CN113048997B

CN113048997B - Driving suggestion method, system, storage medium and server based on big data

Info

Publication number: CN113048997B
Application number: CN202110260806.4A
Authority: CN
Inventors: 颜蓓; 韦鹏程
Original assignee: Chongqing University of Education
Current assignee: Chongqing University of Education
Priority date: 2021-03-10
Filing date: 2021-03-10
Publication date: 2022-08-05
Anticipated expiration: 2041-03-10
Also published as: CN113048997A

Abstract

The application provides a trip suggestion method, a trip suggestion system, a storage medium and a server based on big data, wherein the method is applied to the server and comprises the following steps: the method comprises the steps of obtaining a travel inquiry request sent by a user terminal, wherein the travel inquiry request comprises a departure place, a destination and travel time; determining one or more driving paths from a departure place to a destination at the travel time, wherein each driving path comprises a plurality of road sections which are sequentially communicated; for each driving path, determining vehicle passing data of each road section in the driving path in a corresponding driving sub-period to determine a road smoothness score of the driving path in a target driving period, wherein the target driving period represents a period from travel time to arrival time, and the driving sub-period corresponding to one road section is a predicted period spent by a user vehicle to pass through a road section before the road section; and generating a travel suggestion according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestion to the user terminal.

Description

Driving suggestion method, system, storage medium and server based on big data

Technical Field

The application relates to the technical field of big data, in particular to a travel suggestion method, a travel suggestion system, a storage medium and a server based on big data.

Background

Big data refers to massive, high-growth rate and diversified information assets which need a new processing mode and have stronger decision making power, insight and flow optimization capability. "big data" is a huge data set gathered from many sources in a multivariate way, often with real-time nature. Technically, the relation between big data and cloud computing is as inseparable as the front and back of a coin, and the big data needs to be processed by a distributed computing architecture.

Vehicle driving is a conventional travel mode in modern life of people, but the vehicle holding amount is rapidly increased, so that great traffic burden is brought. Particularly, in the peak of the morning and evening and the peak of the holiday, the problem of road congestion is particularly obvious, the traveling efficiency of people is seriously influenced, and the attendance time of a large number of people is wasted.

The development and popularization of the navigation technology can well show the road condition of people in the driving process, but the reminding mode usually has real-time performance and is difficult to predict in advance, in short, people already select the attendance mode to drive on the road to know the road condition, and are difficult to predict in advance and plan the corresponding attendance mode, so that more inconveniences still exist.

Disclosure of Invention

An object of the embodiment of the application is to provide a travel suggestion method, a travel suggestion system, a storage medium and a server based on big data, so as to predict road conditions needing to be known by a user in advance, and thus provide more accurate and reasonable travel suggestions for the user, and save the attendance time of the user.

In order to achieve the above object, embodiments of the present application are implemented as follows:

in a first aspect, an embodiment of the present application provides a trip suggestion method based on big data, which is applied to a server, and the method includes: the method comprises the steps of obtaining a travel inquiry request sent by a user terminal, wherein the travel inquiry request comprises a departure place, a destination and travel time; determining one or more driving paths from the departure place to the destination at the travel time, wherein each driving path comprises a plurality of road sections which are sequentially communicated; for each driving path, determining vehicle passing data of each road section in the driving path in a corresponding driving sub-period to determine a road smoothness score of the driving path in a target driving period, wherein the target driving period represents a period from the travel time to estimated arrival time at the destination, and the driving sub-period corresponding to one road section is a period taken by the estimated user vehicle to pass through a road section before the road section; and generating a travel suggestion according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestion to the user terminal.

In the embodiment of the application, one or more driving paths (each driving path comprises a plurality of road sections which are sequentially communicated) from the departure place to the destination at the travel time are determined by acquiring the travel inquiry request (comprising the departure place, the destination and the travel time) sent by the user terminal. Therefore, the road condition can be predicted in advance before the user goes out, and a corresponding travel suggestion is given so as to give reference to the user, so that a suitable travel mode and a travel path are selected so as to save the attendance time of the user and improve the travel efficiency. For each driving route, vehicle passing data of each road section in the driving route in a corresponding driving sub-period (the estimated time period taken by the user vehicle to pass through the previous road section of the road section) can be determined, so as to determine the road smoothness score of the driving route in a target driving period (the period from the traveling time to the estimated arrival time at the destination). And generating a travel suggestion according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestion to the user terminal. By the method, the road smoothness degree of each driving path can be predicted and graded according to the vehicle traffic data of each road section in each driving path in the corresponding driving sub-period, so that the road smoothness score of the driving path is accurately predicted, and accurate suggestions and references are given to a user. For the vehicle passing data of each road section in the driving path in the corresponding driving sub-period (namely the estimated time period taken by the user vehicle to pass through the previous road section of the road section), the driving sub-period can be accurately corresponding to the road section, so that the obtained vehicle passing data can indicate the state of the road section when the user vehicle just reaches the road section, and the accuracy and precision of prediction can be greatly improved.

With reference to the first aspect, in a first possible implementation manner of the first aspect, the determining vehicle traffic data of each road segment in the driving path in the corresponding driving sub-period to determine a road smoothness score of the driving path in the target driving period includes: aiming at each road section in the driving path: acquiring the current position of a passing vehicle of the road section, and determining the estimated arrival time of the passing vehicle based on the current position, wherein the passing vehicle represents a vehicle of which a driving path covers the road section and does not completely pass through the road section, and the estimated arrival time represents the time required by the passing vehicle to drive into the road section from the current position of the passing vehicle; determining the real-time vehicle inflow of the road section at the current time according to the passing vehicle of which the current position is positioned on the road section, and determining the future vehicle inflow of the road section in the corresponding driving sub-time period according to the predicted arrival time of the passing vehicle; acquiring a road traffic index and the current vehicle number of the road section, wherein the road traffic index represents the vehicle traffic saturation number of the road section in unit time, and the current vehicle number represents the number of vehicles currently in the road section; determining the real-time vehicle outflow of the road section at the current time according to the road traffic index and the current vehicle quantity of the road section, and determining the future vehicle outflow of the road section in the corresponding driving sub-period; and then determining the road smoothness score of the driving path in the target driving time period according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of each road section.

