Motor vehicle information management system based on big data
Through big data analysis and route planning optimization, the problem of driving management for ride-hailing drivers when they are not accepting orders has been solved, and the frequency and efficiency of accepting orders have been improved, especially during drop-off times on high-traffic vehicles and at large event venues.
Patent Information
- Application Number
- CN202510801789.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-16
- Publication Date
- 2025-11-18
AI Technical Summary
In existing technologies, the management of ride-hailing drivers when they are not accepting orders is relatively arbitrary, resulting in the starting point being too far from the vehicle and low order-accepting efficiency. In particular, the order-accepting frequency is significantly higher during drop-off times on high-traffic public transportation and at large event venues than at other times.
The big data-based motor vehicle information management system collects passenger drop-off time data and order frequency data at various passenger pick-up points through the information collection module, marks high-frequency locations through the map management module, and calculates order frequency and priority through the trip planning module to replan navigation routes to improve order efficiency.
By using big data analysis, we can optimize the routes of ride-hailing drivers, increase the frequency of accepting orders, reduce aimless driving when not accepting orders, and improve drivers' work efficiency and the probability of accepting orders.
Smart Images
Figure CN120975347A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of big data management technology, specifically to a motor vehicle information management system based on big data. Background Technology
[0002] When not accepting rides, drivers on ride-hailing platforms typically decide their own driving areas and routes. Some drivers may choose to stay in areas with high pedestrian traffic to increase their chances of receiving passenger orders. Some ride-hailing platforms provide drivers with suggestions through data analysis, such as providing heat maps to show areas with high passenger demand.
[0003] In cities, high-traffic public transportation modes such as high-speed rail and subways have fixed drop-off times, as do university campuses during school hours and the end of events at large entertainment venues. At these drop-off times, the frequency of ride-hailing services picking up passengers is significantly higher than at other times. Current technology manages ride-hailing vehicles without accepted rides rather haphazardly, leading to drivers driving aimlessly when not accepting rides, with their starting points too far from their vehicles, resulting in inefficient ride-hailing. Therefore, designing a big data-based vehicle information management system to improve ride-hailing frequency is essential. Summary of the Invention
[0004] The purpose of this invention is to provide a motor vehicle information management system based on big data to solve the problems mentioned in the background art.
[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a big data-based motor vehicle information management system, comprising an information collection module, a map management module, and a trip planning module. The information collection module is used to collect drop-off time data, order acceptance time data, and order acceptance frequency data for each passenger pick-up point. The map management module is used to mark the locations of each passenger pick-up point on the ride-hailing navigation map. The trip planning module is used to plan trips for ride-hailing drivers who are in an unaccepted order state.
[0006] According to the above technical solution, the information collection module includes a time recording module, an information storage module, a passenger load recording module, an API interface access module, and a ticket purchase information recording module. The time recording module is electrically connected to the passenger load recording module, the passenger load recording module is electrically connected to the information storage module, and the API interface access module is electrically connected to the ticket purchase information recording module. The time recording module is used to record the statistical period and each statistical time point. The information storage module is used to store all historical passenger load information and time information. The passenger load recording module is used to record passenger load information at each starting point. The API interface access module is used to access the API interface of the ticketing website. The ticket purchase information recording module is used to read the arrival and departure time information from the ticket purchase information and to count the number of ticket purchasers.
[0007] The map management module includes a starting point location reading module, a high-frequency location marking module, a navigation map module, and a type classification module. The starting point location reading module is electrically connected to the high-frequency location marking module, the high-frequency location marking module is electrically connected to the navigation map module, and the type classification module is electrically connected to the high-frequency location marking module. The starting point location reading module is used to read all starting point locations in the navigation map. The high-frequency location marking module is used to mark the locations of high-frequency passengers based on historical passenger information. The navigation map module is used to generate each starting point location and generate driving routes in the navigation map. The type classification module is used to classify high-frequency locations based on whether they are periodic.
[0008] The trip planning module includes an order frequency calculation module, a periodicity determination module, an order frequency prediction module, a route generation module, a priority determination module, and a route modification module. The order frequency calculation module is electrically connected to the periodicity determination module and the order frequency prediction module. The route generation module is electrically connected to the priority determination module and the navigation map module. The route modification module is electrically connected to the route generation module. The order frequency calculation module is used to calculate the order frequency of each high-frequency location. The periodicity determination module is used to determine whether the order taking at high-frequency locations is periodic. The order frequency prediction module is used to predict the order frequency during future drop-off periods. The route generation module is used to generate a driving route based on the priority of the ride-hailing vehicle to a certain high-frequency location. The route modification module is used to replan the navigation route when a circle centered on a high-frequency location intersects with the driving route.
