large sample order data, the characteristics of riding time, parking time and riding distance are extracted, and combined with time and space differences, regional similarity and vacancy rate indicators are calculated to realize the division of the best aggregation area in the city and the calculation of time and space use efficiency.

Benefits of technology

The accurate regional division and spatial and temporal use efficiency calculation of urban shared electric bicycle systems are realized, providing reference for enterprise operations and government planning, and the results are more in line with the actual situation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118521371B_ABST
    Figure CN118521371B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of shared electric bicycle operation and management, and specifically discloses a method, system, device and storage medium for calculating the utilization efficiency of a shared electric bicycle system based on order data. The method includes the following steps: constructing a shared electric bicycle system database; feature extraction; data cleaning; determining the optimal size of urban areas; and spatiotemporal calculation of utilization efficiency. The method of the present invention is based on the deep mining and utilization of large sample order data that is actually generated, and comprehensively considers the usage characteristics of shared electric bicycles and the spatiotemporal differences in urban areas, thereby achieving the optimal division of urban shared electric bicycle system areas and the calculation of spatiotemporal utilization efficiency. The measurement and identification process of the present invention is simple, easy to operate and express, and the data results are more authentic and reliable, with good practicality, accuracy and scalability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of shared electric bicycle operation management, and in particular to a method, system, device and storage medium for calculating the utilization efficiency of a shared electric bicycle system based on order data. Background Art

[0002] As a convenient, economical, green and healthy new mode of transportation, shared electric bicycles provide more diversified options for residents to meet their short-distance travel needs. However, with the rapid development of shared electric bicycle systems, the utilization efficiency of inter-city vehicle systems is low, and the imbalance between vehicle supply and residents' demand is becoming increasingly obvious. In areas with frequent use, the supply of vehicles is insufficient to meet residents' travel needs; while in other areas, the supply of vehicles exceeds the demand, resulting in a large number of vehicles being idle, and the vehicle resources between the entire city are not fully utilized. Therefore, in order to fully tap the use potential of shared electric bicycle systems in different regions and effectively evaluate the efficiency of vehicle use in different time and space in urban areas, the current situation needs to be improved urgently.

[0003] Although existing technologies have been able to partially solve this problem, there are still some shortcomings:

[0004] First, existing methods are usually based on hypothetical data or small sample survey data, which lack the reflection of the actual operation situation in the current city or have accidental bias, and are far from being representative of the use of shared electric bicycles in the region;

[0005] Secondly, most of the existing methods for calculating utilization efficiency are based on the number of vehicles in a region, without considering the error caused by vehicles being abandoned, waiting for maintenance or other long-term parking;

[0006] Finally, there is spatial non-stationarity in the use of shared electric bicycles between different areas of the city. Existing methods fail to consider distinguishing spatial regions for measurement, or lack the process of identifying and aggregating areas with the same type of usage, resulting in misjudgment of regional anomalies. Summary of the invention

[0007] In order to solve the problems existing in the prior art, the present invention provides a method, system, device and storage medium for calculating the utilization efficiency of a shared electric bicycle system based on order data. The method is based on the deep mining and comprehensive analysis of the real large sample order data of shared electric bicycles, extracts the characteristics of riding time, parking time and riding distance of shared electric bicycles, and combines the time and space differences of the vehicles relative to the starting and ending points of the urban area, and finally proposes a calculation method for the regional similarity index and the regional vacancy rate index. It helps to realize the optimal clustering area division and time and space utilization efficiency calculation of the urban shared electric bicycle system, and also provides a reference basis for enterprise operations and government planning, solving the problems mentioned in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solution: a method for calculating the usage efficiency of a shared electric bicycle system based on order data, comprising the following steps:

[0009] S1. Build a shared electric bicycle system database, which includes shared electric bicycle order data and urban area geographic information data;

[0010] S2, feature extraction: Based on the shared electric bicycle order data, the riding time, parking time and riding distance of each record are extracted respectively;

[0011] S3, data cleaning: perform data cleaning on the database constructed in step S1, and delete the records with missing values, abnormal values, duplicate values, and records exceeding the study area and time interval in the database;

[0012] S4. Determination of the optimal size of urban areas: Based on the shared electric bicycle order data, the individual usage efficiency of each order record is used to calculate the regional similarity under different grid sizes, and the optimal grid size of the city is determined through the minimum regional similarity;

[0013] S5. Spatiotemporal efficiency calculation: Divide the area into sub-areas with the optimal grid size of the city, and obtain the distribution of the efficiency of shared electric bicycles in the urban sub-areas at different times and spaces.

