Material mobilization system and method based on multi-source data analysis

Abstract

This invention discloses a material dispatching system and method based on multi-source data analysis, belonging to the field of data analysis technology. The system includes: retrieving transportation plans for material dispatching, obtaining detour records, and extracting the target road segments corresponding to the detour records; obtaining the route to be dispatched for the materials through a navigation platform, identifying congested road segments along the route, and determining the congestion probability of each congested road segment; extracting all detour intersections and lanes for each congested road segment, determining the driver's familiarity with each detour intersection and lane, and determining the driver's familiarity value for the congested road segment; and obtaining the driver's reliability based on the familiarity value and congestion probability, and selecting the optimal driver for transporting the materials to be dispatched. This invention, by analyzing detour records and selecting the optimal driver for the current materials to be dispatched based on different transportation scenarios, helps improve the efficiency of material dispatching, reduce the risk of cargo transportation delays, and enhance the overall stability of material dispatching.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, specifically to a material mobilization system and method based on multi-source data analysis. Background Technology

[0002] To ensure that resources are accurately matched to needs, the mobilization of materials must be flexibly promoted in close combination with actual scenarios. During the transportation of materials, the route is easily affected by congestion and the situation is unpredictable. This requires drivers to analyze the real-time road conditions and, with their familiarity with the route and their on-the-spot judgment, quickly identify safe, compliant, efficient and convenient detours to avoid resource mismatch or transportation delays due to route problems, and to ensure that the flow of materials is efficiently matched to the core needs.

[0003] Because different drivers have significant differences in their familiarity with routes, and the current driver dispatching and allocation does not fully incorporate the core dimensions of driver profiles for accurate matching, it is impossible to select the optimal driver for different transportation scenarios. When drivers are unfamiliar with road conditions, they may mistakenly select inefficient routes, leading to delays in cargo transportation. Alternatively, they may increase the risk of driving violations or even traffic accidents due to a lack of awareness of potential hazards, seriously affecting the overall stability of material mobilization. Summary of the Invention

[0004] The purpose of this invention is to provide a material mobilization system and method based on multi-source data analysis to solve the problems raised in the prior art.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] The material mobilization method based on multi-source data analysis includes the following steps:

[0007] Retrieve historical transportation plans for material mobilization, extract and obtain the preset transportation route for materials based on the origin and destination of the materials through the navigation platform, obtain the actual route traveled by the vehicles during transportation, and obtain detour records during transportation based on the preset route and the actual route; extract the start and end times of the detour records, and extract the target road segments corresponding to the detour records based on the vehicle's position at the start and end times;

[0008] Obtain the origin and destination of the current materials to be moved, obtain the route to be moved through the navigation platform, and obtain all congested sections of the route to be moved, as well as the congestion probability of each congested section, based on the detour records.

[0009] Extract all detour intersections corresponding to each congested road segment, retrieve the driver's historical transport records, and determine the driver's familiarity with each detour intersection based on the driver's turning behavior when passing through the detour intersections in the transport records.

[0010] Extract all detour lanes corresponding to each congested road segment. Based on the lane changes when the driver enters and exits the detour lanes in the transportation records, determine the driver's familiarity with each detour lane.

[0011] Based on the driver's familiarity with detour intersections and lanes, the driver's familiarity value with congested road sections is determined. Based on the familiarity value and the congestion probability of each congested road section, the driver's reliability is obtained, and the optimal driver for transporting the materials to be dispatched is selected.

[0012] Preferably, the target road segment corresponding to the detour record is extracted, including:

[0013] Extract a detour record R. The start time of detour record R is the time T1 when the vehicle begins its detour, and the vehicle's position at time T1 is designated as P1. The end time of detour record R is the time T2 when the vehicle ends its detour, and the vehicle's position at time T2 is designated as P2. The road segment between positions P1 and P2 is designated as S. R The time interval between time T1 and time T2 is referred to as D. R ;

[0014] Extracting section S R A certain road segment S0 and time period D within the area R For a certain time period D0 in the video, retrieve the traffic monitoring video at road segment S0, extract the monitoring screen at a certain moment in time period D0, obtain the specific location of each vehicle in the monitoring screen, obtain the vehicle C2 that is closest to a certain vehicle C1, and take the distance between vehicle C1 and vehicle C2 as the feature distance of vehicle C1; extract the feature distances of several vehicles in different monitoring screens, calculate the average value to obtain the target distance of the detour record R.