[0009] Based on the above technical solution, the working method of this system is as follows:
[0010] S1. Mark the starting points of each ride-hailing vehicle's historical passenger pick-up locations on the navigation map, set a statistical period, count the number of orders received at each starting point within the statistical period, and determine high-frequency locations.
[0011] S2. Collect order-receiving time series for high-frequency locations, map them into time density series at fixed time intervals, determine if there is a periodic pattern at the location, and calculate the order-receiving frequency during high-frequency periods.
[0012] S3. Read the ticketing website API at high-frequency locations such as high-traffic transportation stations and large event venues, collect ticketing data, record the arrival and departure times corresponding to the ticketing information, form drop-off times, and predict order frequency.
[0013] S4. When the ride-hailing vehicle is in an unaccepted state, calculate the driving route and driving time from the current location to each high-frequency location, calculate the priority of each high-frequency location, and select the location with the highest priority as the driving destination.
[0014] S5. Find high-frequency locations around the destination's driving route, draw circles with these high-frequency locations as the center, determine whether it is worthwhile to pass through the high-frequency location before reaching the destination, and update the driving route.
[0015] According to the above technical solution, in step S1, determining the high-frequency position specifically involves:
[0016] S1-1. Mark the starting locations of each ride-hailing vehicle in the city during its historical passenger pick-up times on the navigation map. Set the statistical period to T0. The number of times each starting location was used as the starting point by passengers during the statistical period T0 is {a1, a2…a ... n}, where n is the number of starting points on the navigation map in the city, and the order frequency of the starting point is calculated. Where i∈1~n, let the input threshold be f0, when f i When the value is greater than or equal to f0, the starting point is determined to be a high-frequency location, and data collection during the passenger drop-off period is required.
[0017] According to the above technical solution, the determination of the periodic pattern in S2 is specifically as follows:
[0018] S2-1. For all starting locations where passenger drop-off time slots need to be collected, determine whether the passenger pick-up time slots are fixed periods. For each high-frequency location, record its order-taking time sequence {t} in T0. i1 t i2 …t im}, where m is the number of orders received in T0, and this sequence is mapped to a time density sequence {x} according to fixed time intervals. i1 x i2 …x ik}, where k is the number of time intervals, and the amplitude is obtained by performing a discrete Fourier transform on the time density sequence. Where x ij Let f be the number of orders received during a certain time period, where j∈1~k. If there exists a certain main frequency f p Make Then the main frequency f p This corresponds to a periodic passenger-carrying pattern, where δ is the determination coefficient. Let f be the mean of the amplitude F(f), and f be the dominant frequency. p Corresponding period length When x ij When k≥f0T0, x ij The corresponding time period is the high-frequency period. Calculate the high-frequency period across all T periods. p Average order frequency within the period in For a given passenger-carrying time period, all Ts within T0 p Average number of orders received per cycle.
[0019] According to the above technical solution, in step S3, the predicted order frequency is specifically as follows:
[0020] S3-1. In S2-1, when a high-frequency location is determined to have no periodic passenger-carrying periods, if this high-frequency location is a high-traffic transportation station or a large event venue, then by reading the API interface of the ticketing website corresponding to this high-frequency location, ticketing information is obtained and continuously recorded. In another T0 cycle, based on the arrival and departure times in the ticketing information, the passenger disembarkation times at each high-frequency location are recorded. q Extended drop-off time [t] q The sequence of order counts within [t0] {y i1 y i2 …y ip}, where p is the number of times the current high-frequency position disembarks within T0, and y iq Let t0 be the number of orders accepted during a certain drop-off period, and q∈1~p. Calculate the average order acceptance frequency for a certain high-frequency location during a certain drop-off period. in This represents the historical average number of orders received during the drop-off period at the current high-frequency location.
[0021] S3-2. Obtain the number of ticket buyers from each ticket purchase information obtained from the ticketing website, and calculate the historical average number of ticket buyers for a certain high-frequency location during various drop-off times. In the subsequent judgment process, based on the number of ticket purchasers z during the current disembarkation period is and ratio The order frequency f during the current drop-off period is To make a prediction, the formula is: Where μ is the influence coefficient of the number of people.
