Shared bicycle and user access rule analysis method and system

Abstract

The invention discloses a shared bicycle and user access rule analysis method and system, and relates to the field of traffic data. According to the method, the access rules of the shared bicycles and the specific places of the shared bicycle users or the access rules of the activity areas in different time periods can be obtained by analyzing the past shared bicycle data, and the method can be widely applied to shared bicycle flow rule analysis of different cities; the space-time distribution rule of the shared bicycles and the inflow and outflow of the users of the shared bicycles at various places or active areas in a city can be obtained; the relationship between the input and the output of the shared bicycles and the users of the shared bicycles in different places or activity areas and different factors can be obtained; the rule of the number and frequency of access places of a single shared bicycle or a single user can be obtained. According to the method and the system, the access rules of the shared bicycles and the users in different areas and time can be effectively analyzed.

Description

Technical Field

[0001] The present invention relates to the field of traffic data, and in particular to a method and system for analyzing shared bicycles and user access rules. Background Art

[0002] In the era of the sharing economy, the use of shared bikes instead of taxis or privately owned cars for short-distance transportation has potentially far-reaching benefits for society. First, the rapid growth of cities and populations has led to a rapid increase in traffic volume, congestion, and energy consumption. The current transportation system is already significantly challenged by these rapidly growing demands. Second, air pollution and its impact on public health have become a growing concern worldwide. The combustion of fossil fuels leads to large amounts of greenhouse gases being emitted into the atmosphere, accelerating global warming and causing many environmental consequences, such as rising sea levels or increased respiratory diseases. Therefore, reducing driving and promoting the use of shared bike services as a convenient and cost-effective mode of transportation may help alleviate these pressing issues in cities. Such services have proliferated around the world in recent years.

[0003] Previous methods for analyzing the travel patterns of shared bicycles were mainly focused on the overall scope of the city, and there was no method for analyzing specific locations and active areas at different times. In fact, the distribution patterns of various locations are different. In addition, the distribution pattern of shared bicycles themselves is different from the distribution pattern of shared bicycle users. Both of these data can help with the design of shared bicycle systems and urban planning. In addition, in the past, there was a lack of simultaneous analysis of the relationship between traffic and multiple factors in shared bicycles, which is also an important part of the rules of shared bicycles and can reflect the visit rules of shared bicycles in a more in-depth manner. Finally, shared bicycles also lack analysis of changes in the number of visited locations and the distribution of visit frequencies at various locations. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention obtains the spatiotemporal distribution patterns of the inflow (or outflow) of shared bicycles and shared bicycle users in various active areas or locations in different time periods based on past shared bicycle data; analyzes the relationship between the inflow and outflow of shared bicycles and their users and the frequency, travel distance and turning radius; and analyzes the patterns of the number and frequency of locations visited by a single shared bicycle or a single user.

[0005] A first aspect of the present invention provides a method for analyzing shared bicycles and user access rules, comprising the following steps:

[0006] Step 1: Collect and pre-process the shared bicycle travel data of the target city to obtain the pre-processed shared bicycle travel data; the shared bicycle travel data includes shared bicycle order data and its corresponding shared bicycle travel indicators;

[0007] Step 1.1: Collect the shared bicycle order data within a certain time range in the target city, including shared bicycle ID, user ID, starting point coordinates, ending point coordinates, start time and end time;

[0008] Step 1.2: According to the coordinates of the starting point, the coordinates of the ending point, the starting time and the ending time in the shared bicycle order data, the shared bicycle travel indicators are obtained, including the travel distance, the travel time and the travel angle; the travel angle is the angle formed by the vector from the starting point to the ending point and the positive direction of the x-axis in the city coordinate system, and the city coordinate system takes the east as the x-axis and the north as the y-axis;

[0009] Step 1.3: Use the shared bicycle order data obtained in step 1.1 and the shared bicycle travel index obtained in step 1.2 as shared bicycle travel data;

[0010] Step 1.4: preprocessing the shared bicycle travel data to obtain preprocessed shared bicycle travel data;

[0011] The preprocessing is: judging whether the shared bicycle travel data is abnormal according to the travel distance and travel time, and removing the shared bicycle travel data with abnormalities, specifically, removing the shared bicycle travel data with a travel distance less than a set first threshold and a travel distance greater than a set second threshold; removing the shared bicycle travel data with a travel time less than a set third threshold and a travel time greater than a set fourth threshold;

[0012] Step 2: Divide the target city into grids and determine the shared bicycle activity level of each grid based on the preprocessed shared bicycle travel data;