In this implementation, the following processing is performed for each segment in the driving route: the method comprises the steps of obtaining the current position of a passing vehicle (a vehicle of which the driving path covers the road section and does not completely pass through the road section) of the road section, determining the estimated arrival time of the passing vehicle (the time required for the passing vehicle to drive into the road section from the current position) based on the current position, and determining the real-time vehicle inflow of the road section at the current time according to the passing vehicle of which the current position is located at the road section. By determining the real-time vehicle inflow of a road section in such a way, vehicles which cover the road section and do not completely pass through the road section by all driving paths can be accurately combined (namely, vehicles driving according to the driving paths can always pass through the road section), so that the real-time vehicle inflow of the road section can be accurately determined by using the current positions of the vehicles passing through the road section. And determining the future vehicle inflow of the road section in the corresponding driving sub-period according to the estimated arrival time of the passing vehicle (the time required for the passing vehicle to drive into the road section from the current position). Therefore, the future vehicle inflow amount of the road section in a certain future time period (such as a corresponding driving sub-time period) can be estimated by using the estimated arrival time of the passing vehicle, so that the congestion condition of the road section in the corresponding driving sub-time period can be conveniently predicted. Acquiring a road traffic index (the saturated number of vehicles passing through the road section in unit time) and the current vehicle number (the number of vehicles currently in the road section) of the road section; and determining the real-time vehicle outflow of the road section at the current time according to the road traffic index and the current vehicle quantity of the road section, and determining the future vehicle outflow of the road section in the corresponding driving sub-period. The real-time vehicle outflow of the road section at the current time can be accurately determined by utilizing the road traffic index and the current vehicle quantity of the road section, and the future vehicle outflow of the road section in the corresponding driving sub-period can be further accurately predicted. Then, according to the real-time vehicle inflow, the real-time vehicle outflow, the future vehicle inflow and the future vehicle outflow of each road section, the road smoothness score of the driving route in the target driving time period can be determined very accurately, so as to represent the road congestion condition of the driving route in the target driving time period and determine whether the driving route is suitable for driving, thereby giving accurate and reasonable travel suggestions to the user, and improving the travel efficiency of the user.

With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, the method for determining a real-time vehicle inflow amount of the road segment at a current time according to the passing vehicle at the current position of the road segment, and determining a future vehicle inflow amount of the road segment in a corresponding driving sub-period according to an estimated arrival time of the passing vehicle includes: determining the road section vehicle inflow which is not counted to drive into the road section from the passing vehicles of the current position on the road section; acquiring the inflow quantity of additional vehicles driven into the road section from the parking place at the current time; determining the real-time vehicle inflow according to the road section vehicle inflow and the extra vehicle inflow; obtaining the remaining vehicles in the parking place, and determining the future extra inflow of the road section in the corresponding driving sub-period according to the remaining vehicles and the extra vehicle inflow; determining the future road section inflow of the road section in the corresponding driving sub-time period according to the estimated arrival time of the passing vehicle; and determining the future vehicle inflow of the road section in the corresponding driving sub-period according to the future additional inflow and the future road section inflow.

In this implementation, the road segment has a parking place beside the road segment, the vehicle inflow of the road segment which is not statistically driven into the road segment is determined from the passing vehicles at the current position of the road segment, and the extra vehicle inflow driven into the road segment from the parking place at the current time is obtained, so that the real-time vehicle inflow can be accurately determined according to the vehicle inflow of the road segment and the extra vehicle inflow, and the vehicles driven into the road segment from the parking lot beside the road segment (for example, parking lots beside the road segment, parking lots in a small area, underground parking lots in a building, outdoor parking lots, etc.) can be considered, so that the real-time vehicle inflow can be accurately obtained. And obtaining the remaining vehicles in the parking place, and determining the future extra inflow of the road section in the corresponding driving sub-period according to the remaining vehicles and the extra vehicle inflow. By determining the future additional inflow of the road section in such a way, the influence of the remaining vehicles in the parking place on the future additional inflow can be well considered, so that the estimation of the future additional inflow can be more accurately realized. Determining the future road section inflow of the road section in the corresponding driving sub-time period according to the estimated arrival time of the passing vehicle; and determining the future vehicle inflow of the road section in the corresponding driving sub-period according to the future additional inflow and the future road section inflow. The future road section inflow of the road section in the corresponding driving sub-period can be accurately estimated through the estimated arrival time of the passing vehicle, so that the future vehicle inflow of the road section in the corresponding driving sub-period is determined according to the future extra inflow and the future road section inflow. Therefore, the method can ensure the accuracy of the determined data and is beneficial to ensuring the reasonability and the effectiveness of the travel suggestion.

With reference to the second possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, the determining the real-time vehicle inflow amount according to the road segment vehicle inflow amount and the additional vehicle inflow amount includes:

acquiring a user index of an area where the driving path is located, wherein the user index is used for indicating the proportion between registered users capable of collecting driving information and potential users incapable of collecting driving information in the area, the registered users capable of collecting driving information indicate the users collecting driving information of the server when driving, and the potential users incapable of collecting driving information indicate the users which do not collect driving information of the server when driving;

determining the real-time vehicle inflow based on a first formula, wherein the first formula is as follows:

wherein L is _in Representing the real-time vehicle inflow amount, a representing the road vehicle inflow amount, b representing the additional vehicle inflow amount, theta representing the user index, and theta being a positive number, x representing a preset constant, and x being a positive integer.

In this implementation, the user index (the ratio between the registered users in the area that can collect the driving information and the potential users that cannot collect the driving information) of the area where the driving route is located is obtained, so that the influence of the potential users on the real-time vehicle inflow and the future vehicle inflow can be well considered. By utilizing the first formula, the accurate real-time vehicle inflow amount can be determined by combining the user index according to the number of the vehicle inflow amount and the extra vehicle inflow amount of the road section, and the real-time vehicle inflow amount can be determined to be a preset number (for example, the number is 10, 50, and the like, and also can be a preset random constant in a small range, and the change of the road state of the road section cannot be influenced on the whole) according to the situation that the real-time vehicle inflow amount and the extra vehicle inflow amount of the road section are zero.

With reference to the third possible implementation manner of the first aspect, in a fourth possible implementation manner of the first aspect, the determining, according to the road traffic index and the current number of vehicles of the road segment, a real-time vehicle outflow rate of the road segment at the current time, and a future vehicle outflow rate of the road segment in a corresponding driving sub-period includes:

acquiring the outflow quantity of extra vehicles driven into the parking place from the road section at the current time;

acquiring a road section distance index of the road section, wherein the road section distance index is determined based on the road section distance of the road section, and the road section distance index is more than or equal to 1;

determining the real-time vehicle outflow based on a second formula, the second formula being:

wherein L is _out Representing the real-time vehicle outflow, y representing the current number of vehicles, z representing the road traffic index, p representing the road segment distance index, c representing the extra vehicle outflow;

determining an end vehicle from the passing vehicles, and determining extra future outflow based on the end vehicle, wherein the end vehicle represents a passing vehicle which arrives at the road section in a driving sub-period corresponding to the road section and has a destination located at the road section;

and determining the remaining vehicles of the road section in the corresponding driving sub-period according to the real-time vehicle outflow, the current vehicle quantity, the future vehicle inflow and the future extra outflow of the road section in the corresponding driving sub-period, and determining the future vehicle outflow of the road section in the corresponding driving sub-period according to the remaining vehicles and the second formula.