[0022] According to the above technical solution, in step S4, selecting the location with the highest priority as the driving destination specifically means:
[0023] S4-1. Calculate the order acceptance frequency of each high-frequency location on the navigation map in real time. When the ride-hailing vehicle is in an order-free state, generate driving routes from the vehicle's current location to each high-frequency location, calculate the driving time for each route, and obtain the driving time sequence {t1, t2…t}. L Let the current time be t. e Therefore, the time point at which the ride-hailing vehicle arrives at a certain high-frequency location is t. e +t l , where l
[0024] ∈1~L, based on the type of each high-frequency position, determine the high-frequency position with a fixed period at t. e +t l Whether the time point is in a high-frequency period, and whether the high-frequency location that does not have a fixed cycle and belongs to a large passenger flow transportation station and a large event venue is in the passenger drop-off period;
[0025] S4-2, When a certain high-frequency position is at t e +t l When the time point is in a high-frequency period, read the high-frequency position at t. e +t l Order frequency f at a given time point ij When a certain high-frequency position is at t e +t l When the time point is during the passenger disembarkation period, read this high-frequency position at t. e +t l Order frequency f at a given time point is Calculate the priority G of a ride-hailing vehicle to a certain high-frequency location. i =αf ij ―βt l and G i =αf is ―βt l Where α and β are weighting coefficients, and G is chosen. i The highest frequency location is used as the destination. The higher the order acceptance frequency, the more likely it is to get an order quickly near the current starting point. The longer the travel time, the greater the cost for the ride-hailing vehicle to reach the current starting point. When the ride-hailing vehicle is traveling near the starting point, it will be prioritized by the system to accept orders.
[0026] According to the above technical solution, in step S5, updating the driving route specifically involves:
[0027] S5-1. Since the higher the order-accepting frequency at a certain starting point, the greater the probability that a ride-hailing vehicle farther from that starting point will receive orders, after determining the destination in S4-2, find all high-frequency locations in the surrounding area of the driving route that are in high-frequency and drop-off times, and take each high-frequency location as the center, and calculate the ωf corresponding to each high-frequency location. ij and ωf is A circle is drawn on the navigation map with radius ω, where ω is the radius conversion factor. When a circle centered on a high-frequency location intersects with the driving route, the navigation route is replanned. The new route first passes through the high-frequency location that intersects with the original driving route before reaching the destination. It is also necessary to ensure that the time when the new route reaches the destination is still within the high-frequency period and drop-off period of the destination.
[0028] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: This invention collects data on passenger drop-off times of high-volume transportation vehicles and large entertainment venues at irregular intervals, conducts big data analysis on passenger drop-off times of landmark locations such as university campuses and office parks at fixed intervals, and statistically analyzes the order-taking frequency of these drop-off areas. Combined with the current location of ride-hailing vehicles that are not currently accepting orders, the cost and revenue of each potential destination are estimated, and then the approximate routes and destinations of ride-hailing vehicles are planned, providing drivers with trip suggestions that have the highest potential revenue. Attached Figure Description
[0029] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:
[0030] Figure 1 This is a schematic diagram of the overall modular structure of the present invention. Detailed Implementation
[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0032] Please see Figure 1The present invention provides a technical solution: a motor vehicle information management system based on big data, including an information collection module, a map management module, and a trip planning module. The information collection module is used to collect data on drop-off times, order acceptance times, and order acceptance frequencies at each passenger pick-up point. The map management module is used to mark the locations of each passenger pick-up point on the ride-hailing navigation map. The trip planning module is used to plan trips for ride-hailing drivers who are in a state of not accepting orders.
[0033] The information collection module includes a time recording module, an information storage module, a passenger load recording module, an API interface access module, and a ticket purchase information recording module. The time recording module is electrically connected to the passenger load recording module, the passenger load recording module is electrically connected to the information storage module, and the API interface access module is electrically connected to the ticket purchase information recording module. The time recording module is used to record the statistical period and each statistical time point. The information storage module is used to store all historical passenger load information and time information. The passenger load recording module is used to record passenger load information at each starting point. The API interface access module is used to access the API interface of the ticket purchase website. The ticket purchase information recording module is used to read the arrival and departure time information from the ticket purchase information and to count the number of ticket purchasers.
