A method for determining that a shared bicycle is for shopping trips using LBS data

Abstract

The present invention discloses a method for determining that a shared bicycle is for shopping trips by using LBS data, which relates to the technical fields of urban planning, geography, and traffic management, and includes: preprocessing the shared bicycle data, and calculating the maximum walking radius by using the obtained effective riding data; calculating the attraction range of retail commercial facilities for the docking of shared bicycles based on the maximum walking radius; according to the obtained attraction range of retail commercial facilities for the docking of shared bicycles and the walking reach range formed based on the urban road network with any end point of the shared bicycle ride in the attraction range as the center and the line connecting the end point of the ride and the retail commercial facility as the radius, classifying and judging whether the travel purpose of any shared bicycle is shopping.

Description

Technical Field

[0001] The present invention relates to the technical fields of urban planning, geography and traffic management, and specifically to a method for determining whether a shared bicycle is used for shopping trips by using LBS data. Background Art

[0002] Travel is one of the basic daily activities of residents. The study of its spatiotemporal behavior is helpful to understand the behavior patterns and travel needs of residents. The identification of travel purposes is helpful to strengthen the refined research on "people-spatial-temporal behavior laws", so as to optimize the corresponding urban system in a targeted manner and provide residents with a better travel environment. Among them, shared bicycles, which have become popular due to the development of the sharing economy, also have multiple travel purposes. They may even replace other means of transportation that residents are accustomed to using for specific travel purposes due to certain conditions. Therefore, the identification of the travel purpose of shared bicycles is equally important: it involves the cross-integration of multiple disciplines such as geography, urban planning, transportation, and information technology, which is conducive to promoting theoretical research on behavioral geography and time geography in the information age, urban space optimization and smart city construction, transportation system improvement, and improvement of geospatial remote sensing and GPS positioning technology.

[0003] Among the various travel purposes of shared bicycles, shopping trips have become one of the relatively large but easily overlooked, important and common purposes because of the frequent and sporadic activities and the fact that the usage scenarios are mainly short-distance travel (which is consistent with the typical pattern of shared bicycle use). According to the analysis report of Aurora Big Data, the purposes of shared bicycle use and their proportions are: commuting and school (36.9%), shopping (25.4%), leisure activities such as sports and scenic spot tourism (24.6%), and others (2.9%); and there are more shared bicycle shopping trips on non-working days such as weekends or holidays. The report jointly released by Hello Travel and Koubei Ele.me also shows that "during the May Day holiday in 2020, the proportion of surrounding cycling with shopping malls, home appliance and electronics stores, and special commercial streets as destinations was as high as 30.3%"; in addition, shopping trips themselves have both randomness and a certain regularity (such as regular shopping such as purchasing food and daily necessities), but are weaker than the regularity of commuting trips and the randomness of leisure trips. This makes the identification of shared bicycle shopping trips of great value and certain innovation, and the operability is relatively stronger.

[0004] Existing research on the travel purposes of shared bicycles mainly focuses on the identification of commuting trips and their sub - types. GPS positioning data and POI data are basically used. The technical idea is generally to infer various travel purposes of shared bicycles through a series of probability models, transformation and superposition calculations of weight ratios. The specific technical means are mostly to improve, enhance or fuse existing technical models and appropriately transform them for corresponding research services (for example: decision tree, neural network, support vector machine, K - nearest neighbor, gravity model, etc.). There are also methods that consider the travel habits of residents and the business hours of different places, and then combine Bayes' rule to optimize the model with the frequency density and type level of POIs.