[0013] Step 2.1: Grid the map of the target city to obtain several grids, number each grid, and project the starting point coordinates and the ending point coordinates of the pre-processed shared bicycle travel data into the grids;

[0014] Step 2.2: According to the shared bicycle travel data, obtain the flow rate A(j) of the shared bicycles in each grid, and normalize the flow rate A(j) of the shared bicycles in each grid, where j is the number of the grid; the flow rate is the inflow or outflow, the inflow is the number of trips with the end point in the same grid within the set time range, and the outflow is the number of trips with the starting point in the same grid within the set time range;

[0015] Step 2.3: Sort all grids in ascending order according to the normalized shared bicycle flow ρ(j) of each grid, calculate the location score and cumulative flow score of each grid, and draw the cumulative distribution curve of shared bicycle flow based on the location score and cumulative flow score of each grid;

[0016] In the cumulative distribution curve of the shared bicycle flow, the x-axis represents the position score of the sorted grid, and the y-axis represents the corresponding cumulative flow score F(k);

[0017] The position scores are:

[0018] R(k)=k / n

[0019] Where R(k) is the position score of the kth grid after sorting, k is the number of the sorted grid, and n is the number of grids with shared bicycles flowing in or out;

[0020] The cumulative flow fraction is:

[0021]

[0022] Among them, F(k) is the cumulative flow score of the kth grid after sorting, and ρ(l) is the normalized shared bicycle flow of the lth grid after sorting;

[0023] Step 2.4: Determine a cutoff point of the shared bicycle activity level on the cumulative distribution curve of shared bicycle flow, and divide the grids whose cumulative flow scores are greater than the cutoff point of the shared bicycle activity level into a shared bicycle activity level;

[0024] The method for determining a dividing point of a shared bicycle activity level is as follows: calculating the derivative of the cumulative distribution curve of the shared bicycle flow at (1,1), thereby obtaining the tangent line of the cumulative distribution curve of the shared bicycle flow at (1,1), and then calculating the horizontal coordinate of the intersection of the tangent line of the cumulative distribution curve of the shared bicycle flow at (1,1) and the x-axis, which is the dividing point of the shared bicycle activity level;

[0025] Step 2.5: Remove the cumulative flow scores that are greater than the cutoff point of the current shared bicycle activity level, and redraw the cumulative distribution curve of shared bicycle flow according to the method of step 2.3, and then follow step 2.4 again to obtain the grid belonging to a shared bicycle activity level;

[0026] Step 2.6: Repeat step 2.5 until a set number of shared bicycle activity levels are obtained, and then determine the grids belonging to each shared bicycle activity level;

[0027] Furthermore, in order to divide the shared bicycle activity level more finely, when obtaining the shared bicycle flow of the jth grid, the shared bicycle flow in the morning and evening peak hours on weekdays, other time periods on weekdays except the morning and evening peak hours, and weekends and holidays are obtained respectively, and then the grids of different shared bicycle activity levels in these three time periods are obtained;

[0028] Step 3: Analyze the temporal and spatial distribution of shared bicycles or users in each city area based on the level of shared bicycle activity;

[0029] Step 3.1: Filter the shared bicycle travel data according to the urban area to be analyzed; the urban area to be analyzed is all grids or a certain grid included in a certain shared bicycle activity level;

[0030] The method for filtering shared bicycle travel data is: filtering shared bicycle travel data with a starting point or an end point in this city area;

[0031] Step 3.2: Group the shared bicycle travel data according to the shared bicycle ID or user ID, sort the end point coordinates or the start point coordinates in all the shared bicycle travel data of a shared bicycle or a user by time, obtain the travel trajectory data of the shared bicycle or user, and calculate the turning radius corresponding to each shared bicycle or user according to the travel trajectory data;

[0032]

[0033] Among them, α represents a shared bicycle or user, represents the turning radius of a shared bicycle or user, (x i ,y i ) represents the coordinates of the i-th position passed by the shared bicycle or the user’s corresponding travel trajectory data, n α is the number of locations in the travel trajectory data of a shared bicycle or user α, (x c ,y c ) represents the centroid coordinates of the travel trajectory data of the shared bicycle or user α;

