Traffic industry-based investment attraction business big data integration analysis system and method

Abstract

The invention discloses an investment attraction business big data integration analysis system and method based on the traffic industry, relates to the technical field of traffic data management, and aims to monitor a road network in a radius range around a business place, divide a road into unit management areas, monitor the people flow density and the pedestrian speed of the areas, and improve the traffic management efficiency. Extracting a corresponding relation between the people flow density and the pedestrian speed, forming a correlation model between the people flow density and the pedestrian speed, obtaining vehicle using information of a current passenger, obtaining a driving time prediction value of a vehicle at a superposed part of the first path and the second path with the road section management set, and obtaining a driving time prediction value of the vehicle; the method comprises the following steps: acquiring a pedestrian path from a current passenger position to a reference place, predicting a passenger flow speed of each section on the pedestrian path, calculating a walking time prediction value of the current passenger walking to the reference place, traversing time prediction values corresponding to all get-on places in a place set, and sorting the get-on places to obtain a get-on place recommendation sequence.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic data management, and in particular to a big data integration and analysis system and method for investment promotion business based on the traffic industry. Background Art

[0002] Commercial places are gathering places for people and vehicles, and roads in commercial centers are prone to traffic congestion. When passengers in commercial centers need to use a car, vehicles cannot reach the boarding location due to road congestion, resulting in passengers not being able to get on the bus in time. In addition, large commercial places often have more than one entrance and exit. When traffic congestion occurs, it is difficult for passengers to determine which entrance and exit to take to reduce the congestion time on the road. When they find that the entrance and exit are wrong, they need to find a new entrance and exit, which increases the detour and waiting time.

[0003] The above situations will cause people and vehicles to be stranded near commercial places, further aggravating the traffic congestion around the commercial places and bringing more inconvenience to traffic participants. Summary of the invention

[0004] The purpose of the present invention is to provide a big data integration and analysis system and method for investment promotion business based on the transportation industry to solve the problems raised in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: a big data integration and analysis method for investment promotion business based on the transportation industry, the method comprising:

[0006] Step S100: monitoring the driving speed of vehicles on the road network within the radius around the commercial site, obtaining the historical driving records of vehicles in the road network, marking the congested sections in the road network, and collecting the congested sections and the sections connecting the congested sections and the commercial site to obtain associated roads, and merging all sections on the associated roads into a section management set;

[0007] Step S200: Divide the roads in the road section management set into unit management areas, monitor the pedestrian density and pedestrian speed in these areas, extract the corresponding relationship between the pedestrian density and the pedestrian speed, and form a correlation model between the pedestrian density and the pedestrian speed;

[0008] Step S300: Obtain historical riding records of all passengers in the road segment management set, collect the boarding locations in the riding records to obtain a location set, obtain the vehicle use information of the current passenger, take a certain location in the location set as a reference location, calculate a first path from the vehicle to the reference location and a second path from the reference location to the destination, and obtain a travel time prediction value of the vehicle on the first path and the second path that overlap with the road segment management set;

[0009] Step S400: obtaining a pedestrian path from the current passenger position to a reference location, obtaining a crowd density in the current pedestrian path, predicting the crowd speed of each section on the pedestrian path through an association model, and calculating a predicted walking time for the current passenger to walk to the reference location;

[0010] Step S500: Calculate the corresponding time prediction value when a certain boarding location is used based on the vehicle arrival time, the travel time prediction value and the total time the vehicle spends on the associated roads, traverse the time prediction values ​​corresponding to all boarding locations in the location set, sort the boarding locations to obtain a recommended boarding location sequence, and provide the location recommendation sequence to the current passenger.

[0011] Furthermore, step S100 includes:

[0012] Step S101: Obtain a road network within a range of r from the commercial place, monitor the driving speed of vehicles in the road network, set a vehicle driving speed threshold, and when the average driving speed of vehicles in a certain section of the road network per unit time is lower than the vehicle driving speed threshold, it is recorded as congestion in the certain section of the road;

[0013] Step S102: Obtain all congested roads in the road network within the time range of T1, collect the roads into a first associated road set, obtain all paths from the commercial premises to the roads in the first associated road set, collect all roads in the paths into a second associated road set, and collect the first associated road set and the second associated road set to obtain a road section management set;

[0014] Step S103: Obtain the boarding locations of passengers within the time range T1 in the segment management set U3, and collect the locations into a location set;

[0015] Through historical records, we collect the roads and boarding locations that need to be managed. In order to fully cover the roads around commercial places, in addition to collecting the roads that generate congestion records, we also obtain the roads connected to these roads, which together constitute the areas that need to be monitored.