[0005] There are certain problems with the existing identification methods: (1) In terms of research objects, there are relatively rich research results on commuting trips, while the identification research on non - rigid trips such as shopping trips and leisure trips has less accumulated results. (2) In terms of technical methods, a general method is used to identify shared bicycle trips for multiple purposes, ignoring the objective differences existing between the travel laws of different activities, resulting in certain deviations in the results. At the same time, there is room for further improvement and enhancement in the specific technical links of judging the purposes of shared bicycles. For example, calculating using a unified and determined time weight ignores the inherent differences in the spatio - temporal laws of shared bicycle use in different cities affected by factors such as climate and residents' work and rest, resulting in the applicable range of the method may be limited to the sample cities only; if only the two factors of POI frequency density and type level are used to reflect the overall environment of the destination candidate area, it is a bit one - sided, etc. Summary of the Invention

[0006] To solve the deficiencies mentioned in the above - mentioned background technology, the purpose of the present invention is to provide a method for determining that a shared bicycle is for shopping trips using LBS data.

[0007] The purpose of the present invention can be achieved through the following technical solutions: A method for determining that a shared bicycle is for shopping trips using LBS data, the method includes the following steps:

[0008] Pre - process the shared bicycle data, and screen out valid riding data. Among them, the shared bicycle data includes order number, vehicle number, user number, order start and end times, starting and ending point coordinates of the shared bicycle for each order, and GPS trajectory data;

[0009] Calculate the maximum walking radius using the obtained valid riding data;

[0010] Based on the maximum walking radius, calculate the attraction range of retail commercial facilities for the parking of shared bicycles;

[0011] Based on the obtained attraction range of retail commercial facilities for shared bicycle docking, and taking any shared bicycle riding end point within the attraction range as the center and the line connecting the riding end point and the retail commercial facility as the radius, the walkable range formed based on the urban road network is used to classify and judge whether the travel purpose of any shared bicycle is shopping.

[0012] Preferably, the basis for screening valid riding data is as follows:

[0013] Taking the shared bicycle data with a riding time not greater than 1h and an average riding speed in the range of 1km / h - 30km / h as one valid data; then establishing a time constraint for shared bicycle shopping trips to secondarily screen and extract valid riding data, and the time constraint is: 10:00 - 16:00 on weekdays, 19:00 - 21:00, and 9:00 - 21:00 on weekends.

[0014] Preferably, the calculation process of the maximum walking radius is as follows:

[0015] By calculating the distance between the riding end point of the shared bicycle and the nearest neighbor retailer facility POI data around it, based on the "maximum walking radius - proportion of shared bicycle data volume" histogram, the value of the maximum walking radius r is adaptively determined.

[0016] Preferably, the "maximum walking radius - proportion of shared bicycle data volume" histogram is the change in the proportion of the shared bicycle data volume that can search for at least 1 retail commercial facility POI within a certain range to the total shared bicycle data volume.

[0017] Preferably, the maximum walking radius needs to meet the following conditions:

[0018] Within the circular area with the riding end point of the shared bicycle as the center and r as the radius, at least 1 retailer facility POI data is queried; the proportion of the shared bicycle data meeting the above conditions to the total shared bicycle data volume is 90%.

[0019] Preferably, the process of calculating the attraction range of retail commercial facilities for shared bicycle docking is as follows:

[0020] Using the differences and influences of factors such as the scale and volume of different retail commercial facilities, the number of stores contained, location conditions and traffic environment, and the layout of surrounding electronic fences, etc., to calculate the attraction range A of each retail commercial facility for shared bicycle docking r , and the calculation method is:

[0021] A r = r * [1 + (S + N + D + d r + d bs + d me )]

[0022] Among them, S is the floor area of the facility, N is the number of stores included in the facility, D, d r , d bs , d me are respectively the density of retail commercial facilities, the density of urban road networks, the density of bus stops, and the density of subway entrances and exits within a 1 km radius centered on the target retail commercial facility. Before the index superposition, the dimensionless method of the linear function normalization method needs to be used, and its formula is:

[0023]

[0024] Among them, X is the original data of a certain type of index, X min , X max are respectively the maximum value and the minimum value of a certain type of index data.