[0015] Based on the distance traveled by vehicle C1 within time period D0, the speed of vehicle C1 is obtained; based on the speeds of several vehicles, the average value is calculated to obtain the target speed of detour record R; if the target distance is less than a preset distance threshold and the target speed is less than a preset speed threshold, then road segment S0 is taken as the target road segment corresponding to detour record R.

[0016] Because congested road sections are characterized by a large number of vehicles traveling at low speeds, resulting in smaller intervals between vehicles, this scheme uses target distance and target speed to characterize the actual detour reason of detour record R. When the target distance and target speed are both small, it indicates that the actual detour reason is indeed caused by traffic congestion, and the congested road section, i.e., the target road section, can be identified.

[0017] Preferably, all congested road segments along the route to be traveled, and the congestion probability of each congested road segment, are obtained, including:

[0018] Obtain the bypass records of several historical days, get the target road sections corresponding to each bypass record, converge adjacent target road sections into a congested road section, and obtain all the congested road sections in the to-be-traveled route; obtain the departure time of the vehicle transporting the to-be-adjusted materials, and according to the historical transportation records of the vehicle traveling in the to-be-traveled route, obtain the minimum travel duration and the maximum travel duration of the current vehicle traveling in the to-be-traveled route, and predict the time periods when the vehicle passes through each congested road section according to the positions of the congested road sections in the to-be-traveled route.

[0019] Obtain the time period P when the predicted vehicle passes through a certain congested road section X X , retrieve the traffic monitoring segments of the congested road section X in each day within the historical Q days during the time period P X If in the traffic monitoring segment of the q-th day, it is determined that there is a target road section in the congested road section X, then take the q-th day as a congested date, obtain the total number of congested days Q0, and take the ratio of Q0 to Q as the congestion probability for the driver to pass through the congested road section X.

[0020] Preferably, determine the familiarity degree of the driver with each bypass intersection, including: when a certain congested road section X has a congestion historically, all the intersections passed by the driver after bypassing are regarded as the bypass intersections of the congested road section X; retrieve the historical transportation records of a certain driver dri, extract a certain bypass intersection K passed through during the transportation process, obtain the number of lanes M0 connecting the bypass intersection K, and count the total number of lanes M1 that the driver dri actually passes through and are not repeatedly counted when passing through the bypass intersection K, where 0 < M1 ≤ M0, and obtain the familiarity degree of the driver dri with the bypass intersection K: M1 / M0, and further obtain the familiarity degree with each bypass intersection.

[0021] Preferably, determine the familiarity degree of the driver with each bypass lane, including: when a certain congested road section X has a congestion historically, all the lanes passed by the driver after bypassing are regarded as the bypass lanes of the congested road section X; retrieve the historical transportation records of a certain driver dri, extract a certain bypass lane E passed through during the transportation process; obtain the number of intersection points N0 on the bypass lane E, and count the total number of intersection points N1 that the driver dri actually passes through and are not repeatedly counted when driving into the bypass lane E, where 0 < N1 ≤ N0, and obtain the familiarity degree of the driver dri with the bypass lane E: N1 / N0, and further obtain the familiarity degree with each bypass lane.