[0034] Step 3.3: Fit the probability distributions of the four shared bicycle travel indicators of travel distance, turning radius, travel time and travel angle in the screened shared bicycle travel data respectively, and obtain several different probability distribution functions and their corresponding Akaike information criterion AIC for each shared bicycle travel indicator. For each shared bicycle travel indicator, select the probability distribution function with the smallest Akaike information criterion AIC as the optimal probability distribution function of the shared bicycle travel indicator, and then obtain the optimal probability distribution functions of travel distance, turning radius, travel time and travel angle; the horizontal axis of the probability distribution function is the value of the shared bicycle travel indicator, and the vertical axis is the probability;

[0035] Step 4: Analyze the flow patterns of shared bicycles or users in each city area, including the relationship between flow and travel distance, turning radius and travel frequency;

[0036] Step 4.1: Select the city area to be analyzed, filter the shared bicycle travel data with the end point or the start point in the city area, count the number of times the same shared bicycle or the same user appears, and convert the number into frequency to obtain the travel frequency of each shared bicycle or user;

[0037] Step 4.2: Further filter out the shared bicycle travel data of shared bicycles or users within the set travel frequency range from the shared bicycle travel data filtered in step 4.1, and draw a graph to obtain the functional relationship between the flow rate and the travel distance and the turning radius;

[0038] Step 4.3: Further filter out the shared bicycle travel data of shared bicycles or users within the set travel distance or turning radius from the shared bicycle travel data filtered in step 4.1, and draw a graph to obtain the functional relationship between flow and travel frequency;

[0039] Step 5: Analyze the entry and exit patterns of a single shared bicycle or a single user;

[0040] Step 5.1: Count the number of grids q that flow into or out of the same shared bicycle or the same user as the number of trips m increases, fit the functional relationship between the number of trips m and the number of grids q that flow into or out of the city, and obtain the expression for the number of grids that the shared bicycle or user flows into or out of: q = g(m), where g(m) is the functional expression for the number of trips m. Then, the probability that the shared bicycle or user goes to a city grid that has not been reached during the mth trip is obtained:

[0041]

[0042] Among them, P a The probability that a shared bicycle or user goes to a grid that has not been reached before during the mth trip;

[0043] Step 5.2: Convert the number of times the same shared bicycle or the same user flows into or out of each grid into frequency, and obtain the frequency of visit or leave of each grid f. Statistically calculate the relationship between the frequency of visit or leave of each grid and the ranking K of the traffic of the shared bicycles in the grid: f = h(K), where h(K) is a function expression of the ranking K of the traffic of the grid shared bicycles, which represents the distribution law of the number of times any selected shared bicycle or user flows into or out of each grid.

[0044] A second aspect of the present invention provides a shared bicycle and user access regularity analysis system, which is used to implement a shared bicycle and user access regularity analysis method, including:

[0045] A shared bicycle travel data acquisition module is used to collect shared bicycle travel data in a target city, wherein the shared bicycle travel data includes shared bicycle order data and its corresponding shared bicycle travel indicators;

[0046] A data preprocessing module is used to preprocess the collected shared bicycle travel data of the target city to obtain the preprocessed shared bicycle travel data;

[0047] The shared bicycle activity level classification module is used to grid the map of the target city to obtain a number of grids, and then determine the shared bicycle activity level of each grid, thereby obtaining grids belonging to different shared bicycle activity levels;

[0048] The spatiotemporal distribution law analysis module is used to analyze the spatiotemporal distribution law of shared bicycles or users in urban areas according to the activity level of shared bicycles;

[0049] The flow pattern analysis module is used to analyze the relationship between the flow of shared bicycles or users in the urban area and the travel distance, turning radius and travel frequency, and obtain the flow pattern of shared bicycles in the urban area;

[0050] The location entry and exit pattern analysis module is used to analyze the location entry and exit patterns of a single shared bicycle or a single user.

[0051] The third aspect of the present invention provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for analyzing the regularity of shared bicycles and user access are executed;

[0052] A fourth aspect of the present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the method for analyzing the shared bicycle and user access patterns are executed.

[0053] The shared bicycle and user access regularity analysis method proposed in the present invention has the following beneficial effects:

[0054] Obtaining the activity areas of various locations and activity zones in the city, as well as the activity zones during the morning and evening rush hours on weekdays, other time periods on weekdays, and weekends and holidays, can lay the foundation for a more comprehensive analysis of the access patterns of shared bicycles and users at different locations and times. By analyzing both the shared bicycles themselves and the shared bicycle users, a more comprehensive access pattern can be obtained. Both data can help the shared bicycle system and urban planning. The analysis of the relationship between the inflow and outflow of shared bicycles and their users and various factors, as well as the analysis of the number and frequency of locations visited by a single shared bicycle or a single user, can more deeply reflect the access patterns of shared bicycles. These contents can provide more targeted assistance for shared bicycle scheduling and urban transportation planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A flow chart of a method for analyzing a shared bicycle and user access rules provided by an embodiment of the present invention;

[0056] Figure 2 This is a cumulative distribution diagram of shared bicycle traffic provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The technical solution in this application will be described below in conjunction with the accompanying drawings.