[0014] Preferably, in step S1, the shared electric bicycle order data includes the following fields: vehicle ID, borrowing time, return time, borrowing longitude, borrowing latitude, return longitude, return latitude.

[0015] Preferably, in step S2, the riding time, parking time and riding distance of each record are extracted, and corresponding fields need to be added to the shared electric bicycle order record, wherein the method for extracting features is as follows:

[0016] Riding time: In the order record of the order data, the time interval from the time the vehicle is borrowed to the time it is returned is the riding time T. u ;

[0017] Parking time: Group the shared electric bicycle order data by the unique vehicle number and sort them in ascending order by the borrowing time. In the current order record, the starting parking time of the shared electric bicycle vehicle is the time interval from the time of returning the vehicle immediately before the last destination to the end of the current borrowing time; and the end parking time of the vehicle is the time interval from the time of returning the vehicle immediately before the next borrowing time from the destination. The calculation formula is as follows:

[0018]

[0019] Where, T f is the parking time of the shared electric bicycle, o represents the starting point, d represents the end point; t d(l) The return time of the shared electric bicycle order is recorded as l, t o(l+1) is the starting borrowing time of the next order record l+1 immediately adjacent to the shared electric bicycle order record l after grouping and sorting; similarly, t d(l-1) The destination return time of the last order record l-1 immediately adjacent to the shared electric bicycle order record l after grouping and sorting;

[0020] Riding distance: The Euclidean distance between the vehicle starting point and the destination in the order record of the order data.

[0021] Preferably, in step S4, the individual usage efficiency of the order record is calculated as follows:

[0022]

[0023]

[0024] Where NOR(l,o) is the starting point vacancy rate of order record l, and NOR(l,d) is the ending point vacancy rate of order record l, both of which are individual utilization efficiencies; T u (l) is the riding time of order record l.

[0025] Preferably, in step S4, the measuring of the regional similarity under different grid sizes and determining the optimal grid size of the city by the minimum regional similarity specifically includes: dividing the city according to different grid sizes, and obtaining the minimum regional similarity S under different grid size divisions by calculation, and the corresponding grid size is used as the optimal size, and the calculation method is as follows:

[0026]

[0027]

[0028] Where m is the total number of sub-regions after the study area is divided; w i is the area weight, only when the total number of records N of sub-area i as the starting point or end point i Greater than or equal to threshold N t When , the sub-area is considered to be a reasonable use area and is assigned a weight of 1, otherwise it is a noise area and is assigned a weight of 0; the threshold N t It is recommended to set it to 8 or more; std(NOR i ) is the variance of all individual vacancy rate values ​​NOR in sub-region i.

[0029] Preferably, in step S5, the utilization efficiency distribution of shared electric bicycles in the sub-region is to group and count the shared electric bicycles in different time intervals and spatial regions, and obtain the sum of the parking time ST in all the starting point records and the end point records in the sub-region under different time and space. f The total riding time ST u The ratio is recorded as the regional vacancy rate SNOR, and the calculation formula is as follows:

[0030]

[0031] Preferably, the order data and the riding status of the research sub-area are divided into starting point records and end point records, and the sum of the parking time in all starting point records and end point records in the sub-area ST f The total riding time ST u It means that within the set time interval [t, t+Δt], for any research sub-area, there is a unique set of shared electric bicycles B, which records the unique ID number b of the shared electric bicycles that have appeared in the time interval and area. n , its mathematical expression is as follows:

[0032] B=Set(b1,b2,…,b n )

[0033] Total riding time of shared electric bicycles ST u The total parking time is ST f The calculation formulas are as follows:

[0034] Total riding time ST u : In the order records of shared electric bicycles b in the given time interval [t, t+Δt] and the research sub-area R, the total riding time ST u The calculation formula for the shared electric bicycle riding time recorded at the starting point and the end point is as follows:

[0035]

[0036]