[0022] Preferably, select the optimal driver for transporting the to-be-adjusted materials, including:

[0023] According to the familiarity degree of a certain driver dri with each bypass intersection and bypass lane, obtain the familiarity value of the driver dri with the congested road section X as: , where W1 and W2 are respectively the intersection weights and lane weights, the sum of W1 and W2 is 1, e is the natural constant, A is the number of bypass intersections in the congested road section X, Gi Let di represent driver dri's familiarity with the i-th detour intersection, B represent the number of detour lanes in congested road segment X, and H represent... j The driver's familiarity with the j-th bypass lane;

[0024] Formula y=1-e -x Z is a function of y, where y takes values ​​from 0 to 1 when x > 0, and y increases as x increases. Therefore, for this scheme, the greater the driver dri's familiarity with the detour intersection and the detour lane, the greater the driver's familiarity with the congested road segment. Z takes values ​​from 0 to 1. Based on the driver dri's familiarity with each congested road segment and the congestion probability of each congested road segment, the reliability of the driver dri can be obtained.

[0025] The reliability of driver DRIs is obtained based on their familiarity with each congested road segment and the probability of congestion for each segment: Z v Let U be the driver dri's familiarity value with the i-th congested road segment. v Given the congestion probability of the i-th congested road segment, calculate the reliability of each driver, and select the driver with the highest reliability as the optimal driver for transporting the materials to be dispatched.

[0026] The material dispatch system based on multi-source data analysis includes a target road segment extraction module, a congestion probability calculation module, a familiarity calculation module, and an optimal driver selection module.

[0027] Target route extraction module: used to retrieve historical transportation plans for material mobilization, extract and obtain the preset route for material transportation through the navigation platform based on the origin and destination of the materials, obtain the actual route traveled by the vehicles during transportation, and obtain detour records during transportation based on the preset route and the actual route; extract the start and end times of the detour records, and extract the target route corresponding to the detour records based on the vehicle's position at the start and end times;

[0028] Congestion probability calculation module: used to obtain the origin and destination of the current materials to be moved, obtain the route to be moved through the navigation platform, and obtain all congested road segments on the route to be moved, as well as the congestion probability of each congested road segment, based on the detour records.

[0029] Familiarity Calculation Module: This module is used to extract all detour intersections corresponding to each congested road segment, retrieve the driver's historical transport records, and determine the driver's familiarity with each detour intersection based on the driver's turning behavior when passing through the detour intersections in the transport records; it also extracts all detour lanes corresponding to each congested road segment and determines the driver's familiarity with each detour lane based on the lane changes when the driver enters and exits the detour lanes in the transport records.

[0030] The optimal driver selection module is used to determine the driver's familiarity with congested road sections based on their familiarity with detour intersections and lanes. Based on the familiarity value and the congestion probability of each congested road section, the reliability of the driver is obtained, and the optimal driver for transporting the materials to be dispatched is selected.

[0031] Preferably, the congestion probability calculation module includes a time period prediction unit and a congestion probability calculation unit;

[0032] Time period prediction unit: used to obtain historical detour records, obtain the target road segment corresponding to each detour record, obtain all congested road segments in the route to be traveled; obtain the departure time of the vehicle transporting the materials to be dispatched, obtain the minimum and maximum travel time of the vehicle in the route to be traveled based on the historical transport records of the vehicle in the route to be traveled, and predict the time period of the vehicle passing through each congested road segment based on the position of each congested road segment in the route to be traveled.

[0033] Congestion probability calculation unit: used to obtain the predicted time period when vehicles pass through a congested road segment, retrieve traffic monitoring segments of the congested road segment in each day's time period from several historical days, and obtain the congestion probability of the driver passing through the congested road segment.

[0034] Preferably, the optimal driver selection module includes an optimal driver selection unit;

[0035] The optimal driver selection unit is used to obtain a driver's familiarity value with congested road sections based on their familiarity with each detour intersection and detour lane. Based on the driver's familiarity value with each congested road section and the congestion probability of each congested road section, the reliability of the driver is obtained. The reliability of each driver is calculated, and the optimal driver for transporting the materials to be dispatched is selected.