[0058] like Figure 1 As shown, a method for analyzing shared bicycles and user access rules provided in an embodiment of the present application includes the following steps:

[0059] Step 1: Collect and pre-process the shared bicycle travel data of the target city to obtain the pre-processed shared bicycle travel data; the shared bicycle travel data includes shared bicycle order data and its corresponding shared bicycle travel indicators;

[0060] Step 1.1: Collect the shared bicycle order data within a certain time range in the target city, including shared bicycle ID, user ID, starting point coordinates, ending point coordinates, start time and end time;

[0061] In this implementation, the shared bicycle order data comes from the shared bicycle operator records;

[0062] Step 1.2: According to the coordinates of the starting point, the coordinates of the ending point, the starting time and the ending time in the shared bicycle order data, the shared bicycle travel indicators are obtained, including the travel distance, the travel time and the travel angle; the travel angle is the angle formed by the vector from the starting point to the ending point and the positive direction of the x-axis in the city coordinate system, and the city coordinate system takes the east as the x-axis and the north as the y-axis;

[0063] Step 1.3: Use the shared bicycle order data obtained in step 1.1 and the shared bicycle travel index obtained in step 1.2 as shared bicycle travel data;

[0064] Step 1.4: preprocessing the shared bicycle travel data to obtain preprocessed shared bicycle travel data;

[0065] The preprocessing is: judging whether the shared bicycle travel data is abnormal according to the travel distance and travel time, and removing the shared bicycle travel data with abnormalities, specifically, removing the shared bicycle travel data with a travel distance less than a set first threshold and a travel distance greater than a set second threshold; removing the shared bicycle travel data with a travel time less than a set third threshold and a travel time greater than a set fourth threshold;

[0066] In this implementation, a travel distance of less than 100 meters (first threshold) or greater than 100 kilometers (second threshold) is considered abnormal, and a travel time of less than 2 minutes (third threshold) or greater than 8 hours (fourth threshold) is considered abnormal;

[0067] Step 2: Divide the target city into grids and determine the shared bicycle activity level of each grid based on the preprocessed shared bicycle travel data;

[0068] Step 2.1: Grid the map of the target city to obtain several grids, number each grid, and project the starting point coordinates and the ending point coordinates of the pre-processed shared bicycle travel data into the grids;

[0069] In this implementation, 500m*500m is selected as the grid size;

[0070] Step 2.2: According to the shared bicycle travel data, obtain the flow rate A(j) of the shared bicycles in each grid, and normalize the flow rate A(j) of the shared bicycles in each grid, where j is the number of the grid; the flow rate is the inflow or outflow, the inflow is the number of trips with the end point in the same grid within the set time range, and the outflow is the number of trips with the starting point in the same grid within the set time range;

[0071] The normalization method is:

[0072]

[0073] Where ρ(j) is the normalized shared bicycle flow rate of the jth grid, and n is the number of grids with shared bicycles flowing in or out;

[0074] In this implementation, the time range is set to one year, and the inflow (or outflow) of shared bicycles in each grid in one year is divided by the total inflow (or outflow) of shared bicycles in the city in one year for normalization;

[0075] Step 2.3: Sort all grids in ascending order according to the normalized shared bicycle flow ρ(j) of each grid, calculate the location score and cumulative flow score of each grid, and draw the cumulative distribution curve of shared bicycle flow based on the location score and cumulative flow score of each grid;

[0076] like Figure 2 As shown, in the cumulative distribution curve of the shared bicycle flow, the x-axis represents the position score of the sorted grid, and the y-axis represents the corresponding cumulative flow score F(k);

[0077] The position scores are:

[0078] R(k)=k / n

[0079] Where R(k) is the position score of the kth grid after sorting, k is the number of the sorted grid, and n is the number of grids with shared bicycles flowing in or out;

[0080] The cumulative flow fraction is:

[0081]

[0082] Among them, F(k) is the cumulative flow score of the kth grid after sorting, and ρ(l) is the normalized shared bicycle flow of the lth grid after sorting;