[0016] Further, step S200 includes:

[0017] Step S201: a unit management area is set, and the sidewalk parts of all roads in the road segment management set are gridded according to the unit management area;

[0018] Step S202: a certain road section in the road section management set is set as a target road section, a unit time T2 is set, and the pedestrian density and pedestrian speed in each unit management area of ​​the target road section in the unit time T2 are obtained, and the average value of the pedestrian density is calculated, which is recorded as p, and the average value of the pedestrian speed is calculated, which is recorded as v, and the two tuples (p, v) are obtained by aggregation;

[0019] Step S203: obtaining a plurality of binary groups, and extracting the corresponding relationship between the pedestrian flow density and the pedestrian speed in the target road segment by using a clustering algorithm or a function fitting method, so as to obtain a first objective function of the target road segment;

[0020] For urban roads, there is a clear dividing line between the sidewalk and the roadway. The solution requires passengers to choose a suitable boarding location and provide the vehicle with detour coordinates to reduce the total time consumed in the congested area. Therefore, the vehicle speed and the walking speed of the person need to be calculated separately.

[0021] When pedestrian congestion occurs, the method of predicting pedestrian arrival time based on pedestrian walking speed will be inaccurate. Therefore, by pre-establishing a correlation model between pedestrian density and pedestrian travel speed, the pedestrian density is obtained to infer the pedestrian travel speed, where the pedestrian density is the ratio of the number of people to the unit management area.

[0022] Furthermore, step S300 includes:

[0023] Step S301: obtaining the vehicle use information of the current passenger, the vehicle use information including the current passenger position, the current position of the vehicle and the destination of the vehicle, and obtaining any boarding location from the location set as a reference location;

[0024] Step S302: Record the path from the current position of the vehicle to the reference location as a first driving path, denoted as L1, and record the path from the reference location to the destination of the vehicle as a second driving path, denoted as L2;

[0025] Step S303: Obtain a first coincident path G1 and a second coincident path G2, wherein G1 = L1∩G1,

[0026] G2=L2∩G2, obtain the predicted driving time of the vehicle on the first path and record it as qt1, and the predicted driving time on the second overlapping path and record it as qt2;

[0027] The passenger's car demand is divided into two parts. The first part is from the current position of the vehicle to the passenger's boarding location, and the second part is from the passenger's boarding location to the vehicle's destination. The advantage of this division is that different routes can be obtained by adjusting different boarding locations, and the appropriate route can be selected by comparing the route time.

[0028] Furthermore, step S400 includes:

[0029] Step S401: Obtain the path from the passenger's position to the reference location and record it as the pedestrian path R, where:

[0030] R: (r1, r2, r3, ..., rn), r1, r2, r3, ... and rn represent the first, second, third, ... and nth road segments in the pedestrian path R respectively;

[0031] Step S402: Obtain the density of pedestrian flow in each section of the pedestrian path R, obtain the pedestrian flow speed of each section of the pedestrian path R through the first objective function, calculate the predicted walking time of the passenger to the reference location in sections, and calculate the predicted walking time qt3. Among them, t i It represents the predicted value of the walking time of the i-th road in the pedestrian path R.

[0032] Furthermore, step S500 includes:

[0033] Step S501: Obtain the predicted travel time of the first path of the vehicle, record it as qt4, calculate the time ranking value KT of the reference location, KT = α × (qt 1 + qt2) + (1-α) × [qt3, qt4] max, where α is the adjustment coefficient, satisfying the condition 0 < α < 1, where [] max represents the maximum value acquisition function;

[0034] The time sorting value is divided into two calculation parts. The first part is qt1+qt2, which is the retention time of the vehicle in the area of ​​the associated road. When the vehicle can leave the associated area earlier, it not only saves the time of the driver and passengers, but also relieves the traffic congestion in the associated area. The second part is [qt3, qt4]max, the maximum value of qt3 and qt4, and the maximum value is the maximum waiting time. When qt3>qt4, the passengers are waiting for the car, and when qt4>qt3, the vehicle is waiting for people. Therefore, the maximum waiting time needs to be reduced to allow the vehicle to leave the associated area as much as possible.