[0036] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides a material dispatching system and method based on multi-source data analysis, including: retrieving transportation plans for material dispatching, obtaining detour records, and extracting the target road segments corresponding to the detour records; obtaining the route to be dispatched for the materials through a navigation platform, obtaining congested road segments in the route to be dispatched, and obtaining the congestion probability of the congested road segments; extracting all detour intersections and detour lanes for each congested road segment, determining the driver's familiarity with each detour intersection and each detour lane, and determining the driver's familiarity value for the congested road segment; obtaining the driver's reliability based on the familiarity value and the congestion probability, and selecting the optimal driver for transporting the materials to be dispatched. This invention, by analyzing detour records and selecting the optimal driver for the current materials to be dispatched based on different transportation scenarios, helps to improve the efficiency of material dispatching and transportation, reduce the risk of cargo transportation delays, and enhance the overall stability of material dispatching. Attached Figure Description

[0037] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating the material mobilization method based on multi-source data analysis according to the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Example: Figure 1 As shown, this invention provides a technical solution for a material mobilization method based on multi-source data analysis, including the following steps:

[0041] (1) Retrieve the historical transportation plan for material mobilization, extract and obtain the preset route for material transportation through the navigation platform according to the origin and destination of the material, obtain the actual route traveled by the vehicle during transportation, and obtain the detour record during transportation based on the preset route and the actual route; extract the start time and end time of the detour record, and extract the target road segment corresponding to the detour record according to the position of the vehicle at the start time and end time.

[0042] Extract a detour record R. The start time of detour record R is the time T1 when the vehicle begins its detour, and the vehicle's position at time T1 is designated as P1. The end time of detour record R is the time T2 when the vehicle ends its detour, and the vehicle's position at time T2 is designated as P2. The road segment between positions P1 and P2 is designated as S. R The time interval between time T1 and time T2 is referred to as D. R ;

[0043] In the actual transportation process of material mobilization, there may be situations where road congestion affects transportation efficiency. The solution is usually for vehicles to bypass the congested section of road. For example, when the preset route is a county road, when congestion occurs, drivers usually detour via side roads or side streets. In order to improve transportation efficiency, after bypassing the congested section of road, the vehicle will return to the preset route to continue. The record of this detour via side roads or side streets is called the detour record. The start time of the detour record is the time when the vehicle starts to enter the side road or side street from the county road, and the end time is the time when the vehicle starts to enter the county road again after completing the detour.

[0044] Extracting section S R A certain road segment S0 and time period D within the area R For a certain time period D0 in the video, retrieve the traffic monitoring video at road segment S0, extract the monitoring screen at a certain moment in time period D0, obtain the specific location of each vehicle in the monitoring screen, obtain the vehicle C2 that is closest to a certain vehicle C1, and take the distance between vehicle C1 and vehicle C2 as the feature distance of vehicle C1; extract the feature distances of several vehicles in different monitoring screens, calculate the average value to obtain the target distance of the detour record R.

[0045] Based on the distance traveled by vehicle C1 within time period D0, the speed of vehicle C1 is obtained; based on the speeds of several vehicles, the average value is calculated to obtain the target speed of detour record R; if the target distance is less than a preset distance threshold and the target speed is less than a preset speed threshold, then road segment S0 is taken as the target road segment corresponding to detour record R.

[0046] (2) Obtain the origin and destination of the current material to be moved, obtain the route to be moved through the navigation platform, and obtain all the congested sections of the route to be moved and the congestion probability of each congested section based on the detour record.

[0047] Obtain detour records for several days in the past, obtain the target road segment corresponding to each detour record, merge adjacent target road segments into a congested road segment, and obtain all congested road segments in the route to be traveled; obtain the departure time of the vehicle transporting the materials to be dispatched, obtain the minimum and maximum travel time of the vehicle in the route to be traveled based on the historical transport records of the vehicle in the route to be traveled, and predict the time period of the vehicle passing through each congested road segment based on the position of each congested road segment in the route to be traveled;