[0083] Step 2.4: Determine a cutoff point of the shared bicycle activity level on the cumulative distribution curve of shared bicycle flow, and divide the grids whose cumulative flow scores are greater than the cutoff point of the shared bicycle activity level into a shared bicycle activity level;

[0084] The method for determining a dividing point of a shared bicycle activity level is as follows: calculating the derivative of the cumulative distribution curve of the shared bicycle flow at (1,1), thereby obtaining the tangent line of the cumulative distribution curve of the shared bicycle flow at (1,1), and then calculating the horizontal coordinate of the intersection of the tangent line of the cumulative distribution curve of the shared bicycle flow at (1,1) and the x-axis, which is the dividing point of the shared bicycle activity level;

[0085] Step 2.5: Remove the cumulative flow scores that are greater than the cutoff point of the current shared bicycle activity level, and redraw the cumulative distribution curve of shared bicycle flow according to the method of step 2.3, and then follow step 2.4 again to obtain the grid belonging to a shared bicycle activity level;

[0086] Step 2.6: Repeat step 2.5 until a set number of shared bicycle activity levels are obtained, and then determine the grids belonging to each shared bicycle activity level;

[0087] In this implementation, a total of 5 shared bicycle activity levels are obtained, and urban areas are grouped according to the shared bicycle activity levels;

[0088] Furthermore, in order to facilitate the scheduling and traffic planning of shared bicycles, the shared bicycle activity level can be divided more finely. When obtaining the shared bicycle flow of the jth grid, the shared bicycle flow in the morning and evening rush hours on weekdays, other time periods on weekdays except the morning and evening rush hours, and weekends and holidays can be obtained respectively, and then the urban areas with different shared bicycle activity levels in these three time periods can be obtained;

[0089] Step 3: Analyze the temporal and spatial distribution of shared bicycles or users in each city area based on the level of shared bicycle activity;

[0090] Step 3.1: Filter the shared bicycle travel data according to the urban area to be analyzed; the urban area to be analyzed is all grids or a certain grid included in a certain shared bicycle activity level;

[0091] The method for screening shared bicycle travel data is as follows: screening shared bicycle travel data with a starting point or an end point in this urban area; the starting point reflects the outflow, and the end point reflects the inflow;

[0092] Step 3.2: Group the shared bicycle travel data according to the shared bicycle ID or user ID, sort the end point coordinates or the start point coordinates in all the shared bicycle travel data of a shared bicycle or a user by time, obtain the travel trajectory data of the shared bicycle or the user, and calculate the turning radius corresponding to each shared bicycle or user according to the travel trajectory data; the turning radius reflects the range of the departure (or destination) location of the shared bicycle or user flowing into (or out of) a certain urban area;

[0093] When shared bicycle travel data is filtered according to the starting point in step 3.1, step 3.2 sorts the coordinates of the ending points in all shared bicycle travel data of a shared bicycle or a user according to time; when shared bicycle travel data is filtered according to the ending point in step 3.1, step 3.2 sorts the coordinates of the starting points in all shared bicycle travel data of a shared bicycle or a user according to time;

[0094]

[0095]

[0096] Among them, α represents a shared bicycle or user, represents the turning radius of a shared bicycle or user, (x i ,y i ) represents the coordinates of the i-th position (starting point or ending point) passed in the travel trajectory data corresponding to the shared bicycle or user, n α is the number of locations in the travel trajectory data of a shared bicycle or user α, (x c ,y c ) represents the centroid coordinates of the travel trajectory data of the shared bicycle or user α;

[0097] Step 3.3: The probability distributions of the four shared bicycle travel indicators of travel distance, turning radius, travel time and travel angle in the screened shared bicycle travel data are fitted respectively, and several different probability distribution functions and their corresponding Akaike information criterion AIC are obtained for each shared bicycle travel indicator. For each shared bicycle travel indicator, the probability distribution function with the smallest Akaike information criterion AIC is selected as the optimal probability distribution function of the shared bicycle travel indicator, and then the optimal probability distribution functions of travel distance, turning radius, travel time and travel angle are obtained. In this way, the temporal and spatial distribution and activity range distribution law of shared bicycles in the corresponding urban area are obtained; the horizontal axis of the probability distribution function is the value of the shared bicycle travel indicator, and the vertical axis is the probability;

[0098] Step 4: Analyze the flow patterns of shared bicycles or users in each city area, including the relationship between flow and travel distance, turning radius and travel frequency;