[0025] Preferably, the process of classifying and judging whether the travel purpose of any shared bicycle is shopping is as follows:

[0026] If the riding end of any shared bicycle is outside the attraction range of all retail commercial facilities, it is considered that the travel purpose of the shared bicycle is not shopping;

[0027] If the spatial position of the riding end of any shared bicycle is within the attraction range of all retail commercial facilities, with the riding end of the shared bicycle as the center and the connection line between the riding end and the retail commercial facility as the radius, calculate the walkable range A b , compare A b with A r and establish the judgment rules for their spatial relationship respectively:

[0028] The first case: A b ∩A r =A b , that is, A r completely contains A b , then it is determined that the shared bicycle has a shopping trip associated with the retail commercial facility;

[0029] The second case: A b ∩A r <A b , A b ∩A r <A r , that is, A r and A b have an overlapping part. Assume that A b ∩A r =S, A r and A b except for the overlapping part are respectively set as S r and S b , then there is S + Sr = A r , S + S b = A b ,

[0030] In this case, although the end point of the shared bike ride is within the attraction range of the retail commercial facility, the impact of other types of POIs within walking distance on the recognition result also needs to be considered. It can be judged by counting the proportion of POIs of all retail commercial facilities within the range of A b (P i ), and its calculation formula is as follows:

[0031]

[0032] Among them, N C is the number of POIs of all retail commercial facilities, and N POI is the total number of POIs of all types.

[0033] On this basis, the parameter P0 is introduced as the judgment criterion for whether the purpose of the shared bike trip is shopping, and the judgment method is as follows:

[0034] If P i > P0, it is determined that a shopping trip associated with this retail commercial facility has occurred for the shared bike,

[0035] If P i ≤ P0, it is determined that a shopping trip associated with this retail commercial facility has not occurred for the shared bike.

[0036] Preferably, by traversing all the data of retail commercial facilities within the research range, any shared bike data is judged:

[0037] If the shared bike data satisfies that at least one judgment result is "a shopping trip associated with a certain retail commercial facility has occurred", that is, A b ∩ A r = A b , or A b ∩ A r < A b , A b ∩ A r < A r and P i > P0, it is considered that the purpose of the shared bike trip is shopping;

[0038] If all the judgment results of the shared bike data are "no shopping trip associated with a certain retail commercial facility has occurred for this shared bike", it is considered that the purpose of the shared bike trip is not shopping.

[0039] Preferably, the value range of the parameter P0 is 50% ≤ P0 ≤ 100%, and the value can be adjusted according to the accuracy required by the target data.

[0040] Advantages of the present invention:

[0041] The present invention provides a method for relatively accurately determining whether the purpose attribute of a certain trip of a shared bicycle is shopping by using multi-source LBS data. First, a time constraint is established on the basis of the preliminary screening data to further screen the shared bicycle data whose trip purpose may be shopping; secondly, the attraction range of each retail business facility for the docking of shared bicycles is calculated based on the maximum walking radius, and on this basis, a circle is drawn with the riding end point of the shared bicycle as the center and the line connecting the riding end point and the target retail business facility as the radius to calculate the walkable area based on the municipal road network; finally, the spatial relationship between the walkable area and the attraction range is compared, and the trip purpose of the shared bicycle is determined to be shopping in combination with the proportion of the POI types of the retail business facilities. The present invention can relatively conveniently and accurately determine whether the trip purpose attribute of the shared bicycle data is shopping, provide a basis for the research on the spatio-temporal laws of different trip activities of the shared bicycle, so as to further optimize the scheduling management of the shared bicycle and the planning and layout of related supporting facilities in a specific space and specific time period, and provide strong technical support for the efficient utilization of urban space and the rational allocation of urban resources. Description of the drawings

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts;

[0043] Figure 1 is a schematic flow chart of the method of the present invention;

[0044] Figure 2 is a schematic diagram of the spatial range for determining the shopping trips of shared bicycles when the method of the present invention is applied to XL Street.