In this implementation, the extra vehicle outflow from the road segment entering the parking place at the current time may be obtained, and the road segment distance index of the road segment (determined based on the road segment distance of the road segment, greater than or equal to 1) may be obtained, and then the real-time vehicle outflow may be determined based on the second formula. In the second formula, the real-time vehicle outflow is calculated in different calculation manners according to the magnitude relation between the current vehicle number y and ρ z (the product of the link distance index ρ and the road traffic index z) (which can be understood as the relation between the current vehicle number y and the theoretical vehicle saturation stock ρ z of the link, and can be used for representing the degree of congestion of the vehicles on the link, wherein the theoretical vehicle saturation stock is not the largest load-carrying vehicle of the link). The method can well consider the driving influence of the road congestion degree on the road section, the traffic jam can influence the driving efficiency of vehicles on the road, and therefore the real-time vehicle outflow volume is reduced, and therefore the real-time vehicle outflow volume determined in the method can better meet the actual situation on one hand, and can also be very accurate on the other hand, and the real-time vehicle outflow volume of the road section can be better determined.

With reference to the first possible implementation manner of the first aspect, in a fifth possible implementation manner of the first aspect, the determining, according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount, and the future vehicle outflow amount of each road segment, a road smoothness score of the driving route in the target driving period includes: for each road section, judging the road state of the road section in the corresponding driving sub-period according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of the road section, wherein the road state comprises a smooth state, a slow state and a congestion state; according to the road state of each road section in the corresponding driving sub-period, scoring each road section to determine the road state score of each road section; and determining the road smoothness score of the driving path in the target driving time period according to the road state score of each road section.

In the implementation mode, the road state of each road section in one driving path in the corresponding driving sub-period can be accurately evaluated in such a mode, so that the corresponding road state score is determined, and the road smoothness score of the driving path in the target driving period is further determined. Therefore, the road state of one driving path in the target driving time period can be accurately evaluated, and a better driving suggestion is generated for the user, so that the traveling efficiency of the user is improved.

In a second aspect, an embodiment of the present application provides a big data-based travel suggestion system, which is applied to a server, and the system includes: the system comprises a request acquisition unit, a travel inquiry unit and a travel inquiry unit, wherein the request acquisition unit is used for acquiring a travel inquiry request sent by a user terminal, and the travel inquiry request comprises a departure place, a destination and travel time; a route determining unit, configured to determine one or more driving routes from the departure point to the destination at the travel time, where each driving route includes multiple road segments that are sequentially connected; the route evaluation unit is used for determining vehicle passing data of each road section in the driving route in a corresponding driving sub-period according to each driving route so as to determine a road passing score of the driving route in a target driving period, wherein the target driving period represents a period from the travel time to estimated arrival time at the destination, and the driving sub-period corresponding to one road section is a period taken by the estimated user vehicle to pass through the previous road section of the road section; and the travel suggestion unit is used for generating a travel suggestion according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestion to the user terminal.

In a third aspect, an embodiment of the present application provides a storage medium, where the storage medium includes a stored program, and when the program runs, a device where the storage medium is located is controlled to execute the big data-based travel suggestion method according to any one of the first aspect or possible implementation manners of the first aspect.

In a fourth aspect, an embodiment of the present application provides a server, which includes a memory and a processor, where the memory is configured to store information including program instructions, and the processor is configured to control execution of the program instructions, where the program instructions are loaded and executed by the processor to implement the big-data-based travel suggestion method according to the first aspect or any one of the possible implementation manners of the first aspect.

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.

Fig. 1 is an application scene diagram of a big data-based travel suggestion method according to an embodiment of the present application.

Fig. 2 is a block diagram of a server according to an embodiment of the present disclosure.

Fig. 3 is a flowchart of a big data-based travel suggestion method according to an embodiment of the present application.

Fig. 4 is a schematic diagram of an exemplary driving path provided in an embodiment of the present application.

Fig. 5 is a block diagram of a structure of a big data-based travel suggestion system according to an embodiment of the present application.

Icon: 10-a server; 11-a memory; 12-a communication module; 13-a bus; 14-a processor; 20-big data based travel advice system; 21-a request acquisition unit; 22-a path determination unit; 23-a path evaluation unit; 24-travel advice unit.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

Referring to fig. 1, fig. 1 is an application scenario diagram of a big data-based travel suggestion method according to an embodiment of the present application.

In this embodiment, the user can carry out trip suggestion inquiry through user terminal to know road conditions, thereby select suitable trip mode, select suitable trip route etc. thereby promote trip efficiency, reduce the shared time of attendance. And a travel advice system based on big data is arranged in the server 10, so that the server 10 runs a travel advice method based on big data. The server 10 runs a big data-based travel suggestion method, and can generate a corresponding travel suggestion and return the travel suggestion to the user terminal, so that a suitable travel suggestion is given to the user, and the travel efficiency of the user is improved.

Referring to fig. 2, fig. 2 is a block diagram of a server 10 according to an embodiment of the present disclosure.

In this embodiment, the server 10 may be a cloud server 10, a network server 10, a server 10 cluster, and the like, and is not limited herein.

Illustratively, the server 10 may include: a communication module 12 connected to the outside world via a network, one or more processors 14 for executing program instructions, a bus 13, and a different form of memory 11, such as a disk, ROM, or RAM, or any combination thereof. The memory 11, the communication module 12, and the processor 14 may be connected by a bus 13.

Illustratively, the memory 11 stores a program. The processor 14 can call and run these programs from the memory 11, so that the big data-based driving recommendation method can be implemented by running the programs.

Referring to fig. 3, fig. 3 is a flowchart of a big data-based travel suggestion method according to an embodiment of the present application. In the present embodiment, the big data based travel advice method is performed by the server 10, and may include step S10, step S20, step S30, and step S40.