[0035] The adjustment coefficient α is used to balance the importance of the vehicle's travel time in the associated area and the maximum waiting time. If the road is congested, a smaller α value can be selected to increase the weight of the maximum waiting time in the sorting process. When a certain boarding location requires a longer waiting time, this defect can be magnified by a larger (1-α) value;

[0036] Step S502: Calculate the time ranking value of each boarding location in the location set, and sort the time ranking values ​​of all boarding locations in order from low to high to obtain a time ranking sequence;

[0037] Step S503: Match the boarding locations according to the time sorting sequence to obtain a recommended boarding location sequence, and send the recommended boarding location sequence to the passenger.

[0038] In order to better implement the above method, a big data integration and analysis system for investment promotion business based on the transportation industry is also proposed. The system includes: a road management module, an associated model management module, a driving time prediction module, a walking time prediction module and a location management module, wherein the road management module is used to manage the associated roads of commercial places, the associated model management module is used to manage the associated model between the crowd density and the pedestrian speed, the driving time prediction module is used to manage the predicted value of vehicle driving, the walking time prediction module is used to manage the predicted value of passenger walking, and the location management module is used to sort the boarding locations to obtain a recommended sequence of boarding locations, and provide the location recommendation sequence to the current passenger;

[0039] Further, the road management module includes a congestion identification unit, an associated road management unit and a location set management unit, wherein the congestion identification unit is used to identify congestion information around the commercial place, the associated road management unit is used to manage a first associated road set and a second associated road set around the commercial place, and the location set management unit is used to manage the boarding locations around the commercial place in the historical data;

[0040] Furthermore, the association model management module includes: an area management unit, a crowd information management unit and an association model management unit, wherein the area management unit is used to perform grid processing on the associated roads, the crowd information management unit is used to obtain the crowd density and pedestrian speed in the associated roads, and the association model management unit is used to extract the corresponding relationship between the crowd density and the pedestrian speed to form an association model between the crowd density and the pedestrian speed;

[0041] Furthermore, the association model management module includes: an area management unit, a crowd information management unit and an association model management unit, wherein the area management unit is used to perform grid processing on the associated roads, the crowd information management unit is used to obtain the crowd density and pedestrian speed in the associated roads, and the association model management unit is used to extract the corresponding relationship between the crowd density and the pedestrian speed to form an association model between the crowd density and the pedestrian speed;

[0042] Furthermore, the walking time prediction module includes: a walking path management unit and a second time prediction unit, wherein the walking path management unit is used to manage the walking path of the current passenger, and the second time prediction unit is used to manage the walking prediction time of the current passenger;

[0043] Furthermore, the location management module includes: a time sorting value calculation unit, a location traversal unit and a sequence management unit, wherein the time sorting value calculation unit is used to calculate the time sorting value of the boarding location, the location traversal unit is used to traverse each boarding location in the location set and calculate the time sorting value of each boarding location, and the sequence management unit is used to sort each boarding location according to the time sorting value to obtain a recommended sequence of boarding locations.

[0044] Compared with the prior art, the beneficial effects of the present invention are: by separately analyzing the driving conditions of vehicles and the walking conditions of pedestrians, and providing detour solutions for vehicles and personnel based on the vehicle conditions and the vehicle use needs of pedestrians, so as to replace the nearest solutions in traditional technical solutions, avoid local congestion of roads and personnel caused by the extensive use of nearest navigation solutions, and relieve traffic pressure around commercial places. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a structural schematic diagram of a big data integration and analysis system for investment promotion business based on the transportation industry of the present invention;

[0046] Figure 2 It is a flow chart of the big data integration and analysis method of investment promotion business based on the transportation industry of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Example: Figure 1 and Figure 2 As shown, the present invention provides a technical solution, a big data integration and analysis method for investment promotion business based on the transportation industry:

[0049] Step S100: monitoring the driving speed of vehicles on the road network within the radius around the commercial site, obtaining the historical driving records of vehicles in the road network, marking the congested sections in the road network, and collecting the congested sections and the sections connecting the congested sections and the commercial site to obtain associated roads, and merging all sections on the associated roads into a section management set;