[0045] Figure 3 is a histogram of "maximum walking radius - proportion of shared bicycle data volume" of XL Street in the embodiment of the present invention.

[0046] Figure 4 is a schematic diagram of two spatial relationships between the walkable range (A b ) and the attraction range of retail business facilities for the docking of shared bicycles (A r ) in the embodiment of the present invention.

[0047] Figure 5 is a schematic diagram for determining whether any shared bicycle trip in the research scope is a shopping trip in the embodiment of the present invention.

[0048] Figure 6 This is the recognition result of shared bicycle shopping trips in XL Street of the embodiments of the present invention. Detailed implementation manners

[0049] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0050] As Figure 1 shown, a method for determining that a shared bicycle is for shopping trips using LBS data includes the following steps:

[0051] Step 1: Obtain the POI data of NJ City in 2022, the urban road network data from the Amap API, and the usage data of shared bicycles on May 13 (Monday) and May 18 (Saturday) in 2019 from a third-party company (including order numbers, vehicle numbers, user numbers, order start and end times, starting and ending point coordinates of each shared bicycle order, and GPS trajectory data), and clean and screen the valid data of shared bicycles.

[0052] Step 1.1: Extract and retain the data with a riding time not greater than 1h and an average riding speed in the range of 1km / h - 30km / h for subsequent calculations.

[0053] Step 1.2: Extract the shared bicycle data with the order start time between 10:00 - 16:00 on weekdays, 19:00 - 21:00 on weekdays, and 9:00 - 21:00 on weekends as the valid data for this time.

[0054] Step 2: Draw a histogram of "maximum walking radius - proportion of shared bicycle data", adaptively determine the maximum walking radius, and finally determine that the maximum walking radius in this example is 200 meters, as shown in the appendix Figure 3 shown;

[0055] It should be further noted that in the specific implementation process, the maximum walking radius (r) should simultaneously meet the following two conditions: First, within the circular area with the end point of the shared bicycle ride as the center and r as the radius, at least 1 piece of retailer facility POI data is queried; Second, the proportion of the shared bicycle data meeting the above conditions in the total amount of shared bicycle data is 90%. Within the circular area with the end point of the shared bicycle ride as the center and r as the radius,

[0056] Step 3: Based on the maximum walking radius, calculate the attraction range (A r ) of a retail commercial facility within XL Street for bike-sharing docking. The relevant calculation formula is:

[0057] A r = r * [1 + (S + N + D + d r + d bs + d me )]

[0058] where S is the floor area of the facility, N is the number of stores in the facility, and D, d r , d bs , d me are the densities of retail commercial facilities, urban road networks, bus stops, and subway entrances within a 1 km radius centered on a certain retail commercial facility (bike-sharing usually has an advantage in completing the last kilometer of travel in connection with public transportation). First, perform linear function normalization on the indicators and then superimpose them.

[0059] Step 4: Classify and determine whether the purpose of a certain bike-sharing trip is shopping;

[0060] Step 4.1: Determine that the purpose of a bike-sharing trip whose riding end is outside the attraction range of all retail commercial facilities is not shopping;

[0061] Step 4.2: For the bike-sharing data whose riding end is within the attraction range of all retail commercial facilities, extract any bike-sharing data whose riding end is within the attraction range of a certain retail commercial facility. With the riding end of this bike-sharing as the center and the line connecting the riding end and this retail commercial facility as the radius, calculate the walkable range based on the actual road network (A b );

[0062] Step 4.3: Compare the spatial relationship between A r and A b .

[0063] When A b ∩A r = A b , that is, A r completely contains A b , then it is determined that this bike-sharing has a shopping trip associated with this retail commercial facility, as shown in Attachment Figure 4 -a;

[0064] When A b ∩A r < A b , A b ∩A r < A r , that is, A r and Ab There is an overlapping part. Assume A b ∩A r = S,A r And A b The remaining parts except for the intersection with A are respectively set as S r and S b , then there is S + S r = A r , S + S b = A b , then count the POI proportion (P b ) of all retail business facilities within the range of A for judgment. The calculation formula is as follows: i ) for judgment. The calculation formula is as follows:

[0065]

[0066] Among them, N C is the number of POIs of all retail business facilities, and N POI is the total number of all types of POIs.