Before going out, a user can inquire the going out condition through a user terminal, and the user terminal can be an intelligent terminal device such as a smart phone, a tablet personal computer and a personal computer. And the user can input the origin, destination, travel time, etc. of the query to the user terminal. The user terminal may generate a travel query request based on the departure location, the destination, and the travel time, and then transmit the generated travel query request to the server 10. Then the server 10 may perform step S10.

Step S10: the method comprises the steps of obtaining a travel inquiry request sent by a user terminal, wherein the travel inquiry request comprises a departure place, a destination and travel time.

In this embodiment, the server 10 may obtain a travel query request sent by a user terminal. The travel inquiry request may include an origin, a destination, and a travel time. For example, user a is on 1 month, 22 days 9: 00 Inquiry day 10: 00 travel suggestions from place a to place B, then the server 10 receives a travel query request containing the origin: a is ground; destination: b is ground; travel time: 1 month, 22 days 10: 00. of course, the current time is 1 month, 22 days, 9: 00.

after the server 10 receives the travel query request, step S20 may be performed.

Step S20: and determining one or more driving paths from the departure place to the destination at the travel time, wherein each driving path comprises a plurality of road sections which are sequentially communicated.

In this embodiment, the server 10 may determine one or more driving routes according to the departure location and the destination in the travel query request, where each driving route includes multiple road segments connected in sequence. Here, the way that the server 10 determines one or more driving paths can refer to the existing way of determining paths, which is more mature and reliable, and the efficiency of determining paths is higher.

For example, referring to fig. 4, fig. 4 is a schematic diagram of an exemplary driving path provided by the embodiment of the present application. In this embodiment, the driving route is a driving route L from a ground to a ground B, and the driving route L further includes a plurality of road segments communicated in sequence: l1, L2, L3 and L4. Of course, this is merely exemplary, and more complex road segments are usually included in practice, and should not be considered as limiting the present application.

After determining the one or more driving paths, the server 10 may execute step S30.

Step S30: and determining vehicle passing data of each road section in the driving path in the corresponding driving sub-period aiming at each driving path so as to determine the road smoothness score of the driving path in the target driving period, wherein the target driving period represents the period from the travel time to the estimated arrival time of the user vehicle to the destination, and the driving sub-period corresponding to one road section is the estimated period taken by the user vehicle to pass the previous road section of the road section.

In this embodiment, for each driving route, the server 10 may determine vehicle traffic data of each road segment in the driving route in the corresponding driving sub-period, so as to determine a road smoothness score of the driving route in the target driving period. Here, the target driving time interval may represent a time interval between the trip time and the predicted arrival time at the destination, and the driving sub-time interval corresponding to a road segment may represent a time interval that is predicted to be spent by the user vehicle to pass through a road segment before the road segment.

For example, it is expected that it takes 5 minutes for the user vehicle to arrive at the section L1 from the parking lot (place a), and the time for the user vehicle to depart from the parking lot (place a) is 10: 00, then the time for the user vehicle to reach the road segment L1 is 10: 05, therefore, the driving sub-period corresponding to the link L1 is 10: 01-10: 05. Similarly, it is expected that the user vehicle will take 10 minutes from the time it just arrived at the link L1 to the time it arrives at the link L2 (i.e., completely through the link L1), and then the travel sub-period corresponding to the link L2 is 10: 06-10: 15.

after determining the road clearance score of the driving path in the target driving period, the server 10 may execute step S40.

Step S40: and generating a travel suggestion according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestion to the user terminal.

In this embodiment, the server 10 may generate a travel suggestion according to the road smoothness score of each driving route in the target driving time period, and return the travel suggestion to the user terminal, so that the user performs travel planning based on the travel suggestion (for example, what kind of travel mode is selected, or driving according to which driving route, etc., which is not limited herein). Of course, the travel advice may include a driving route and corresponding driving time, a road smoothness score of the driving route, a road state of each road segment in the driving route, and the like, which is not limited herein.

One or more driving paths (each driving path comprises a plurality of road sections which are communicated in sequence) between the starting place and the destination at the travel time are determined by acquiring the travel inquiry request (comprising the starting place, the destination and the travel time) sent by the user terminal. Therefore, the road condition can be predicted in advance before the user goes out, and a corresponding travel suggestion is given so as to give reference to the user, so that a suitable travel mode and a travel path are selected so as to save the attendance time of the user and improve the travel efficiency. For each driving route, vehicle passing data of each road section in the driving route in a corresponding driving sub-period (the estimated time period taken by the user vehicle to pass through the previous road section of the road section) can be determined, so as to determine the road smoothness score of the driving route in a target driving period (the period from the traveling time to the estimated arrival time at the destination). And generating a travel suggestion according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestion to the user terminal. By the method, the road smoothness degree of each driving path can be predicted and graded according to the vehicle traffic data of each road section in each driving path in the corresponding driving sub-period, so that the road smoothness score of the driving path is accurately predicted, and accurate suggestions and references are given to a user. For the vehicle passing data of each road section in the driving path in the corresponding driving sub-period (namely the estimated time period taken by the user vehicle to pass through the previous road section of the road section), the driving sub-period can be accurately corresponding to the road section, so that the obtained vehicle passing data can indicate the state of the road section when the user vehicle just reaches the road section, and the accuracy and precision of prediction can be greatly improved.

In this embodiment, the specific way for determining the road smoothness score of the driving route in the target driving time period by determining the vehicle passing data of each road section in the driving route in the corresponding driving sub-time period by the server 10 may be:

for each road segment in the driving route, the server 10 may obtain a current position of a passing vehicle of the road segment, and determine an estimated arrival time of the passing vehicle based on the current position, where the passing vehicle represents a vehicle (including a vehicle that does not reach the road segment and a vehicle that reaches the road segment but does not pass the road segment) whose driving route covers the road segment and does not completely pass the road segment, and the estimated arrival time represents a time required for the passing vehicle to drive into the road segment from the current position thereof.

For example, the server 10 may determine the estimated arrival time of the passing vehicle based on the current position by: the server 10 predicts the driving distance, the driving speed, and the like required from the current position to the road section, and may comprehensively predict the driving time interval, the number of traffic lights therebetween, and the like. The existing estimation method of the estimated arrival time also has good stability, and the estimated arrival time of the passing vehicle from the current position to the road section can also be estimated by adopting the existing estimation method of the travel time, which is not limited here.

Then, the server 10 may determine the real-time vehicle inflow of the road segment at the current time according to the passing vehicle at the current position of the road segment, and determine the future vehicle inflow of the road segment in the corresponding driving sub-period according to the predicted arrival time of the passing vehicle.