[0037] Where, T u(b,o) is the riding time of the shared electric bicycle b in the research sub-area R as the starting point. Similarly, T u(b,d) The riding time to the destination; |L b | is the total number of orders for shared electric bicycles b in the research sub-area R; L b It is the order set that falls into the time interval after sorting in the parking time extraction; t d(l) Record the return time of the shared electric bicycle order l; t o(l)The starting time of borrowing a shared electric bicycle in order record l;

[0038] Total parking time ST f : In the order records of shared electric bicycles b in the given time interval [t, t+Δt] and the research sub-area R, the total parking time ST f The calculation formula for the parking time of shared electric bicycles recorded at the starting point and the end point is as follows:

[0039]

[0040]

[0041] Where, T f(b,o) is the parking time of the shared electric bicycle b in the research sub-area R as the starting point, T f(b,d) is the parking time of the shared electric bicycle b as the destination in the study sub-area R.

[0042] On the other hand, in order to achieve the above-mentioned purpose, the present invention also provides the following technical solution: a system for calculating the utilization efficiency of a shared electric bicycle system based on order data, the system comprising:

[0043] Database construction module: used to build a shared electric bicycle system database, which includes shared electric bicycle order data and urban area geographic information data;

[0044] Feature extraction module: Based on the shared electric bicycle order data, the riding time, parking time and riding distance of each record are extracted respectively;

[0045] Data cleaning module: cleans the database constructed by the database construction module and deletes the records with missing values, abnormal values, duplicate values, and records exceeding the research area and time interval;

[0046] Module for determining the optimal size of urban areas: Based on the shared electric bicycle order data, the individual usage efficiency of each order record is used to measure the regional similarity under different grid sizes, and the optimal grid size of the city is determined through the minimum regional similarity;

[0047] Efficiency spatiotemporal measurement module: Divide the area into sub-areas with the optimal grid size of the city, and obtain the distribution of shared electric bicycle usage efficiency in urban sub-areas at different times and spaces.

[0048] On the other hand, to achieve the above-mentioned purpose, the present invention also provides the following technical solution: an electronic device, the electronic device comprising: a processor; and a memory for storing one or more programs;

[0049] When the one or more programs are executed by the processor, the processor executes the method for calculating the usage efficiency of the shared electric bicycle system based on order data.

[0050] On the other hand, to achieve the above-mentioned purpose, the present invention also provides the following technical solution: a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for calculating the usage efficiency of a shared electric bicycle system based on order data.

[0051] The beneficial effects of the present invention are: 1) Based on the deep mining and utilization of the real large sample order data, the present invention comprehensively considers the use characteristics of shared electric bicycles and the spatial and temporal differences of urban areas, and realizes the optimal division of urban shared electric bicycle system regions and the calculation of spatial and temporal use efficiency. The method of the present invention uses the large sample shared electric bicycle order data actually generated in real life, which truly reflects the operation of the vehicle in the actual life of the city, making the results more in line with the actual situation; 2) The method of the present invention fully extracts the use characteristics of the shared electric bicycle system, and uses the regional vehicle riding time and parking time to calculate the use efficiency, which is conducive to quickly grasping the system usage in different spatial and temporal regions, and provides a reference for corporate operations and government planning; 3) The method of the present invention comprehensively considers the differences in the shared electric bicycle system in different areas of the city, and achieves more accurate and reasonable regional division by calculating the regional similarity method under grids of different sizes. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the steps of the method of the present invention;

[0053] Figure 2 is a curve showing the variation of the similarity of urban areas in a city at different grid sizes in an embodiment of the present invention;

[0054] Figure 3 This is a spatiotemporal distribution diagram of the vacancy rate of shared electric bicycles in a certain city in an embodiment of the present invention;

[0055] Figure 4 It is a schematic diagram of a system module for calculating the usage efficiency of a shared electric bicycle system based on order data in an embodiment of the present invention;

[0056] Figure 5 This is a schematic diagram of the device structure in an embodiment of the present invention;

[0057] In the figure, 110 - database construction module; 120 - feature extraction module; 130 - data cleaning module; 140 - urban area optimal size determination module; 150 - efficiency spatiotemporal measurement module; 210 - processor; 220 - storage. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] Example