[0050] Wherein, step S100 includes:

[0051] Step S101: Obtain a road network within a range of r from the commercial place, monitor the driving speed of vehicles in the road network, set a vehicle driving speed threshold, and when the average driving speed of vehicles in a certain section of the road network per unit time is lower than the vehicle driving speed threshold, it is recorded as congestion in the certain section of the road;

[0052] Step S102: Obtain all congested roads in the road network within the time range of T1, aggregate the roads into a first associated road set, obtain all paths from commercial places to roads in the first associated road set, aggregate all roads in the paths into a second associated road set, and aggregate the first associated road set and the second associated road set to obtain a road section management set;

[0053] Step S103: Obtain the boarding locations of passengers within the time range T1 in the segment management set U3, and aggregate the locations into a location set;

[0054] In an embodiment, the boarding locations are divided by the types of different passenger vehicles, such as the boarding location for small cars and the boarding location for large shuttle buses.

[0055] Step S200: Divide the roads in the road section management set into unit management areas, monitor the pedestrian density and pedestrian speed in these areas, extract the corresponding relationship between the pedestrian density and the pedestrian speed, and form a correlation model between the pedestrian density and the pedestrian speed;

[0056] Wherein, step S200 includes:

[0057] Step S201: a unit management area is set, and the sidewalk parts of all roads in the road segment management set are gridded according to the unit management area;

[0058] Step S202: a certain road section in the road section management set is set as a target road section, a unit time T2 is set, and the pedestrian density and pedestrian speed in each unit management area of ​​the target road section in the unit time T2 are obtained, and the average value of the pedestrian density is calculated, which is recorded as p, and the average value of the pedestrian speed is calculated, which is recorded as v, and the two tuples (p, v) are obtained by aggregation;

[0059] Step S203: obtaining a plurality of binary groups, extracting the corresponding relationship between the pedestrian flow density and the pedestrian speed in the target road segment through a clustering algorithm or a function fitting method, and obtaining a first objective function of the target road segment.

[0060] Step S300: Obtain historical riding records of all passengers in the road segment management set, collect the boarding locations in the riding records to obtain a location set, obtain the vehicle use information of the current passenger, take a certain location in the location set as a reference location, calculate a first path from the vehicle to the reference location and a second path from the reference location to the destination, and obtain a travel time prediction value of the vehicle on the first path and the second path that overlap with the road segment management set;

[0061] Wherein, step S300 includes:

[0062] Step S301: obtaining the vehicle use information of the current passenger, which includes the current passenger position, the current position of the vehicle and the destination of the vehicle, and obtaining any boarding location from the location set as a reference location;

[0063] Step S302: Record the path from the current position of the vehicle to the reference location as a first driving path, denoted as L1, and record the path from the reference location to the destination of the vehicle as a second driving path, denoted as L2;

[0064] Step S303: Obtain the first overlapping path G1 and the second overlapping path G2, where G1 = L1∩G1, G2 = L2∩G2, obtain the predicted driving time of the vehicle on the first path, record it as qt1, and the predicted driving time on the second overlapping path, record it as qt2

[0065] Step S400: obtaining a pedestrian path from the current passenger position to a reference location, obtaining a crowd density in the current pedestrian path, predicting the crowd speed of each section on the pedestrian path through an association model, and calculating a predicted walking time for the current passenger to walk to the reference location;

[0066] During the implementation process, the density of human traffic is obtained through human body sensors or video recognition;

[0067] Wherein, step S400 includes:

[0068] Step S401: Obtain a path from the passenger's position to the reference location and record it as a pedestrian path R, where R: (r1, r2, r3, ..., rn), r1, r2, r3, ... and rn represent the first, second, third, ... and nth road segments in the pedestrian path R respectively;

[0069] Step S402: Obtain the density of pedestrian flow in each section of the pedestrian path R, obtain the pedestrian flow speed of each section of the pedestrian path R through the first objective function, calculate the predicted walking time of the passenger to the reference location in sections, and calculate the predicted walking time qt3. Among them, t i represents the predicted value of the walking time of the i-th section of the pedestrian path R;

[0070] In the embodiment, the length of the sidewalk portion of each road in the associated area is obtained, and the walking time prediction value is obtained by the ratio of the sidewalk length to the predicted speed.