And, the server 10 may obtain a road traffic index and a current number of vehicles for the road segment, wherein the road traffic index represents a vehicle traffic saturation number of the road segment in unit time, and the current number of vehicles represents a number of vehicles currently in the road segment. Then, the server 10 may determine the real-time vehicle outflow of the road segment at the current time and determine the future vehicle outflow of the road segment in the corresponding driving sub-period according to the road traffic index and the current vehicle quantity of the road segment.

After the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of each road section are determined in this way, the server 10 may determine the road smoothness score of the driving path in the target driving time period according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of each road section.

The following processing is carried out for each road section in the driving path: the method comprises the steps of obtaining the current position of a passing vehicle (a vehicle of which the driving path covers the road section and does not completely pass through the road section) of the road section, determining the estimated arrival time of the passing vehicle (the time required for the passing vehicle to drive into the road section from the current position) based on the current position, and determining the real-time vehicle inflow of the road section at the current time according to the passing vehicle of which the current position is located at the road section. By determining the real-time vehicle inflow of a road section in such a way, vehicles which cover the road section and do not completely pass through the road section by all driving paths can be accurately combined (namely, vehicles which drive according to the driving paths can pass through the road section), so that the real-time vehicle inflow of the road section can be accurately determined by using the current positions of the vehicles passing through the road section. And determining the future vehicle inflow of the road section in the corresponding driving sub-period according to the estimated arrival time of the passing vehicle (the time required for the passing vehicle to drive into the road section from the current position). Therefore, the future vehicle inflow amount of the road section in a certain future time period (such as a corresponding driving sub-time period) can be estimated by using the estimated arrival time of the passing vehicle, so that the congestion condition of the road section in the corresponding driving sub-time period can be conveniently predicted. Acquiring a road traffic index (the saturated number of vehicles passing through the road section in unit time) and the current vehicle number (the number of vehicles currently in the road section) of the road section; and determining the real-time vehicle outflow of the road section at the current time according to the road traffic index and the current vehicle quantity of the road section, and determining the future vehicle outflow of the road section in the corresponding driving sub-period. The real-time vehicle outflow of the road section at the current time can be accurately determined by utilizing the road traffic index and the current vehicle quantity of the road section, and the future vehicle outflow of the road section in the corresponding driving sub-period can be further accurately predicted. Then, according to the real-time vehicle inflow, the real-time vehicle outflow, the future vehicle inflow and the future vehicle outflow of each road section, the road smoothness score of the driving route in the target driving time period can be determined very accurately, so as to represent the road congestion condition of the driving route in the target driving time period and determine whether the driving route is suitable for driving, thereby giving accurate and reasonable travel suggestions to the user, and improving the travel efficiency of the user.

In this embodiment, one road segment may have parking places (usually, a plurality of parking places), such as a plurality of underground parking lots, a parking lot of a cell, a parking space on a roadside, and the like, which is not limited herein. Referring again to fig. 4, fig. 4 is a schematic diagram of parking locations such as parking spaces, parking lots, etc. for ease of understanding.

For example, the specific way for the server 10 to determine the real-time vehicle inflow of the road segment at the current time may be:

the server 10 may determine the vehicle inflow of the road segment which is not counted to drive into the road segment from the passing vehicles at the current position of the road segment; acquiring an inflow amount of additional vehicles driven into the road section from a parking place at the current time; and determining the real-time vehicle inflow amount according to the vehicle inflow amount of the road section and the extra vehicle inflow amount.

When determining the real-time vehicle inflow amount according to the vehicle inflow amount and the extra vehicle inflow amount of the road section, the server 10 may implement the following steps:

the server 10 may obtain a user index of an area where the driving route is located, where the user index is used to indicate a ratio between registered users in the area that can collect driving information and potential users that cannot collect driving information, where the registered users that can collect driving information indicate users whose driving information is collected by the server 10 while driving, and the potential users that cannot collect driving information indicate users whose driving information is not collected by the server 10 while driving.

The server 10 may then determine the real-time vehicle influx based on a first formula:

wherein L is _in Representing real-time vehicle inflow, a representing road vehicle inflow, b representing extra vehicle inflow, theta representing a user index, and theta being a positive number, x representing a preset constant, and x being a positive integer.

The user index of the area where the driving path is located (the ratio of the registered users in the area capable of collecting the driving information to the potential users in the area incapable of collecting the driving information) is obtained, so that the influence of the potential users on the real-time vehicle inflow and the future vehicle inflow can be well considered. By utilizing the first formula, the accurate real-time vehicle inflow amount can be determined by combining the user index according to the number of the vehicle inflow amount and the extra vehicle inflow amount of the road section, and the real-time vehicle inflow amount can be determined to be a preset number (for example, the number is 10, 50, and the like, and also can be a preset random constant in a small range, and the change of the road state of the road section cannot be influenced on the whole) according to the situation that the real-time vehicle inflow amount and the extra vehicle inflow amount of the road section are zero.

For example, the specific way for the server 10 to determine the future vehicle inflow of the road segment in the corresponding driving sub-period may be:

the server 10 may obtain the remaining vehicles in the parking place, and determine the future additional inflow amount of the road segment in the corresponding driving sub-period according to the remaining vehicles and the additional vehicle inflow amount. For example, a neural network model can be built in a parking spot for the time period, the remaining amount of the vehicle and the future additional inflow, using the collected data: and training the neural network model according to the data of the vehicle surplus and the extra vehicle inflow in a certain time period so as to realize the prediction of the future extra inflow by utilizing the trained neural network model.

Then, the server 10 may determine the future road segment inflow amount of the road segment in the corresponding driving sub-period according to the estimated arrival time of the passing vehicle. For example, the server 10 may determine that the predicted arrival time is located in the passing vehicles of the road segment in the corresponding driving sub-period and count the passing vehicles to obtain the inflow of the future road segment.

Then, the server 10 can determine the future vehicle inflow of the road segment in the corresponding driving sub-period according to the future additional inflow and the future road segment inflow.

When determining the future vehicle inflow of the road segment in the corresponding driving sub-period according to the future additional inflow and the future road segment inflow, the server 10 may implement the following steps:

the server 10 may also obtain the user index of the area where the driving route is located, and then determine the future vehicle inflow amount by combining a first variation, where the first variation is:

wherein, L' _in Representing a future vehicle inflow, a 'representing a future road segment inflow, b' representing a future extra inflow, theta representing a user index, and x representing a preset positive integer constant.