[0060] The method of the present invention is actually implemented in combination with a shared electric bicycle system actually operated in a certain city. As of the end of 2022, the city had a total of 122,000 shared electric bicycles in operation, and the operation scope covered all main urban areas. This example collected the shared electric bicycle order data of a certain operating company in the city from April 20, 2022 to May 20, 2022, involving 28,667 shared electric bicycles and a total of 2,701,277 order records. In the example implementation of the method for calculating the utilization efficiency of a shared electric bicycle system based on order data of the present invention, the process is as follows Figure 1 As shown, specifically including the following:

[0061] (1) Building a shared electric bicycle system database

[0062] Construct a shared electric bicycle system database, which includes shared electric bicycle order data and research area geographic information data. Among them, a complete shared electric bicycle order record collected in a certain city includes 8 fields: vehicle ID, user ID, borrowing time, return time, borrowing longitude, borrowing latitude, return longitude, return latitude. Among them, longitude and latitude are converted into projection coordinate system. The details are shown in Table 1.

[0063] Table 1 Example of shared electric bicycle order data table (partial)

[0064]

[0065] Table 1 continued

[0066]

[0067] (2) Feature extraction: Based on the shared electric bicycle order data in step (1), the riding time, parking time and riding distance of each record are calculated and extracted respectively;

[0068] (2.1) Riding time: In the shared electric bicycle order data table example (part) in Table 1, the starting borrowing time of the second shared electric bicycle order record is "2022 / 5 / 8 08:39:21", and the end return time is "2022 / 5 / 8 08:52:43", so the riding time is 13.37 minutes.

[0069] (2.2) Parking time: In the example (part) of the shared electric bicycle order data table in Table 1, the first order record and the second order record are two orders with adjacent vehicles after sorting. The first destination return time is "2022 / 5 / 8 08:31:06", and the second starting borrowing time is "2022 / 5 / 8 08:39:21". Therefore, the destination parking time of the first order record and the starting parking time of the second order record are both 8.25 minutes.

[0070] (2.3) Riding distance: In Table 1, Example (part) of shared electric bicycle order data, the starting longitude, starting latitude, end longitude, and end latitude of the second shared electric bicycle order record after vehicle projection are 298592.9671 meters, 2781374.70 meters, 295305.1136 meters, and 2777861.705 meters, respectively. The calculated Euclidean distance of the riding distance is 4811.561 meters.

[0071] (3) Data cleaning: Perform data cleaning on the database constructed in step (1). Delete the order records with missing values, abnormal values, duplicate values, and those exceeding the study area and time interval in the database fields; delete the order records where the vehicle is in riding or parked status at the same time; delete the order records of shared electric bicycles with a riding time of less than 30 seconds or more than 2 hours; delete the order records of shared electric bicycles with a parking time of less than 0 seconds and more than 1256.61 minutes (the 95th percentile of parking time); delete the order records of shared electric bicycles with a riding distance of less than 100 meters or more than 10 kilometers. After data cleaning, there are 2490945 shared electric bicycle order records remaining, accounting for 92.21% of the total records. The remaining order records can support the subsequent steps, and the data cleaning process is acceptable.

[0072] (4) Calculation of individual usage efficiency: The vacancy rate of shared electric bicycle order data is calculated item by item, and the calculated vacancy rate is divided into the starting point vacancy rate and the end point vacancy rate according to the different time and space locations involved in the order data, as shown in Table 2.

[0073] (5) Urban area division and indicator calculation: The study area is divided into grid sizes ranging from 100 meters to 2000 meters at intervals of 100 meters. The divided sub-areas are numbered, and then spatially connected with the sub-areas based on the latitude and longitude positions of the starting and ending points in the shared electric bicycle order data, and the "starting point ID" and "end point ID" fields are added to the order data. Furthermore, the vacancy rate values ​​of all individual order records falling into the different divided sub-areas are matched, and their variance disturbance is calculated. Finally, all areas with less than 8 records in all sub-areas are eliminated, and the mean of the variance disturbance in the remaining areas is calculated, that is, the regional similarity.