[0071] Step S500: Calculate the time prediction value corresponding to a certain boarding location based on the vehicle arrival time, the travel time prediction value and the total time spent by the vehicle on the associated road, traverse the time prediction values ​​corresponding to all boarding locations in the location set, sort the boarding locations to obtain a recommended boarding location sequence, and provide the recommended location sequence to the current passenger;

[0072] Wherein, step S500 includes:

[0073] Step S501: Obtain the predicted travel time of the first path of the vehicle, record it as qt4, calculate the time ranking value KT of the reference location, KT = α × (qt 1 + qt2) + (1-α) × [qt3, qt4] max, where α is the adjustment coefficient, satisfying the condition 0 < α < 1, where [] max represents the maximum value acquisition function;

[0074] Step S502: Calculate the time ranking value of each boarding location in the location set, and sort the time ranking values ​​of all boarding locations in order from low to high to obtain a time ranking sequence;

[0075] Step S503: Match the boarding locations according to the time sorting sequence to obtain a recommended boarding location sequence, and send the recommended boarding location sequence to the passenger.

[0076] Embodiment 1:

[0077] A1: The passenger selects the destination and the system calls a passenger car;

[0078] A2: Generate a recommended sequence of boarding locations by executing the method in the solution;

[0079] A3: The system provides the routes corresponding to different boarding locations to passengers for reference, and passengers select the appropriate boarding location through mobile communication devices;

[0080] A4: Send the pick-up location and the corresponding route to the passenger car driver;

[0081] This solution is used for car-hailing needs initiated by passengers, such as taxis and online ride-hailing services.

[0082] Embodiment 2:

[0083] B1: The shuttle bus driver presets the commercial location and destination for picking up passengers;

[0084] B2: Generate a recommended sequence of boarding locations by executing the method in the solution;

[0085] B3: The system provides the routes corresponding to different boarding locations to the driver for reference, and the driver selects the appropriate boarding location;

[0086] B4: Send the pedestrian path corresponding to the boarding location to the passengers who need to take the shuttle bus, and guide the passengers to the boarding location;

[0087] This solution is suitable for transfer requests initiated by drivers, such as large shuttle vehicles, such as buses.

[0088] A big data integration and analysis system for investment promotion business based on the transportation industry. The system includes: a big data integration and analysis system for investment promotion business based on the transportation industry;

[0089] The road management module is used to manage the associated roads of the commercial place, wherein the road management module includes a congestion identification unit, an associated road management unit and a location set management unit, wherein the congestion identification unit is used to identify congestion information around the commercial place, the associated road management unit is used to manage a first associated road set and a second associated road set around the commercial place, and the location set management unit is used to manage the boarding locations around the commercial place in the historical data;

[0090] The correlation model management module is used to manage the correlation model between the pedestrian flow density and the pedestrian speed, wherein the correlation model management module includes: an area management unit, a pedestrian flow information management unit and an association model management unit, wherein the area management unit is used to perform grid processing on the associated roads, the pedestrian flow information management unit is used to obtain the pedestrian flow density and the pedestrian speed in the associated roads, and the association model management unit is used to extract the corresponding relationship between the pedestrian flow density and the pedestrian speed to form the correlation model between the pedestrian flow density and the pedestrian speed;

[0091] The driving time prediction module is used to manage the predicted value of vehicle driving, wherein the driving time prediction module includes: a vehicle information management unit, a path management unit and a first time prediction unit, wherein the vehicle information management unit is used for the vehicle information of the current passenger, the path management unit is used to obtain the path information of the vehicle driving, and the first time prediction unit is used to obtain the predicted time of vehicle driving;

[0092] The walking time prediction module is used to manage the predicted value of the passenger's walking, wherein the walking time prediction module includes: a walking path management unit and a second time prediction unit, wherein the walking path management unit is used to manage the walking path of the current passenger, and the second time prediction unit is used to manage the predicted walking time of the current passenger;

[0093] Among them, the location management module is used to sort the boarding locations to obtain a recommended sequence of boarding locations, and provide the recommended sequence of locations to the current passenger. Among them, the location management module includes: a time sorting value calculation unit, a location traversal unit and a sequence management unit. Among them, the time sorting value calculation unit is used to calculate the time sorting value of the boarding location, the location traversal unit is used to traverse each boarding location in the location set, calculate the time sorting value of each boarding location, and the sequence management unit is used to sort each boarding location according to the time sorting value to obtain a recommended sequence of boarding locations.