For example, the specific way for the server 10 to determine the real-time vehicle outflow of the road segment at the current time according to the road traffic index and the current vehicle number of the road segment may be as follows:

the server 10 may acquire an additional vehicle outflow amount driving from the road segment into the parking place at the current time, and the server 10 may further acquire a road segment distance index of the road segment, wherein the road segment distance index is determined based on the road segment distance of the road segment, and the road segment distance index is greater than or equal to 1. The road section distance index can be understood as a vehicle saturation number and a road traffic index which can normally pass through a road section (namely the vehicle traffic saturation number of the road section in unit time, such as the vehicle traffic per minute, for example, 240 vehicle times per minute).

The server 10 may then determine the real-time vehicle outflow based on a second formula:

wherein L is _out Representing real-time vehicle outflow, y representing the current number of vehicles, z representing the road traffic index, ρ representing the road section distance index, and c representing extra vehicle outflow.

The real-time vehicle outflow is determined based on the second formula by acquiring the extra vehicle outflow from the road segment into the parking place at the current time, acquiring the road segment distance index of the road segment (determined based on the road segment distance of the road segment, and is greater than or equal to 1). In the second formula, the real-time vehicle outflow is calculated in different calculation manners according to the magnitude relation between the current vehicle number y and ρ z (the product of the link distance index ρ and the road traffic index z) (which can be understood as the relation between the current vehicle number y and the theoretical vehicle saturation stock ρ z of the link, and can be used for representing the degree of congestion of the vehicles on the link, wherein the theoretical vehicle saturation stock is not the largest load-carrying vehicle of the link). The method can well consider the driving influence of the road congestion degree on the road section, the traffic jam can influence the driving efficiency of vehicles on the road, and therefore the real-time vehicle outflow volume is reduced, and therefore the real-time vehicle outflow volume determined in the method can better meet the actual situation on one hand, and can also be very accurate on the other hand, and the real-time vehicle outflow volume of the road section can be better determined.

For example, the specific way for the server 10 to determine the future vehicle outflow of the road segment in the corresponding driving sub-period may be:

the server 10 may determine an end vehicle indicating a passing vehicle that arrives at the road segment within a traveling sub-period corresponding to the road segment and has a destination located at the road segment, from among the passing vehicles, and determine an extra future outflow amount based on the end vehicle. A simple understanding is a vehicle arriving at the end point on this road segment.

Then, the server 10 may determine the remaining vehicles of the road segment in the corresponding driving sub-period according to the real-time vehicle outflow amount, the current vehicle quantity, the future vehicle inflow amount and the future extra outflow amount of the road segment in the corresponding driving sub-period, and determine the future vehicle outflow amount of the road segment in the corresponding driving sub-period according to the remaining vehicles and the second formula.

Here, the server 10 determines the remaining vehicles in the corresponding driving sub-period of the road segment according to the real-time vehicle outflow, the current vehicle quantity, the future vehicle inflow and the future extra outflow of the road segment in the corresponding driving sub-period, and may be regarded as the vehicle inventory in different periods of the road segment (i.e. the quantity of vehicles in the road segment in a certain period).

And the second formula is used for determining the future vehicle outflow of a road section in the corresponding driving sub-period, and can be evolved into a second variant:

wherein, L' _out Representing future vehicle outflow, y 'representing a vehicle in reserve, z representing a road traffic index, ρ representing a link distance index, and c' representing future additional outflow.

Through the first formula, the first variable, the second formula and the second variable, the real-time vehicle inflow, the future vehicle inflow, the real-time vehicle outflow and the future vehicle outflow can be accurately determined, so that accurate and reliable data can be provided for road state evaluation of a driving path, accurate evaluation is achieved, and accuracy and effectiveness of driving suggestions are guaranteed.

In this embodiment, the specific way for the server 10 to determine the road smoothness score of one driving route in the target driving time period may be:

for each road segment in the driving path, the server 10 may determine a road state of the road segment in the corresponding driving sub-period according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount, and the future vehicle outflow amount of the road segment, where the road state includes a clear state, a slow state, and a congestion state.

For example, the current road state of the road segment can be determined through the real-time vehicle inflow amount and the real-time vehicle outflow amount, and then the road state of the road segment in the corresponding driving sub-period determined on the basis of the current road state can be well considered by combining the future vehicle inflow amount and the future vehicle outflow amount.

The concrete way of determining the current road state of the road section based on the real-time vehicle inflow and the real-time vehicle outflow can be realized by adopting a classification combination way. For example, classification is performed according to the following table 1, and judgment of the road state is performed according to the following table 2:

TABLE 1

The determination of the current road state of the road segment is made using the combination of table 2 below:

TABLE 2

The determination of the current road state can be realized by the manners of table 1 and table 2, which are, of course, only exemplary descriptions herein and should not be construed as limiting the present application. In addition, a similar manner may be adopted for determining the road state of a road segment in the corresponding driving sub-period, but it should be noted that, since the real-time vehicle inflow amount and the real-time vehicle outflow amount may affect the subsequent road state, in order to more accurately determine the road state of the road segment in the corresponding driving sub-period, the current road state of the road may also be determined in combination, which is not limited herein.

After determining the road state of each road segment in the driving path in the corresponding driving sub-period, the server 10 may further score each road segment according to the road state of each road segment in the corresponding driving sub-period, and determine the road state score of each road segment. For example, the clear status, the slow status, and the congestion status are respectively given 5 points, 3 points, and 1 point, so that the road status score of each road segment can be obtained.

Then, the server 10 may determine a road smoothness score of the driving route in the target driving time period according to the road state score of each road segment. For example, the server 10 may obtain an average score of the road condition score of each road segment, thereby obtaining a road popularity score. Of course, in other alternative implementations, other ways may be used to calculate the road popularity score, and the road popularity score may be better reflected in the driving recommendation by highlighting the slowness state and the congestion state.

By the method, the road state of each road section in one driving path in the corresponding driving sub-period can be accurately evaluated, so that the corresponding road state score is determined, and the road smoothness score of the driving path in the target driving period is further determined. Therefore, the road state of one driving path in the target driving time period can be accurately evaluated, and a better driving suggestion is generated for the user, so that the traveling efficiency of the user is improved.

In that

Referring to fig. 5, fig. 5 is a block diagram illustrating a big data-based travel suggestion system 20 according to an embodiment of the present application. In the present embodiment, the big data-based travel advice system is applied to the server 10, and includes:

a request obtaining unit 21, configured to obtain a travel query request sent by a user terminal, where the travel query request includes a departure place, a destination, and a travel time.

A path determining unit 22, configured to determine one or more driving paths between the departure point and the destination at the travel time, where each driving path includes multiple road segments connected in sequence.