[0048] The current navigation platform can obtain the driving route of the materials to be mobilized based on the starting point and the destination, take the shortest duration of the historical vehicles passing through the entire driving route as the minimum driving duration, and take the longest duration of the historical vehicles passing through the entire driving route as the maximum driving duration. Since there are many congested sections in the driving route, the time periods when the vehicle passes through each congested section can be predicted according to the locations of the congested sections. For example: If the materials to be mobilized depart at 8:00, according to the historical transportation records, the minimum driving duration is 4h and the maximum driving duration is 6h. And the congested section X is in the middle of the driving route, then the time period when the vehicle passes through the congested section X can be obtained as 10:00 to 11:00; then according to the total number of days Q0 of the target sections (if there is a target section in the congested section X on the qth day, it means that the congested section X is congested on the qth day. The more days of congestion, the greater the congestion probability for the driver passing through the congested section X. The determination of the target section is obtained based on step (1) of this embodiment, specifically by calculating the target distance and the target speed, which will not be elaborated in detail here) in the congested section X during the time period from 10:00 to 11:00 within the historical Q days, the congestion probability for the driver passing through the congested section X can be obtained, where 0 ≤ Q0 ≤ Q.

[0049] Obtain the predicted time period P when the vehicle passes through a certain congested section X X , retrieve the traffic monitoring segments of the congested section X at the time period P of each day within the historical Q days X If it is determined that there is a target section in the congested section X in the traffic monitoring segment of the qth day, then take the qth day as the congested date, obtain the total number of congested days Q0, and take the ratio of Q0 to Q as the congestion probability for the driver passing through the congested section X.

[0050] (3) Extract all the detour intersections corresponding to each congested section, retrieve the historical transportation records of the driver, and determine the familiarity of the driver with each detour intersection according to the turning behaviors of the driver when passing through the detour intersections in the transportation records.

[0051] All the intersections passed by the driver after detouring when a certain congested section X has a historical congestion are regarded as the detour intersections of the congested section X; retrieve the historical transportation records of a certain driver dri, extract a certain detour intersection K passed through during the transportation process, obtain the number of lanes M0 connecting the detour intersection K, count the total number of lanes M1 that the driver dri actually passed through and were not double-counted when passing through the detour intersection K, where 0 < M1 ≤ M0, and obtain the familiarity of the driver dri with the detour intersection K: M1 / M0, and further obtain the familiarity with each detour intersection.

[0052] For example: There are 4 lanes connecting the detour intersection K, namely L1, L2, L3, and L4. If a vehicle first approaches from lane L1 and heads to lane L2 after passing through the detour intersection K, then the total number of lanes M1 is 2 at this time. If the vehicle then approaches from lane L2 and heads to lane L3 after passing through the detour intersection K, since lane L2 has already been counted, the total number of lanes M1 is 3 at this time.

[0053] (4) Extract all the detour lanes corresponding to each congested section. Based on the lane changes when the driver enters and exits the detour lanes in the transportation records, determine the driver's familiarity with each detour lane.

[0054] When a certain congested section X has a historical congestion, all the lanes that the driver passes through after detouring are regarded as the detour lanes of the congested section X. Retrieve the historical transportation records of a certain driver dri and extract a certain detour lane E passed through during the transportation process. Obtain the number of intersection points N0 on the detour lane E, and count the total number of intersection points N1 that the driver dri actually passes through and are not double-counted when entering the detour lane E for the first time, where 0 < N1 ≤ N0. Obtain the driver dri's familiarity with the detour lane E: N1 / N0, and then obtain the familiarity with each detour lane.

[0055] For example: There are 4 intersection points connecting the detour lane E, namely K1, K2, K3, and K4. If the vehicle first enters the detour lane E from the intersection point K1, then the total number of intersection points N1 is 1 at this time. If the vehicle then enters the detour lane E from the intersection point K2, then the total number of intersection points N1 is 2 at this time. If the vehicle enters the detour lane E from the intersection point K2 for the third time, since the intersection point K2 has already been counted, the total number of intersection points N1 is 2 at this time.

[0056] (5) Determine the driver's familiarity value for each congested section based on the driver's familiarity with the detour intersections and detour lanes. Obtain the driver's reliability based on the familiarity value and the congestion probability of each congested section, and select the optimal driver for transporting the to-be-dispatched materials.