[0094] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A big data integration and analysis method for investment promotion business based on the transportation industry, characterized by: The method comprises the following steps: Step S100: monitoring the driving speed of vehicles on the road network within the radius around the commercial site, obtaining the historical driving records of vehicles in the road network, marking the congested sections in the road network, and collecting the congested sections and the sections connecting the congested sections and the commercial site to obtain associated roads, and merging all sections on the associated roads into a section management set; Step S200: dividing the roads in the road section management set into unit management areas, monitoring the pedestrian density and pedestrian speed in these areas, extracting the corresponding relationship between the pedestrian density and the pedestrian speed, and forming a correlation model between the pedestrian density and the pedestrian speed; Step S300: Obtain historical riding records of all passengers in the road segment management set, collect the boarding locations in the riding records to obtain a location set, obtain the vehicle use information of the current passenger, take a certain location in the location set as a reference location, calculate a first path from the vehicle to the reference location and a second path from the reference location to the destination, and obtain a travel time prediction value of the vehicle on the first path and the second path that overlap with the road segment management set; Step S400: obtaining a pedestrian path from the current passenger position to a reference location, obtaining a crowd density in the current pedestrian path, predicting the crowd speed of each section on the pedestrian path through an association model, and calculating a predicted walking time for the current passenger to walk to the reference location; Step S500: Calculate the corresponding time prediction value when a certain boarding location is used based on the vehicle arrival time, the travel time prediction value and the total time the vehicle spends on the associated roads, traverse the time prediction values ​​corresponding to all boarding locations in the location set, sort the boarding locations to obtain a recommended boarding location sequence, and provide the location recommendation sequence to the current passenger.

2. The big data integration and analysis method for investment promotion business based on the transportation industry according to claim 1 is characterized by: Step S100 includes: Step S101: Obtain a road network within a range of r from the commercial place, monitor the driving speed of vehicles in the road network, set a vehicle driving speed threshold, and when the average driving speed of vehicles in a certain section of the road network per unit time is lower than the vehicle driving speed threshold, it is recorded as congestion in the certain section of the road; Step S102: Obtain all congested roads in the road network within the time range of T1, collect the roads into a first associated road set, obtain all paths from the commercial premises to the roads in the first associated road set, collect all roads in the paths into a second associated road set, and collect the first associated road set and the second associated road set to obtain a road section management set; Step S103: Obtain the boarding locations of passengers within the time range T1 in the segment management set U3, and collect the locations into a location set.

3. The big data integration and analysis method for investment promotion business based on the transportation industry according to claim 2 is characterized by: Step S200 includes: Step S201: a unit management area is set, and the sidewalk parts of all roads in the road segment management set are gridded according to the unit management area; Step S202: a certain road section in the road section management set is set as a target road section, a unit time T2 is set, and the pedestrian density and pedestrian speed in each unit management area of ​​the target road section in the unit time T2 are obtained, and the average value of the pedestrian density is calculated, which is recorded as p, and the average value of the pedestrian speed is calculated, which is recorded as v, and the two tuples (p, v) are obtained by aggregation; Step S203: obtaining a plurality of binary groups, and extracting the corresponding relationship between the pedestrian flow density and the pedestrian speed in the target road segment through a clustering algorithm or a function fitting method, so as to obtain a first objective function of the target road segment.

4. The big data integration and analysis method for investment promotion business based on the transportation industry according to claim 3 is characterized by: Step S300 includes: Step S301: obtaining the vehicle use information of the current passenger, the vehicle use information including the current passenger position, the current position of the vehicle and the destination of the vehicle, and obtaining any boarding location from the location set as a reference location; Step S302: Record the path from the current position of the vehicle to the reference location as a first driving path, denoted as L1, and record the path from the reference location to the destination of the vehicle as a second driving path, denoted as L2; Step S303: Obtain a first coincident path G1 and a second coincident path G2, wherein G1 = L1∩G1, G2=L2∩G2, the predicted driving time of the vehicle on the first path is obtained and recorded as qt1, and the predicted driving time on the second overlapping path is recorded as qt2.