[0099] Step 4.1: Select the city area to be analyzed, filter the shared bicycle travel data with the end point or the start point in the city area, count the number of times the same shared bicycle or the same user appears, and convert the number into frequency to obtain the travel frequency of each shared bicycle or user;

[0100] Step 4.2: Further filter out the shared bicycle travel data of shared bicycles or users within the set travel frequency range from the shared bicycle travel data filtered in step 4.1, and draw a graph to obtain the functional relationship between the flow rate and the travel distance or the turning radius;

[0101] Step 4.3: Further filter out the shared bicycle travel data of shared bicycles or users within the set travel distance or turning radius from the shared bicycle travel data filtered in step 4.1, and draw a graph to obtain the functional relationship between flow and travel frequency;

[0102] Step 5: Analyze the entry and exit patterns of a single shared bicycle or a single user;

[0103] Step 5.1: Count the number of grids q that flow into or out of the same shared bicycle or the same user as the number of trips m increases, fit the functional relationship between the number of trips m and the number of grids q that flow into or out of the city, and obtain the expression for the number of grids that the shared bicycle or user flows into or out of: q = g(m), where g(m) is the functional expression for the number of trips m. Then, the probability that the shared bicycle or user goes to a city grid that has not been reached during the mth trip is obtained:

[0104]

[0105] Among them, P a The probability that a shared bicycle or user goes to a grid that has not been reached before during the mth trip;

[0106] Step 5.2: Convert the number of times the same shared bicycle or the same user flows into or out of each grid into frequency, and obtain the frequency of visit or leave of each grid f. Statistically calculate the relationship between the frequency of visit or leave of each grid and the ranking K of the traffic of the shared bicycles in the grid: f = h(K), where h(K) is a function expression of the ranking K of the traffic of the grid shared bicycles, which represents the distribution law of the number of times any selected shared bicycle or user flows into or out of each grid.

[0107] The present invention analyzes the access patterns of shared bicycles and their users in various urban areas and urban areas of various activity levels at different time periods from multiple perspectives, providing assistance for the scheduling of shared bicycle systems and urban traffic planning.

[0108] This embodiment provides a shared bicycle and user access regularity analysis system, which is used to implement a shared bicycle and user access regularity analysis method, including:

[0109] A shared bicycle travel data acquisition module is used to collect shared bicycle travel data in a target city, wherein the shared bicycle travel data includes shared bicycle order data and its corresponding shared bicycle travel indicators;

[0110] A data preprocessing module is used to preprocess the collected shared bicycle travel data of the target city to obtain the preprocessed shared bicycle travel data;

[0111] The shared bicycle activity level classification module is used to grid the map of the target city to obtain a number of grids, each grid being a city area, and then determine the shared bicycle activity level of each city area, thereby obtaining city areas belonging to different shared bicycle activity levels;

[0112] The spatiotemporal distribution law analysis module is used to analyze the spatiotemporal distribution law of shared bicycles or users in each city area according to the activity level of shared bicycles;

[0113] The flow pattern analysis module is used to analyze the relationship between the flow of shared bicycles or users in each city area and the travel distance and turning radius, and obtain the flow pattern of shared bicycles in the city area, including the relationship between the flow and the travel distance or turning radius and the relationship between the flow and the travel frequency;

[0114] Location entry and exit pattern analysis module, used for the location entry and exit pattern of a single shared bicycle or a single user;

[0115] This embodiment provides an electronic device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for analyzing the regularity of shared bicycles and user access are executed;

[0116] This embodiment provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the method for analyzing the shared bicycle and user access rules are executed.

Claims

1. A method for analyzing shared bicycles and user access rules, characterized in that: The steps include: Step 1: Collect and pre-process the shared bicycle travel data of the target city to obtain the pre-processed shared bicycle travel data; the shared bicycle travel data includes shared bicycle order data and its corresponding shared bicycle travel indicators; Step 2: Divide the target city into grids and determine the shared bicycle activity level of each grid based on the preprocessed shared bicycle travel data; Step 3: Analyze the temporal and spatial distribution of shared bicycles or users in each city area based on the level of shared bicycle activity; Step 4: Analyze the flow patterns of shared bicycles or users in each city area, including the relationship between flow and travel distance, turning radius and travel frequency; Step 5: Analyze the entry and exit patterns of a single shared bicycle or a single user.