[0034] The map management module includes a starting point location reading module, a high-frequency location marking module, a navigation map module, and a type classification module. The starting point location reading module is electrically connected to the high-frequency location marking module, the high-frequency location marking module is electrically connected to the navigation map module, and the type classification module is electrically connected to the high-frequency location marking module. The starting point location reading module is used to read all starting point locations in the navigation map. The high-frequency location marking module is used to mark the locations of high-frequency passengers based on historical passenger information. The navigation map module is used to generate each starting point location and generate driving routes in the navigation map. The type classification module is used to classify whether the high-frequency locations are periodic.
[0035] The trip planning module includes an order frequency calculation module, a periodicity determination module, an order frequency prediction module, a route generation module, a priority determination module, and a route modification module. The order frequency calculation module is electrically connected to the periodicity determination module and the order frequency prediction module. The route generation module is electrically connected to the priority determination module and the navigation map module. The route modification module is electrically connected to the route generation module. The order frequency calculation module is used to calculate the order frequency of each high-frequency location. The periodicity determination module is used to determine whether the order taking at high-frequency locations is periodic. The order frequency prediction module is used to predict the order frequency during future drop-off periods. The route generation module is used to generate a driving route based on the priority of the ride-hailing vehicle to a certain high-frequency location. The route modification module is used to replan the navigation route when a circle centered on a high-frequency location intersects with the driving route.
[0036] The system works as follows:
[0037] S1. Mark the starting points of each ride-hailing vehicle's historical passenger pick-up locations on the navigation map, set a statistical period, count the number of orders received at each starting point within the statistical period, and determine high-frequency locations.
[0038] S2. Collect order-receiving time series for high-frequency locations, map them into time density series at fixed time intervals, determine if there is a periodic pattern at the location, and calculate the order-receiving frequency during high-frequency periods.
[0039] S3. Read the ticketing website API at high-frequency locations such as high-traffic transportation stations and large event venues, collect ticketing data, record the arrival and departure times corresponding to the ticketing information, form drop-off times, and predict order frequency.
[0040] S4. When the ride-hailing vehicle is in an unaccepted state, calculate the driving route and driving time from the current location to each high-frequency location, calculate the priority of each high-frequency location, and select the location with the highest priority as the driving destination.
[0041] S5. Find high-frequency locations around the destination's driving route, draw circles with these high-frequency locations as the center, determine whether it is worthwhile to pass through the high-frequency location before reaching the destination, and update the driving route.
[0042] In S1, determining the high-frequency position specifically involves:
[0043] S1-1. Mark the starting locations of each ride-hailing vehicle in the city during its historical passenger pick-up times on the navigation map. Set the statistical period to T0. The number of times each starting location was used as the starting point by passengers during the statistical period T0 is {a1, a2…a ... n}, where n is the number of starting points on the navigation map in the city, and the order frequency of the starting point is calculated. Where i∈1~n, let the input threshold be f0, when f i When f0 is greater than or equal to 0, the starting point is determined to be a high-frequency location, and data collection during the passenger drop-off period is required.
[0044] In S2, the periodic pattern is determined as follows:
[0045] S2-1. For all starting locations where passenger drop-off time slots need to be collected, determine whether the passenger pick-up time slots are fixed periods. For each high-frequency location, record its order-taking time sequence {t} in T0. i1 t i2 …t im}, where m is the number of orders received in T0, and this sequence is mapped to a time density sequence {x} according to fixed time intervals. i1 x i2 …x ik}, where k is the number of time intervals, and the amplitude is obtained by performing a discrete Fourier transform on the time density sequence. Where x ij Let f be the number of orders received during a certain time period, where j∈1~k. If there exists a certain main frequency f p Make Then the main frequency f p This corresponds to a periodic passenger-carrying pattern, where δ is the determination coefficient. Let f be the mean of the amplitude F(f), and f be the dominant frequency. p Corresponding period length When x ij When k≥f0T0, x ij The corresponding time period is the high-frequency period. Calculate the high-frequency period across all T periods. p Average order frequency within the period in For a given passenger-carrying time period, all Ts within T0 p Average number of orders received per cycle; for locations with high order frequency within a fixed cycle, the time periods are broken down into specific time slots, making it easier to allocate more ride-hailing drivers based on time slots, thus making supply and demand more matched.