[0067] On this basis, introduce the parameter P0 as the judgment standard for whether the purpose of bike-sharing travel is shopping. The specific judgment method is as follows:

[0068] If P i > P0, it is determined that the bike-sharing has a shopping trip associated with the retail business facility,

[0069] If P i ≤ P0, it is determined that the bike-sharing has not had a shopping trip associated with the retail business facility;

[0070] In general, the value range of P0 is 50% ≤ P0 ≤ 100%. Its specific value can be adjusted according to the required accuracy of the target data. According to the summary of empirical values and trial-and-error simulation verification, it is found that P0 in the closed interval [0.65, 0.90] is sufficient to achieve a relatively ideal discrimination effect. In this example, the value of P0 is set to 80%.

[0071] Step 5: Traverse all the retail business facility data within the research range, and perform the operations in the above steps 2) - 4) on any bike-sharing data,

[0072] If the bike-sharing data satisfies that at least one judgment result is "has had a shopping trip associated with a certain retail business facility" (that is, A b ∩A r = A b , or A b ∩A r < A b , A b ∩A r < Ar and P i > P0), it is considered that the travel purpose of the shared bicycle is shopping, as shown in Attachment Figure 5 -a;

[0073] If all the determination results of the shared bicycle data are "no shopping trips associated with a certain retail commercial facility", it is considered that the travel purpose of the shared bicycle is not shopping, as shown in Attachment Figure 5 -b.

[0074] The final recognition result is shown in Attachment Figure 6 .

[0075] Around a commercial complex in XL Street, NJ City, the determination results are verified by on-site observation and interviews with residents, and it is found that the accuracy rate can basically reach 83.3%, which proves the necessity and effectiveness of this method.

[0076] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0077] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art of this industry should understand that the present disclosure is not limited by the above embodiments, and the above embodiments and the descriptions in the specification only illustrate the principles of the present disclosure. Without departing from the spirit and scope of the present disclosure, the present disclosure will have various changes and improvements, and these changes and improvements all fall within the scope of the present disclosure claimed.