[0074] After iteratively calculating the regional similarity for different grid sizes, the regional similarity change curve of a certain city is obtained as follows: Figure 2 As shown in the figure, the area similarity value corresponding to 800×800 meters is the smallest, so the 800×800 meter grid is selected as the optimal size of the urban area;

[0075] (6) Efficiency spatiotemporal calculation: The study area is divided into 800×800 m grids, and 1 hour is set as the time interval Δt. The order records in the study sub-areas under different time and space are counted respectively, and the total parking time at the starting point and the end point and the corresponding riding time at the starting point and the end point are calculated to obtain the vacancy rate of the area in this period. The following Table 2 gives the total order data table of area 1876 from 2022 / 04 / 2016:00:00 to 2022 / 04 / 2017:00:00, from which it can be obtained that the total parking time at the starting point is 2007.972 minutes, the total riding time at the starting point is 91.765 minutes, the total parking time at the end point is 450.415 minutes, and the total riding time at the end point is 84.952 minutes. The calculated vacancy rate of area 1876 is 13.911.

[0076] Table 2: Order data update table within the set time of area 1876

[0077]

[0078]

[0079] Table 2 continued

[0080]

[0081] Table 2 continued

[0082]

[0083] Furthermore, in order to more intuitively demonstrate the efficiency of shared electric bicycles in different areas of the city, this example also uses ArcMap 10.8 software to generate heat maps of the efficiency of the morning peak (7:00 to 9:00) and evening peak (17:00 to 19:00). Combined with the fact that the larger the regional vacancy rate value, the lower the regional utilization efficiency, it can be clearly found that: the utilization efficiency of shared electric bicycles in cities at different times and spaces varies significantly. Whether on weekdays or non-working days, the evening peak efficiency of shared electric bicycles in a certain city is much higher than the morning peak, and the city center is much higher than the city suburbs. The north, northwest and southeast are all areas where shared electric bicycles are more fully used. For example Figure 3 shown.

[0084] The method of the present invention is based on a large sample of order data of shared electric bicycles, and comprehensively considers the vehicle usage characteristics and regional spatiotemporal differences, realizes the optimal clustering area division of the urban shared electric bicycle system, and successfully completes the calculation of the spatiotemporal utilization efficiency of vehicles in different regions. The measurement and identification process of the present invention is simple, easy to operate and perform, the data results are more real and reliable, and have good practicality, accuracy and scalability.

[0085] Based on the same inventive concept as the above method embodiment, the present application embodiment also provides a system for calculating the efficiency of a shared electric bicycle system based on order data, which can implement the functions provided by the above method embodiment, such as Figure 4 As shown, the system includes the following modules:

[0086] Database construction module 110: used to construct a shared electric bicycle system database, the database includes shared electric bicycle order data and urban area geographic information data;

[0087] Feature extraction module 120: based on the shared electric bicycle order data, extract the riding time, parking time and riding distance of each record respectively;

[0088] Data cleaning module 130: performs data cleaning on the database constructed by database construction module 110, and deletes records with missing values, abnormal values, duplicate values, and records exceeding the research area and time interval in the database;

[0089] The city area optimal size determination module 140: based on the shared electric bicycle order data, using the individual usage efficiency of each order record, calculates the regional similarity under different grid sizes, and determines the city's optimal grid size through the minimum regional similarity;

[0090] The efficiency spatiotemporal calculation module 150 divides the area into sub-areas with the optimal grid size of the city, and obtains the distribution of the utilization efficiency of shared electric bicycles in the sub-areas of the city at different times and spaces.

[0091] Based on the same inventive concept as the above method embodiment, the present application embodiment also provides an electronic device, such as Figure 5 As shown, the device includes: a processor 210; and a memory 220, for storing one or more programs;

[0092] When the one or more programs are executed by the processor 210, the processor executes the method for calculating the usage efficiency of the shared electric bicycle system based on order data.

[0093] The method for calculating the utilization efficiency of the shared electric bicycle system based on order data specifically includes the following:

[0094] Build a shared electric bicycle system database, which includes shared electric bicycle order data and urban area geographic information data;

[0095] Feature extraction: Based on the shared electric bicycle order data, the riding time, parking time and riding distance of each record are extracted respectively;

[0096] Data cleaning: Clean the constructed database and delete the records with missing values, abnormal values, duplicate values, and records that exceed the research area and time interval;

[0097] Determination of the optimal size of urban areas: Based on the shared electric bicycle order data, the individual usage efficiency of each order record is used to measure the regional similarity under different grid sizes, and the optimal grid size of the city is determined through the minimum regional similarity;

[0098] Spatiotemporal efficiency measurement: The area is divided into sub-areas using the optimal grid size of the city, and the distribution of shared electric bicycle usage efficiency in urban sub-areas at different times and spaces is obtained.