[0046] In S3, the predicted order frequency is as follows:
[0047] S3-1. In S2-1, when a high-frequency location is determined to have no periodic passenger-carrying periods, if this high-frequency location is a high-traffic transportation station or a large event venue, then by reading the API interface of the ticketing website corresponding to this high-frequency location, ticketing information is obtained and continuously recorded. In another T0 cycle, based on the arrival and departure times in the ticketing information, the passenger disembarkation times at each high-frequency location are recorded. q Extended drop-off time [t] q The sequence of order counts within [t0] {y i1 y i2 …y ip}, where p is the number of times the current high-frequency position disembarks within T0, and y iq Let t0 be the number of orders accepted during a certain drop-off period, and q∈1~p. Calculate the average order acceptance frequency for a certain high-frequency location during a certain drop-off period. in This represents the historical average number of orders received during the drop-off period at the current high-frequency location.
[0048] S3-2. Obtain the number of ticket buyers from each ticket purchase information obtained from the ticketing website, and calculate the historical average number of ticket buyers for a certain high-frequency location during various drop-off times. In the subsequent judgment process, based on the number of ticket purchasers z during the current disembarkation period is and ratio The order frequency f during the current drop-off period is To make a prediction, the formula is: Where μ is the number of people impact coefficient; predicting the number of passengers to drop off in the future based on the number of people can dynamically adjust the order-taking method and make it easier to allocate more ride-hailing drivers when there are many people, thereby improving the passenger experience.
[0049] In S4, the highest priority location is selected as the destination as follows:
[0050] S4-1. Calculate the order acceptance frequency of each high-frequency location on the navigation map in real time. When the ride-hailing vehicle is in an order-free state, generate driving routes from the vehicle's current location to each high-frequency location, calculate the driving time for each route, and obtain the driving time sequence {t1, t2…t}. L Let the current time be t. e Therefore, the time point at which the ride-hailing vehicle arrives at a certain high-frequency location is t. e +t l , where l
[0051] ∈1~L, based on the type of each high-frequency position, determine the high-frequency position with a fixed period at t. e +t l Whether the time point is in a high-frequency period, and whether the high-frequency location that does not have a fixed cycle and belongs to a large passenger flow transportation station and a large event venue is in the passenger drop-off period;
[0052] S4-2, When a certain high-frequency position is at t e +t l When the time point is in a high-frequency period, read the high-frequency position at t. e +t l Order frequency f at a given time point ij When a certain high-frequency position is at t e +t l When the time point is during the passenger disembarkation period, read this high-frequency position at t. e +t l Order frequency f at a given time point is Calculate the priority G of a ride-hailing vehicle to a certain high-frequency location. i =αf ij ―βt l and G i =αf is ―βt l Where α and β are weighting coefficients, and G is chosen. iThe highest frequency location is used as the destination. The higher the order acceptance frequency, the more likely it is to get an order quickly near the current starting point. The longer the travel time, the greater the cost for the ride-hailing vehicle to reach the current starting point. When the ride-hailing vehicle is driving near the starting point, it will be prioritized by the system to accept orders. Only places with high order acceptance frequency and close distance have higher priority, so that ride-hailing drivers do not drive aimlessly when they have no orders, which can improve their work efficiency.
[0053] In S5, the updated driving routes are as follows:
[0054] S5-1. Since the higher the order-accepting frequency at a certain starting point, the greater the probability that a ride-hailing vehicle farther from that starting point will receive orders, after determining the destination in S4-2, find all high-frequency locations in the surrounding area of the driving route that are in high-frequency and drop-off times, and take each high-frequency location as the center, and calculate the ωf corresponding to each high-frequency location. ij and ωf is A circle is drawn on the navigation map with radius ω, where ω is the radius conversion factor. When a circle centered at a high-frequency location intersects the original route, the navigation route is replanned. The new route first passes through the high-frequency location that intersects with the original route before reaching the destination. It must ensure that the new route arrives at the destination during the high-frequency and drop-off times of the destination. This design takes into account areas along the route with a high probability of accepting orders, increasing the chances of getting orders earlier, while not affecting the original route planning, allowing drivers to pick up orders as early as possible while on the route.
[0055] By collecting data on passenger drop-off times from high-traffic public transportation and large entertainment venues at irregular intervals, and conducting big data analysis on drop-off times from landmark locations such as university campuses and office parks at fixed intervals, and by statistically analyzing the order-taking frequency in these drop-off areas, combined with the current location of ride-hailing vehicles that are not currently accepting orders, the cost and revenue of each potential destination are estimated. This allows for the planning of approximate routes and destinations for ride-hailing vehicles, providing drivers with trip suggestions that offer the highest potential revenue.