The path evaluation unit 23 is configured to determine, for each driving path, vehicle passing data of each road segment in the driving path in a corresponding driving sub-period, so as to determine a road passing score of the driving path in a target driving period, where the target driving period represents a period from the travel time to estimated arrival time at the destination, and the driving sub-period corresponding to one road segment is a period taken by the estimated user vehicle to pass through a road segment before the one road segment.

A travel advice unit 24. And the system is used for generating a travel suggestion according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestion to the user terminal.

In this embodiment, the path evaluation unit 23 is further configured to, for each road segment in the driving path: acquiring the current position of a passing vehicle of the road section, and determining the estimated arrival time of the passing vehicle based on the current position, wherein the passing vehicle represents a vehicle of which a driving path covers the road section and does not completely pass through the road section, and the estimated arrival time represents the time required by the passing vehicle to drive into the road section from the current position of the passing vehicle; determining the real-time vehicle inflow of the road section at the current time according to the passing vehicle of which the current position is positioned on the road section, and determining the future vehicle inflow of the road section in the corresponding driving sub-time period according to the predicted arrival time of the passing vehicle; acquiring a road traffic index and the current vehicle number of the road section, wherein the road traffic index represents the vehicle traffic saturation number of the road section in unit time, and the current vehicle number represents the number of vehicles currently in the road section; determining the real-time vehicle outflow of the road section at the current time according to the road traffic index and the current vehicle quantity of the road section, and determining the future vehicle outflow of the road section in the corresponding driving sub-period; and then, according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of each road section, determining the road smoothness score of the driving path in the target driving time period.

In this embodiment, the road segment has a parking place beside it, and the route evaluation unit 23 is further configured to determine a vehicle inflow amount of the road segment that is not statistically driven into the road segment from the passing vehicles at the current position on the road segment; acquiring an inflow amount of additional vehicles driving into the road section from the parking place at the current time; determining the real-time vehicle inflow according to the road section vehicle inflow and the extra vehicle inflow; obtaining the remaining vehicles in the parking place, and determining the future extra inflow of the road section in the corresponding driving sub-period according to the remaining vehicles and the extra vehicle inflow; determining the future road section inflow of the road section in the corresponding driving sub-time period according to the estimated arrival time of the passing vehicle; and determining the future vehicle inflow of the road section in the corresponding driving sub-period according to the future additional inflow and the future road section inflow.

In this embodiment, the path evaluation unit 23 is further configured to obtain a user index of an area where the driving path is located, where the user index is used to indicate a ratio between a registered user that can collect driving information and a potential user that cannot collect driving information in the area, where the registered user that can collect driving information indicates a user that the server 10 collects driving information while driving, and the potential user that cannot collect driving information indicates a user that the server 10 does not collect driving information while driving; determining the real-time vehicle inflow based on a first formula, wherein the first formula is as follows:

wherein L is _in Representing the real-time vehicle inflow, a representing the road vehicle inflow, b representing the additional vehicle inflow, theta representing the user index, and theta being a positive number, x representing a preset constant, and x being a positive integer.

In this embodiment, the path evaluating unit 23 is further configured to obtain an extra vehicle outflow amount from the road segment entering the parking place at the current time; acquiring a road section distance index of the road section, wherein the road section distance index is determined based on the road section distance of the road section, and the road section distance index is more than or equal to 1; determining the real-time vehicle outflow based on a second formula, the second formula being:

wherein L is _out Representing the real-time vehicle outflow, y representing the current number of vehicles, z representing the road traffic index, p representing the road segment distance index, c representing the extra vehicle outflow.

The route evaluation unit 23 is further configured to determine an end vehicle from the passing vehicles, and determine an extra future outflow amount based on the end vehicle, where the end vehicle indicates a passing vehicle that arrives at the road segment within a driving sub-period corresponding to the road segment and has a destination located in the road segment; and determining the remaining vehicles of the road section in the corresponding driving sub-period according to the real-time vehicle outflow, the current vehicle quantity, the future vehicle inflow and the future extra outflow of the road section in the corresponding driving sub-period, and determining the future vehicle outflow of the road section in the corresponding driving sub-period according to the remaining vehicles and the second formula.

In this embodiment, the path evaluating unit 23 is further configured to, for each road segment, determine a road state of the road segment in the corresponding driving sub-period according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount, and the future vehicle outflow amount of the road segment, where the road state includes a clear state, a slow state, and a congested state; according to the road state of each road section in the corresponding driving sub-period, scoring each road section to determine the road state score of each road section; and determining the road smoothness score of the driving path in the target driving time period according to the road state score of each road section.

The embodiment of the present application further provides a storage medium, where the storage medium includes a stored program, and when the program runs, the device where the storage medium is located is controlled to execute the driving recommendation method based on big data in this embodiment.

In summary, the present application provides a driving suggestion method, a driving suggestion system, a storage medium, and a server 10 based on big data, in which one or more driving paths (each including multiple road segments connected in sequence) from a departure point to a destination at a travel time are determined by obtaining a travel query request (including a departure point, a destination, and a travel time) sent by a user terminal. Therefore, the road condition can be predicted in advance before the user goes out, and a corresponding travel suggestion is given so as to give reference to the user, so that a suitable travel mode and a travel path are selected so as to save the attendance time of the user and improve the travel efficiency. For each driving route, vehicle passing data of each road section in the driving route in a corresponding driving sub-period (the estimated time period taken by the user vehicle to pass through the previous road section of the road section) can be determined, so as to determine the road smoothness score of the driving route in a target driving period (the period from the traveling time to the estimated arrival time at the destination). And generating a travel suggestion according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestion to the user terminal. By the method, the road smoothness degree of each driving path can be predicted and graded according to the vehicle traffic data of each road section in each driving path in the corresponding driving sub-period, so that the road smoothness score of the driving path is accurately predicted, and accurate suggestions and references are given to a user. For the vehicle passing data of each road section in the driving path in the corresponding driving sub-period (namely the estimated time period taken by the user vehicle to pass through the previous road section of the road section), the driving sub-period can be accurately corresponding to the road section, so that the obtained vehicle passing data can indicate the state of the road section when the user vehicle just reaches the road section, and the accuracy and precision of prediction can be greatly improved.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A big data-based travel suggestion method is applied to a server and comprises the following steps:

the method comprises the steps of obtaining a travel inquiry request sent by a user terminal, wherein the travel inquiry request comprises a departure place, a destination and travel time;

determining one or more driving paths from the departure place to the destination at the travel time, wherein each driving path comprises a plurality of road sections which are sequentially communicated;