[0099] Based on the same inventive concept as the above-mentioned method embodiment, the embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor 210, the method for calculating the usage efficiency of the shared electric bicycle system based on order data is implemented.

[0100] The method for calculating the utilization efficiency of the shared electric bicycle system based on order data specifically includes the following:

[0101] Build a shared electric bicycle system database, which includes shared electric bicycle order data and urban area geographic information data;

[0102] Feature extraction: Based on the shared electric bicycle order data, the riding time, parking time and riding distance of each record are extracted respectively;

[0103] Data cleaning: Clean the constructed database and delete the records with missing values, abnormal values, duplicate values, and records that exceed the research area and time interval;

[0104] Determination of the optimal size of urban areas: Based on the shared electric bicycle order data, the individual usage efficiency of each order record is used to measure the regional similarity under different grid sizes, and the optimal grid size of the city is determined through the minimum regional similarity;

[0105] Spatiotemporal efficiency measurement: The area is divided into sub-areas using the optimal grid size of the city, and the distribution of shared electric bicycle usage efficiency in urban sub-areas at different times and spaces is obtained.

[0106] The present invention plays an important role in fusing and processing big data samples in real life, quickly identifying hot spots for shared electric bicycle use, and improving the efficiency of spatiotemporal use. It also provides a reference for corporate operations and government planning.

[0107] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for calculating the utilization efficiency of a shared electric bicycle system based on order data, characterized in that: The steps include: S1. Build a shared electric bicycle system database, which includes shared electric bicycle order data and urban area geographic information data; S2, feature extraction: Based on the shared electric bicycle order data, the riding time, parking time and riding distance of each record are extracted respectively; S3, data cleaning: perform data cleaning on the database constructed in step S1, and delete the records with missing values, abnormal values, duplicate values, and records exceeding the study area and time interval in the database; S4. Determination of the optimal size of urban areas: Based on the shared electric bicycle order data, the individual usage efficiency of each order record is used to calculate the regional similarity under different grid sizes, and the optimal grid size of the city is determined through the minimum regional similarity; The method of measuring the regional similarity under different grid sizes and determining the optimal grid size of the city through the minimum regional similarity specifically includes: dividing the city according to different grid sizes, and calculating to obtain the minimum regional similarity S under different grid size divisions, and taking the corresponding grid size as the optimal size, and the calculation method is as follows: Where m is the total number of sub-regions after the study area is divided; w i is the area weight, only when the total number of records N of sub-area i as the starting point or end point i Greater than or equal to threshold N t When , the sub-area is considered to be a reasonable use area and is assigned a weight of 1, otherwise it is a noise area and is assigned a weight of 0; std(NOR i ) is the variance of all individual vacancy rate values ​​NOR in sub-region i; S5. Efficiency spatiotemporal calculation: Divide the area into sub-areas using the optimal grid size of the city, and obtain the distribution of the efficiency of shared electric bicycles in the city sub-areas at different times and spaces; In step S5, the utilization efficiency distribution of shared electric bicycles in the sub-region is to group and count the shared electric bicycles in different time intervals and spatial regions, and obtain the sum of the parking time ST of all starting point records and end point records in the sub-region under different time and space. f The total riding time ST u The ratio is recorded as the regional vacancy rate SNOR, and the calculation formula is as follows: The sum of the stop times in all the starting and ending records in the sub-area, ST f The total riding time ST u It means that within the set time interval [t, t+Δt], for any research sub-area, there is a unique set of shared electric bicycles B, which records the unique ID number b of the shared electric bicycles that appeared in the time interval and area. n , its mathematical expression is as follows: B=Set(b1,b2,…,b n ) Total riding time of shared electric bicycles ST u The total parking time ST f The calculation formulas are as follows: In the given time interval [t, t+Δt] and the order records of shared electric bicycles b in the research sub-area R, the total riding time ST u The calculation formula for the shared electric bicycle riding time recorded at the starting point and the end point is as follows: Where, T u(b,o) is the riding time of the shared electric bicycle b in the research sub-area R as the starting point. Similarly, T u(b,d) The riding time to the destination; |L b | is the total number of order records for shared electric bicycles b in the research sub-area R; L b It is the order set that falls into the time interval after sorting in the parking time extraction; t d(l) Record the return time of the shared electric bicycle order l; t o(l) The starting time of the shared electric bicycle order record l; o represents the starting point, and d represents the end point; In the given time interval [t, t+Δt] and the order records of shared electric bicycles b in the research sub-area R, the total parking time ST f The calculation formula for the parking time of shared electric bicycles recorded at the starting point and the end point is as follows: Where, T f(b,o) is the parking time of the shared electric bicycle b in the research sub-area R as the starting point, T f(b,d) is the parking time of the shared electric bicycle b as the destination in the research sub-area R; l+1 is the next order record adjacent to the shared electric bicycle order record l after group sorting; l-1 is the previous order record adjacent to the shared electric bicycle order record l after group sorting.