2. A method for analyzing shared bicycles and user access rules according to claim 1, characterized in that: The step 1 specifically includes: Step 1.1: Collect the shared bicycle order data within a certain time range in the target city, including shared bicycle ID, user ID, starting point coordinates, ending point coordinates, start time and end time; Step 1.2: According to the coordinates of the starting point, the coordinates of the ending point, the starting time and the ending time in the shared bicycle order data, the shared bicycle travel indicators are obtained, including the travel distance, the travel time and the travel angle; the travel angle is the angle formed by the vector from the starting point to the ending point and the positive direction of the x-axis in the city coordinate system, and the city coordinate system takes the east as the x-axis and the north as the y-axis; Step 1.3: Use the shared bicycle order data obtained in step 1.1 and the shared bicycle travel index obtained in step 1.2 as shared bicycle travel data; Step 1.4: Preprocess the shared bicycle travel data to obtain the preprocessed shared bicycle travel data; The preprocessing is: judging whether there are abnormalities in the shared bicycle travel data according to the travel distance and travel time, and removing the shared bicycle travel data with abnormalities, specifically, removing the shared bicycle travel data with a travel distance less than a set first threshold and a travel distance greater than a set second threshold; removing the shared bicycle travel data with a travel time less than a set third threshold and a travel time greater than a set fourth threshold.

3. A method for analyzing shared bicycles and user access rules according to claim 1, characterized in that: The step 2 specifically includes: Step 2.1: Grid the map of the target city to obtain several grids, number each grid, and project the starting point coordinates and the ending point coordinates of the pre-processed shared bicycle travel data into the grids; Step 2.2: According to the shared bicycle travel data, obtain the flow rate A(j) of the shared bicycles in each grid, and normalize the flow rate A(j) of the shared bicycles in each grid, where j is the number of the grid; the flow rate is the inflow or outflow, the inflow is the number of trips with the end point in the same grid within the set time range, and the outflow is the number of trips with the starting point in the same grid within the set time range; Step 2.3: Sort all grids in ascending order according to the normalized shared bicycle flow ρ(j) of each grid, calculate the location score and cumulative flow score of each grid, and draw the cumulative distribution curve of shared bicycle flow based on the location score and cumulative flow score of each grid; In the cumulative distribution curve of the shared bicycle flow, the x-axis represents the position score of the sorted grid, and the y-axis represents the corresponding cumulative flow score F(k); The position scores are: R(k)=k / n Where R(k) is the position score of the kth grid after sorting, k is the number of the sorted grid, and n is the number of grids with shared bicycles flowing in or out; The cumulative flow fraction is: Among them, F(k) is the cumulative flow score of the kth grid after sorting, and ρ(l) is the normalized shared bicycle flow of the lth grid after sorting; Step 2.4: Determine a cutoff point of the shared bicycle activity level on the cumulative distribution curve of shared bicycle flow, and divide the grids whose cumulative flow scores are greater than the cutoff point of the shared bicycle activity level into a shared bicycle activity level; The method for determining a dividing point of a shared bicycle activity level is as follows: calculating the derivative of the cumulative distribution curve of the shared bicycle flow at (1,1), thereby obtaining the tangent line of the cumulative distribution curve of the shared bicycle flow at (1,1), and then calculating the horizontal coordinate of the intersection of the tangent line of the cumulative distribution curve of the shared bicycle flow at (1,1) and the x-axis, which is the dividing point of the shared bicycle activity level; Step 2.5: Remove the cumulative flow scores that are greater than the cutoff point of the current shared bicycle activity level, and redraw the cumulative distribution curve of shared bicycle flow according to the method of step 2.3, and then follow step 2.4 again to obtain the grid belonging to a shared bicycle activity level; Step 2.6: Repeat step 2.5 until a set number of shared bicycle activity levels are obtained, and then determine the grid belonging to each shared bicycle activity level.

4. A method for analyzing shared bicycles and user access rules according to claim 3, characterized in that: When obtaining the shared bicycle traffic of the jth grid, the shared bicycle traffic in three situations is obtained respectively, namely, the morning and evening peak hours on weekdays, other time periods on weekdays except the morning and evening peak hours, and weekends and holidays, and then grids with different shared bicycle activity levels in these three time periods are obtained.