for each driving path, determining vehicle passing data of each road section in the driving path in a corresponding driving sub-period to determine a road smoothness score of the driving path in a target driving period, wherein the target driving period represents a period from the travel time to estimated arrival time at the destination, and the driving sub-period corresponding to one road section is a period taken by the estimated user vehicle to pass through a road section before the road section;

generating a travel suggestion according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestion to the user terminal;

wherein, the determining of the vehicle traffic data of each road section in the driving path in the corresponding driving sub-period to determine the road smoothness score of the driving path in the target driving period includes:

aiming at each road section in the driving path:

acquiring the current position of a passing vehicle of the road section, and determining the estimated arrival time of the passing vehicle based on the current position, wherein the passing vehicle represents a vehicle of which a driving path covers the road section and does not completely pass through the road section, and the estimated arrival time represents the time required by the passing vehicle to drive into the road section from the current position of the passing vehicle;

determining the real-time vehicle inflow of the road section at the current time according to the passing vehicle of which the current position is positioned on the road section, and determining the future vehicle inflow of the road section in the corresponding driving sub-time period according to the predicted arrival time of the passing vehicle;

acquiring a road traffic index and the current vehicle number of the road section, wherein the road traffic index represents the vehicle traffic saturation number of the road section in unit time, and the current vehicle number represents the number of vehicles currently in the road section;

determining the real-time vehicle outflow of the road section at the current time according to the road traffic index and the current vehicle quantity of the road section, and determining the future vehicle outflow of the road section in the corresponding driving sub-period;

then, according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of each road section, determining a road smoothness score of the driving path in the target driving time period;

wherein, according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of each road section, determining the road smoothness score of the driving path in the target driving time period comprises:

for each road section, judging the road state of the road section in the corresponding driving sub-period according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of the road section, wherein the road state comprises a smooth state, a slow state and a congestion state;

according to the road state of each road section in the corresponding driving sub-period, scoring each road section to determine the road state score of each road section;

and determining the road smoothness score of the driving path in the target driving time period according to the road state score of each road section.

2. A travel suggestion method based on big data according to claim 1, wherein a parking place is provided beside the road segment, the real-time vehicle inflow of the road segment at the current time is determined according to the passing vehicle of the current position at the road segment, and the future vehicle inflow of the road segment in the corresponding driving sub-period is determined according to the predicted arrival time of the passing vehicle, comprising:

determining the road section vehicle inflow which is not counted to drive into the road section from the passing vehicles of the current position on the road section;

acquiring an inflow amount of additional vehicles driving into the road section from the parking place at the current time;

determining the real-time vehicle inflow according to the road section vehicle inflow and the extra vehicle inflow;

obtaining the remaining vehicles in the parking place, and determining the future extra inflow of the road section in the corresponding driving sub-period according to the remaining vehicles and the extra vehicle inflow;

determining the future road section inflow of the road section in the corresponding driving sub-time period according to the estimated arrival time of the passing vehicle;

and determining the future vehicle inflow of the road section in the corresponding driving sub-period according to the future additional inflow and the future road section inflow.

3. A travel suggestion method based on big data according to claim 2, wherein the determining the real-time vehicle inflow amount according to the road vehicle inflow amount and the additional vehicle inflow amount comprises:

4. A big data-based travel suggestion method according to claim 3, wherein the determining a real-time vehicle outflow of the road segment at the current time and a future vehicle outflow of the road segment in the corresponding driving sub-period according to the road traffic index and the current vehicle quantity of the road segment comprises:

acquiring the outflow quantity of the extra vehicles driving into the parking place from the road section at the current time;

5. A big data-based travel suggestion system is applied to a server and comprises the following components:

the system comprises a request acquisition unit, a travel inquiry unit and a travel inquiry unit, wherein the request acquisition unit is used for acquiring a travel inquiry request sent by a user terminal, and the travel inquiry request comprises a departure place, a destination and travel time;

a route determining unit, configured to determine one or more driving routes from the departure point to the destination at the travel time, where each driving route includes multiple road segments that are sequentially connected;

the route evaluation unit is used for determining vehicle passing data of each road section in the driving route in a corresponding driving sub-period according to each driving route so as to determine a road passing score of the driving route in a target driving period, wherein the target driving period represents a period from the travel time to estimated arrival time at the destination, and the driving sub-period corresponding to one road section is a period taken by the estimated user vehicle to pass through the previous road section of the road section;

the travel suggestion unit is used for generating travel suggestions according to the road smoothness score of each driving path in the target driving time period and returning the travel suggestions to the user terminal;

wherein, the path evaluation unit is further configured to, for each road segment in the driving path: acquiring the current position of a passing vehicle of the road section, and determining the estimated arrival time of the passing vehicle based on the current position, wherein the passing vehicle represents a vehicle of which a driving path covers the road section and does not completely pass through the road section, and the estimated arrival time represents the time required by the passing vehicle to drive into the road section from the current position of the passing vehicle; determining the real-time vehicle inflow of the road section at the current time according to the passing vehicle of which the current position is positioned on the road section, and determining the future vehicle inflow of the road section in the corresponding driving sub-time period according to the predicted arrival time of the passing vehicle; acquiring a road traffic index and the current vehicle number of the road section, wherein the road traffic index represents the vehicle traffic saturation number of the road section in unit time, and the current vehicle number represents the number of vehicles currently in the road section; determining the real-time vehicle outflow of the road section at the current time according to the road traffic index and the current vehicle quantity of the road section, and determining the future vehicle outflow of the road section in the corresponding driving sub-period; then, according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of each road section, determining a road smoothness score of the driving path in the target driving time period;

the path evaluation unit is further used for judging the road state of each road section in the corresponding driving sub-period according to the real-time vehicle inflow amount, the real-time vehicle outflow amount, the future vehicle inflow amount and the future vehicle outflow amount of the road section, wherein the road state comprises a smooth state, a slow state and a congestion state; according to the road state of each road section in the corresponding driving sub-period, scoring each road section to determine the road state score of each road section; and determining the road smoothness score of the driving path in the target driving time period according to the road state score of each road section.

6. A storage medium, characterized in that the storage medium comprises a stored program, wherein when the program runs, a device on which the storage medium is located is controlled to execute the big data based travel suggestion method according to any one of claims 1 to 4.

7. A server, comprising a memory for storing information including program instructions and a processor for controlling execution of the program instructions, the program instructions being loaded and executed by the processor to implement the big-data based travel advice method according to any one of claims 1 to 4.