2. The method for calculating the utilization efficiency of a shared electric bicycle system based on order data according to claim 1 is characterized in that: In step S1, the shared electric bicycle order data includes the following fields: vehicle ID, borrowing time, return time, borrowing longitude, borrowing latitude, return longitude, return latitude.

3. The method for calculating the utilization efficiency of a shared electric bicycle system based on order data according to claim 1 is characterized in that: In step S2, the riding time, parking time and riding distance of each record are extracted. Corresponding fields need to be added to the shared electric bicycle order record. The method for extracting features is as follows: Riding time: In the order record of the order data, the time interval from the time the vehicle is borrowed to the time it is returned is the riding time T. u ; Parking time: Group the shared electric bicycle order data by vehicle ID number and sort them in ascending order by the borrowing time. In the current order record, the starting parking time of the shared electric bicycle vehicle is the time interval from the time of returning the vehicle immediately before the last destination to the end of the current borrowing time; and the end parking time of the vehicle is the time interval from the time of returning the vehicle immediately before the next borrowing time from the destination. The calculation formula is as follows: Where, T f is the parking time of the shared electric bicycle, o represents the starting point, d represents the end point; t d(l) The return time of the shared electric bicycle order is recorded as l, t o(l+1) is the starting borrowing time of the next order record l+1 immediately adjacent to the shared electric bicycle order record l after grouping and sorting; similarly, t d(l-1) The destination return time of the last order record l-1 immediately adjacent to the shared electric bicycle order record l after grouping and sorting; Riding distance: The Euclidean distance between the vehicle starting point and the destination in the order record of the order data.

4. The method for calculating the utilization efficiency of a shared electric bicycle system based on order data according to claim 1 is characterized in that: In step S4, the individual usage efficiency of the order record is calculated as follows: Where NOR(l,o) is the starting point vacancy rate of order record l, and NOR(l,d) is the ending point vacancy rate of order record l, both of which are individual utilization efficiencies; T u (l) is the riding time of order record l.

5. A system according to any one of claims 1 to 4, wherein the method for calculating the use efficiency of a shared electric bicycle system based on order data is characterized in that: The system comprises the following: Database construction module (110): used to construct a shared electric bicycle system database, the database including shared electric bicycle order data and urban area geographic information data; Feature extraction module (120): based on the shared electric bicycle order data, extracting the riding time, parking time and riding distance of each record respectively; Data cleaning module (130): performs data cleaning on the database constructed by the database construction module (110), and deletes the records with missing values, abnormal values, duplicate values, and records exceeding the research area and time interval in the database; The module for determining the optimal size of urban areas (140) is based on the shared electric bicycle order data, uses the individual usage efficiency of each order record, measures the regional similarity under different grid sizes, and determines the optimal grid size of the city through the minimum regional similarity; The efficiency time-space calculation module (150) is to divide the area into sub-areas with the optimal grid size of the city, and obtain the distribution of the efficiency of shared electric bicycles in the city sub-areas under different time and space.

6. An electronic device, characterized in that: The electronic device comprises: a processor (210); and a memory (220) for storing one or more programs; When the one or more programs are executed by the processor (210), the processor executes the method for calculating the usage efficiency of a shared electric bicycle system based on order data as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by the processor (210), the method for calculating the utilization efficiency of a shared electric bicycle system based on order data as described in any one of claims 1 to 4 is implemented.

Citation Information

Patent Citations

  • A shared bicycle borrowing, returning and parking space-time distribution visualization method based on OD data

    CN109903125A