5. The big data integration and analysis method for investment promotion business based on the transportation industry according to claim 4 is characterized by: Step S400 includes: Step S401: Obtain the path from the passenger's position to the reference location and record it as the pedestrian path R, where: R: (r1, r2, r3, ..., rn), r1, r2, r3, ... and rn represent the first, second, third, ... and nth road segments in the pedestrian path R respectively; Step S402: Obtain the density of pedestrian flow in each section of the pedestrian path R, obtain the pedestrian flow speed of each section of the pedestrian path R through the first objective function, calculate the predicted walking time of the passenger to the reference location in sections, and calculate the predicted walking time qt3. Among them, t i It represents the predicted value of the walking time of the i-th road in the pedestrian path R.

6. The method for integrating and analyzing big data of investment promotion business based on the transportation industry according to claim 5 is characterized in that: Step S500 includes: Step S501: Obtain the predicted travel time of the first path of the vehicle, record it as qt4, calculate the time ranking value KT of the reference location, KT = α × (qt 1 + qt2) + (1-α) × [qt3, qt4] max, where α is the adjustment coefficient, satisfying the condition 0 < α < 1, where [] max represents the maximum value acquisition function; Step S502: Calculate the time ranking value of each boarding location in the location set, and sort the time ranking values ​​of all boarding locations in order from low to high to obtain a time ranking sequence; Step S503: Match the boarding locations according to the time sorting sequence to obtain a recommended boarding location sequence, and send the recommended boarding location sequence to the passenger.

7. A big data integration and analysis system for investment promotion business based on the transportation industry, used to execute the big data integration and analysis method for investment promotion business based on the transportation industry as described in any one of claims 1 to 6, characterized in that: The system includes: A road management module, an associated model management module, a travel time prediction module, a walking time prediction module and a location management module, wherein the road management module is used to manage associated roads of commercial places, the associated model management module is used to manage the associated model between crowd density and pedestrian speed, the travel time prediction module is used to manage the predicted value of vehicle travel, the walking time prediction module is used to manage the predicted value of passenger walking, and the location management module is used to sort the boarding locations to obtain a recommended boarding location sequence, and provide the location recommendation sequence to the current passenger.

8. The method for integrating and analyzing big data of investment promotion business based on the transportation industry according to claim 7 is characterized in that: The road management module includes a congestion identification unit, an associated road management unit and a location set management unit, wherein the congestion identification unit is used to identify congestion information around the commercial site, the associated road management unit is used to manage a first associated road set and a second associated road set around the commercial site, and the location set management unit is used to manage the boarding locations around the commercial site in the historical data; The associated model management module includes: an area management unit, a crowd information management unit and an associated model management unit, wherein the area management unit is used to perform grid processing on the associated roads, the crowd information management unit is used to obtain the crowd density and pedestrian speed in the associated roads, and the associated model management unit is used to extract the corresponding relationship between the crowd density and the pedestrian speed to form an associated model between the crowd density and the pedestrian speed.

9. The big data integration and analysis system for investment promotion business based on the transportation industry according to claim 7 is characterized by: The driving time prediction module includes: a vehicle information management unit, a path management unit and a first time prediction unit, wherein the vehicle information management unit is used for the vehicle information of the current passenger, the path management unit is used for obtaining the path information of the vehicle, and the first time prediction unit is used for obtaining the predicted time of the vehicle; The walking time prediction module includes: a walking path management unit and a second time prediction unit, wherein the walking path management unit is used to manage the walking path of the current passenger, and the second time prediction unit is used to manage the walking prediction time of the current passenger.

10. The big data integration and analysis system for investment promotion business based on the transportation industry according to claim 7 is characterized by: The location management module includes: a time sorting value calculation unit, a location traversal unit and a sequence management unit, wherein the time sorting value calculation unit is used to calculate the time sorting value of the boarding location, the location traversal unit is used to traverse each boarding location in the location set and calculate the time sorting value of each boarding location, and the sequence management unit is used to sort each boarding location according to the time sorting value to obtain a recommended sequence of boarding locations.

Images