[0056] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0057] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A big data based motor vehicle information management system characterized in that: The system comprises an information collection module, a map management module and a trip planning module, the information collection module is used for collecting passenger drop-off time period data, order receiving time data and order receiving frequency data of each passenger pickup point, the map management module is used for marking the positions of each passenger pickup point on a navigation map of the online car-hailing, and the trip planning module is used for trip planning for the online car-hailing drivers in an order receiving state.
2. The big data based motor vehicle information management system as claimed in claim 1 wherein: The information collection module comprises a time recording module, an information storage module, a passenger pickup recording module, an API interface access module and a ticket purchase information recording module, the time recording module is electrically connected with the passenger pickup recording module, the passenger pickup recording module is electrically connected with the information storage module, and the API interface access module is electrically connected with the ticket purchase information recording module; the time recording module is used for recording a statistical period and each statistical time point, the information storage module is used for storing all passenger pickup information and time information in history, the passenger pickup recording module is used for recording passenger pickup information of each starting point position, the API interface access module is used for accessing an API interface of a ticket purchase website, and the ticket purchase information recording module is used for reading arrival and departure time information in ticket purchase information and counting ticket purchase number information; The map management module comprises a starting point position reading module, a high-frequency position marking module, a navigation map module and a type division module, the starting point position reading module is electrically connected with the high-frequency position marking module, the high-frequency position marking module is electrically connected with the navigation map module, and the type division module is electrically connected with the high-frequency position marking module; the starting point position reading module is used for reading all starting point positions in a navigation map, the high-frequency position marking module is used for marking high-frequency passenger pickup positions according to historical passenger pickup information, the navigation map module is used for generating each starting point position and a driving route in the navigation map, and the type division module is used for dividing whether the high-frequency position has periodicity. The trip planning module comprises an order receiving frequency calculation module, a periodicity determination module, an order receiving frequency prediction module, a route generation module, a priority determination module and a route change module, the order receiving frequency calculation module is electrically connected with the periodicity determination module and the order receiving frequency prediction module, the route generation module is electrically connected with the priority determination module and the navigation map module, and the route change module is electrically connected with the route generation module; the order receiving frequency calculation module is used for calculating the order receiving frequency of each high-frequency position, the periodicity determination module is used for determining whether the order receiving of the high-frequency position has periodicity, the order receiving frequency prediction module is used for predicting the order receiving frequency of a future passenger drop-off time period, the route generation module is used for generating a driving route according to the priority of the online car-hailing to a high-frequency position, and the route change module is used for re-planning a navigation route when a circle with the high-frequency position as the center and the driving route have an intersection.
3. The big data based motor vehicle information management system as claimed in claim 2 wherein: The working method of the system is as follows: S1, marking the starting point positions of each online car-hailing historical passenger pickup in a navigation map, setting a statistical period, counting the order receiving number of each starting point position in the statistical period, and determining a high-frequency position; S2, collect order time series of high-frequency locations, map into time density series according to fixed time interval, judge periodicity mode of the location, and calculate order frequency of high-frequency period; S3, read ticket purchase website API of high-frequency locations of large passenger flow transportation tool sites and large activity sites, collect ticket purchase data, record arrival and departure time corresponding to ticket purchase information, form passenger drop-off period and predict order frequency; S4, when the network car is in the state of no order, calculate the driving route and driving time from the current location to each high-frequency location, calculate the priority of each high-frequency location, and select the location with the highest priority as the driving destination; S5, find out the high-frequency locations around the driving route of the destination, take these high-frequency locations as the center of the circle, judge whether it is worth going through the high-frequency location to the destination, and update the driving route.
4. The big data based motor vehicle information management system as claimed in claim 3 wherein: In the S1, the judgment of high-frequency location is specifically: S1-1, marking the starting positions of each historical passenger carrying of the online car-hailing in the city in the navigation map, setting the statistical period as T0, and the number of times that each starting position is used as a starting point by passengers in the statistical period T0 is {a1, a2…an} n}, wherein n is the number of starting positions of the navigation map in the city, and the order receiving frequency of the starting position is calculated wherein i∈1~n, and the entry threshold is f0. When f i ≥f0, it is determined that the starting position is a high-frequency position, and the passenger drop-off period collection needs to be performed.