5. A method for analyzing shared bicycles and user access rules according to claim 1, characterized in that: The step 3 specifically includes: Step 3.1: Filter the shared bicycle travel data according to the urban area to be analyzed; the urban area to be analyzed is all grids or a certain grid included in a certain shared bicycle activity level; The method for filtering shared bicycle travel data is: filtering shared bicycle travel data with a starting point or an end point in this city area; Step 3.2: Group the shared bicycle travel data according to the shared bicycle ID or user ID, sort the end point coordinates or the start point coordinates in all the shared bicycle travel data of a shared bicycle or a user by time, obtain the travel trajectory data of the shared bicycle or user, and calculate the turning radius corresponding to each shared bicycle or user according to the travel trajectory data; Among them, α represents a shared bicycle or user, represents the turning radius of a shared bicycle or user, (x i ,y i ) represents the coordinates of the i-th position passed by the shared bicycle or the user’s corresponding travel trajectory data, n α is the number of locations in the travel trajectory data of a shared bicycle or user α, (x c ,y c ) represents the centroid coordinates of the travel trajectory data of the shared bicycle or user α; Step 3.3: Fit the probability distributions of the four shared bicycle travel indicators of travel distance, turning radius, travel time and travel angle in the screened shared bicycle travel data respectively, and obtain several different probability distribution functions and their corresponding Akaike information criterion AIC for each shared bicycle travel indicator. For each shared bicycle travel indicator, select the probability distribution function with the smallest Akaike information criterion AIC as the optimal probability distribution function of the shared bicycle travel indicator, and then obtain the optimal probability distribution function of travel distance, turning radius, travel time and travel angle; the horizontal axis of the probability distribution function is the value of the shared bicycle travel indicator, and the vertical axis is the probability.

6. A method for analyzing shared bicycles and user access rules according to claim 1, characterized in that: The step 4 specifically includes: Step 4.1: Select the city area to be analyzed, filter the shared bicycle travel data with the end point or the start point in the city area, count the number of times the same shared bicycle or the same user appears, and convert the number into frequency to obtain the travel frequency of each shared bicycle or user; Step 4.2: Further filter out the shared bicycle travel data of shared bicycles or users within the set travel frequency range from the shared bicycle travel data filtered in step 4.1, and draw a graph to obtain the functional relationship between the flow rate and the travel distance or the turning radius; Step 4.3: Further filter out the shared bicycle travel data of shared bicycles or users within the set travel distance or turning radius from the shared bicycle travel data filtered in step 4.1, and draw a graph to obtain the functional relationship between flow and travel frequency.

7. A method for analyzing shared bicycles and user access rules according to claim 1, characterized in that: The step 5 specifically includes: Step 5.1: Count the number of grids q that flow into or out of the same shared bicycle or the same user as the number of trips m increases, fit the functional relationship between the number of trips m and the number of grids q that flow into or out of the city, and obtain the expression for the number of grids that the shared bicycle or user flows into or out of: q = g(m), where g(m) is the functional expression for the number of trips m. Then, the probability that the shared bicycle or user goes to a city grid that has not been reached during the mth trip is obtained: Among them, P a The probability that a shared bicycle or user goes to a grid that has not been reached before during the mth trip; Step 5.2: Convert the number of times the same shared bicycle or the same user flows into or out of each grid into frequency, and obtain the frequency of visit or leave of each grid f. Statistically calculate the relationship between the frequency of visit or leave of each grid and the ranking K of the traffic of the shared bicycles in the grid: f = h(K), where h(K) is a function expression of the ranking K of the traffic of the grid shared bicycles, which represents the distribution law of the number of times any selected shared bicycle or user flows into or out of each grid.

8. A shared bicycle and user access rule analysis system, characterized in that: A method for analyzing the regularity of shared bicycles and user accesses used to implement any one of claims 1 to 7, comprising: A shared bicycle travel data acquisition module is used to collect shared bicycle travel data in a target city, wherein the shared bicycle travel data includes shared bicycle order data and its corresponding shared bicycle travel indicators; A data preprocessing module is used to preprocess the collected shared bicycle travel data of the target city to obtain the preprocessed shared bicycle travel data; The shared bicycle activity level classification module is used to grid the map of the target city to obtain a number of grids, and then determine the shared bicycle activity level of each grid, thereby obtaining grids belonging to different shared bicycle activity levels; The spatiotemporal distribution law analysis module is used to analyze the spatiotemporal distribution law of shared bicycles or users in urban areas according to the activity level of shared bicycles; The flow pattern analysis module is used to analyze the relationship between the flow of shared bicycles or users in the urban area and the travel distance, turning radius and travel frequency, and obtain the flow pattern of shared bicycles in the urban area; The location entry and exit pattern analysis module is used to analyze the location entry and exit patterns of a single shared bicycle or a single user.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate via the bus. When the machine-readable instructions are executed by the processor, the steps of the method for analyzing shared bicycles and user access patterns are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for analyzing the shared bicycle and user access rules are executed.

Images