Claims

1. A method for determining that a shared bicycle is for shopping trips using LBS data, characterized in that, The method includes the following steps: Preprocess the shared bicycle data to screen out valid riding data. The shared bicycle data includes order number, vehicle number, user number, order start and end times, starting and ending point coordinates of the shared bicycle for each order, and GPS trajectory data; Calculate the maximum walking radius using the obtained valid riding data; Calculate the attraction range of retail commercial facilities for shared bicycle docking based on the maximum walking radius; The calculation process of the maximum walking radius is as follows: By calculating the distance between the riding end point of the shared bicycle and the nearest neighbor retailer facility POI data around it, based on the "maximum walking radius - proportion of shared bicycle data volume" histogram, adaptively determine the value of the maximum walking radius r; The "maximum walking radius - proportion of shared bicycle data volume" histogram is the change in the proportion of the shared bicycle data volume that can search for at least 1 retail commercial facility POI within a certain range to the total shared bicycle data volume; The maximum walking radius needs to meet the following conditions: Within the circular area with the riding end point of the shared bicycle as the center and r as the radius, at least 1 retailer facility POI data is queried; the proportion of the shared bicycle data that meets the above conditions to the total shared bicycle data volume is 90%; The process of calculating the attraction range of retail commercial facilities for shared bicycle docking is as follows: Calculate the attraction range A of each retail business facility for bike-sharing docking by taking into account the differences and impacts of the scale and volume of different retail business facilities, the number of stores they contain, location conditions and traffic environment, and the layout factors of the surrounding electronic fences r , and the calculation method is as follows: A r = r * [1 + (S + N + D + d r + d bs + d me )] Among them, S is the floor area of the facility, N is the number of stores included in the facility, D, d r , d bs , d me are respectively the density of retail commercial facilities, the density of urban road networks, the density of bus stops, and the density of subway entrances and exits within 1 km with the target retail commercial facility as the center. Before the index superposition, the dimensionless method using the linear function normalization method is required, and its formula is: Among them, X is the original data of a certain type of indicator, X min , X max are the maximum value and the minimum value of the data of a certain type of indicator respectively; Based on the obtained attraction range of retail commercial facilities for shared bicycle docking and with any riding end point within the attraction range as the center and the line connecting the riding end point and the retail commercial facility as the radius, based on the walkable range formed by the urban road network, classify and judge whether the travel purpose of any shared bicycle is shopping; The process of classifying and judging whether the travel purpose of any shared bicycle is shopping is as follows: If the riding end point of any shared bicycle is outside the attraction range of all retail commercial facilities, it is considered that the travel purpose of the shared bicycle is not shopping; If the spatial location of the riding end of any shared bicycle is within the attraction range of all retail commercial facilities, taking the riding end of the shared bicycle as the center and the line connecting the riding end and the retail commercial facility as the radius, calculate the walkable range A based on the actual road network b , compare A b with A r and establish determination rules for their spatial relationships respectively: The first case: A b ∩A r = A b , that is, A r completely contains A b , it is determined that a shopping trip associated with this retail commercial facility has occurred for the shared bicycle; The second case: A b ∩A r <A b ,A b ∩A r <A r , that is, A r and A b have an overlapping part. Assume that A b ∩A r = S, A r and A b The remaining parts except the intersection are respectively set as S r and S b , then there is S + S r = A r , S + S b = A b , In this case, although the end point of the shared bike ride is within the attraction range of the retail commercial facilities, it is also necessary to consider the impact of other types of POIs within the walkable range on the recognition result. This can be done by counting the proportion P of the POIs of all retail commercial facilities within the range A b to make a judgment. The calculation formula is as follows: i to make a judgment, and its calculation formula is as follows: Among them, N C is the number of all retail business facility POIs, and N POI is the total number of all types of POIs; On this basis, introduce the parameter P0 as the judgment criterion for whether the travel purpose of the shared bicycle is shopping, and the judgment method is as follows: If P i > P0, it is determined that the shared bicycle has made a shopping trip associated with the retail commercial facility. If P i ≤ P0, it is determined that the shared bicycle has not made a shopping trip associated with the retail commercial facility; By traversing all retail commercial facility data within the research range, judge any shared bicycle data: If the shared bike data meets the condition that at least one judgment result is "a shopping trip associated with a certain retail commercial facility", i.e., A b ∩A r =A b , or A b ∩A r <A b ,A b ∩A r <A r and P i >P0, then the travel purpose of the shared bike is considered to be shopping; If all judgment results of the shared bicycle data are "no shopping trip associated with a certain retail commercial facility occurred for this shared bicycle", it is considered that the travel purpose of the shared bicycle is not shopping.

2. The method for determining that a shared bicycle is for shopping trips by using LBS data according to claim 1, wherein The basis for screening valid riding data is as follows: The shared bicycle data with a riding time not greater than 1h and an average riding speed in the range of 1km / h - 30km / h is regarded as one piece of valid data; then establish a time constraint for shared bicycle shopping trips to secondarily screen and extract valid riding data, and the time constraint is: 10:00 - 16:00, 19:00 - 21:00 on weekdays and 9:00 - 21:00 on weekends.

3. A method for determining that a shared bicycle is for shopping trips using LBS data according to claim 1, characterized in that, The value range of the parameter P0 is 50% ≤ P0 ≤ 100%, and the value can be adjusted according to the accuracy required by the target data.

Images