5. The big data based motor vehicle information management system as claimed in claim 4, wherein: In the S2, the judgment of periodicity mode is specifically: S2-1, for all the start locations which need to be collected in the passenger pickup period, determine whether the passenger pickup period is a fixed period, for each high frequency location, record its order receiving time sequence {t i1 , t i2 …t im} in T0, m is the number of orders received, map this sequence into time density sequence {x i1 , x i2 …x ik} according to fixed time interval, k is the number of time periods, do discrete Fourier transform on the time density sequence, get amplitude , where x ij is the number of orders received in a certain time period, and j∈1~k, if there is a main frequency f p such that , then the main frequency f p corresponds to a periodic passenger pickup mode, where δ is the determination coefficient, is the mean of amplitude F(f), the main frequency f p corresponds to the period length , when x ij k≥f0T0, x ij corresponds to the high frequency period, calculate the average order receiving frequency of the high frequency period in all T p periods , where is the average number of orders received in T0 of a certain passenger pickup period in all T p periods.
6. The big data based motor vehicle information management system as claimed in claim 5 wherein: In the S3, the prediction of order frequency is specifically: S3-1, in S2-1, when a certain high-frequency location does not have a periodic passenger-carrying period, if the high-frequency location is a large passenger flow vehicle station and a large event site, the API interface of the ticket purchase website corresponding to the station of the high-frequency location is read to obtain the ticket purchase information and continuously record the ticket purchase information for another T0 period, and according to the arrival and departure time in the ticket purchase information, the arrival and departure time of a certain high-frequency location in each passenger drop-off time t q is recorded q , and the order number sequence {y i1 of the passenger drop-off period [t i2 ~t0] of the high-frequency location is calculated, where p is the number of passenger drop-offs of the current high-frequency location within t0, y ip is the order number of a certain passenger drop-off period, t0 is the length of the passenger drop-off period, and q ∈ 1 ~ p iq , and the average order frequency of a certain high-frequency location in a certain passenger drop-off period is calculated , where is the historical average order number of the passenger drop-off period of the current high-frequency location. S3-2, obtaining the number of ticket information in each obtained ticket information in the ticket website, obtaining the historical average number of tickets in each drop-off period in a high-frequency location In the subsequent judgment process, the number of tickets z is With The ratio of The order frequency f is of the current drop-off period is predicted, and the formula is Where μ is the number of people influence coefficient.
7. The big data based motor vehicle information management system as claimed in claim 6 wherein: In the S4, the selection of the location with the highest priority as the driving destination is specifically: S4-1, calculating the order receiving frequency of each high-frequency position in the navigation map in real time, when the online car-hailing is in the state of not receiving orders, generating a driving route from the current position of the online car-hailing to each high-frequency position, calculating the driving time of each driving route, obtaining a driving time sequence {t1, t2…t L} , taking the current time as t e , so as to obtain the time point t e +t l , where l∈1~L, according to the type of each high-frequency position, judging whether the high-frequency position with fixed cycle is in the high-frequency period at the time point t e +t l , and judging whether the high-frequency position without fixed cycle and belonging to the large passenger flow transportation tool station and the large activity place is in the passenger drop-off period. S4-2, when a high-frequency location is in the high-frequency period at t e +t l , read the order receiving frequency f e of the high-frequency location at t l +t ij , when a high-frequency location is in the drop-off period at t e +t l , read the order receiving frequency f e of the high-frequency location at t l +t is , calculate the priority G i of the online car-hailing to a high-frequency location = αf ij - βt l , and G i = αf is - βt l , where α and β are weight coefficients, select the high-frequency location with the highest G i as the driving destination.
8. The big data based motor vehicle information management system as claimed in claim 7, wherein: In the S5, the update of the driving route is specifically: S5-1, the higher the pickup frequency of a certain starting position, the greater the probability of a ride-hailing vehicle far away from the starting position to pick up a single, after determining the driving destination in S4-2, find all high-frequency positions in the high-frequency period and the passenger drop-off period around the driving route of the vehicle, and take each high-frequency position as the center, ωf ij and ωf is as the radius to make a circle in the navigation map, ω is the radius conversion coefficient, when a certain circle with high-frequency position as the center has intersection with the driving route, re-plan the navigation route, the new route first passes through the high-frequency position with intersection with the original driving route, and then reaches the driving destination, and it needs to ensure that the time point of the new route reaching the driving destination is still in the high-frequency period and the passenger drop-off period of the driving destination.