[0057] Based on a certain driver dri's familiarity with each detour intersection and detour lane, the familiarity value of the driver dri with the congested section X is: , where W1 and W2 are the intersection weights and lane weights respectively, the sum of W1 and W2 is 1, e is the natural constant, A is the number of detour intersections in the congested section X, G i is the driver dri's familiarity with the i-th detour intersection, B is the number of detour lanes in the congested section X, H j is the driver dri's familiarity with the j-th detour lane;

[0058] The reliability of driver DRIs is obtained based on their familiarity with each congested road segment and the probability of congestion for each segment: Z v Let U be the driver dri's familiarity value with the i-th congested road segment. v Given the congestion probability of the i-th congested road segment, calculate the reliability of each driver, and select the driver with the highest reliability as the optimal driver for transporting the materials to be dispatched.

[0059] This embodiment also provides a material mobilization system based on multi-source data analysis, including a target road segment extraction module, a congestion probability calculation module, a familiarity calculation module, and an optimal driver selection module. The congestion probability calculation module includes a time period prediction unit and a congestion probability calculation unit, and the optimal driver selection module includes an optimal driver selection unit. When the system executes the computer program, it implements the above-mentioned material mobilization method based on multi-source data analysis. Since the material mobilization method based on multi-source data analysis has been described in detail above, it will not be repeated here.

[0060] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0061] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0062] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for mobilizing materials based on multi-source data analysis, characterized in that, The method comprises the following steps: The historical transportation scheme of the mobilization of the material is called, the preset route of the transportation of the material is obtained through a navigation platform according to the starting point and the destination of the material, the actual route of the vehicle in the transportation process is obtained, the detour record in the transportation process is obtained based on the preset route and the actual route, the starting time and the ending time of the detour record are extracted, the target road section corresponding to the detour record is extracted according to the position of the vehicle at the starting time and the ending time; The starting point and the destination of the current to-be-mobilized material are obtained, the to-be-traveled route of the to-be-mobilized material is obtained through the navigation platform, all congestion road sections in the to-be-traveled route and the congestion probability of each congestion road section are obtained according to the detour record; The familiarity of the driver to each detour intersection is determined according to the turning behavior of the driver when passing through the detour intersection in the transportation record; The familiarity of the driver to each detour lane is determined according to the lane change of the driver when entering and leaving the detour lane in the transportation record; The familiarity value of the driver to the congestion road section is determined according to the familiarity of the driver to the detour intersection and the detour lane, the reliability of the driver is obtained according to the familiarity value and the congestion probability of each congestion road section, and the optimal driver for transporting the to-be-mobilized material is selected; The familiarity of the driver to each detour intersection is determined, including: all intersections passed by the driver after detouring when a certain congestion road section X historically occurs congestion are regarded as the detour intersection of the congestion road section X, the historical transportation record of a certain driver dri is called, a certain detour intersection K passed in the transportation process is extracted, the number M0 of lanes connected with the detour intersection K is obtained, the total number M1 of actually passed and non-repeated counted lanes of the driver dri historically passing through the detour intersection K is counted, 0 < M1 ≤ M0, the familiarity of the driver dri to the detour intersection K is obtained: M1 / M0, and then the familiarity to each detour intersection is obtained; The familiarity of the driver to each detour lane is determined, including: all lanes passed by the driver after detouring when a certain congestion road section X historically occurs congestion are regarded as the detour lane of the congestion road section X, the historical transportation record of a certain driver dri is called, a certain detour lane E passed in the transportation process is extracted, the number N0 of intersection road sections on the detour lane E is obtained, the total number N1 of actually passed and non-repeated counted intersection road sections of the driver dri historically entering the detour lane E is counted, 0 < N1 ≤ N0, the familiarity of the driver dri to the detour lane E is obtained: N1 / N0, and then the familiarity to each detour lane is obtained; Select the optimal driver to transport the animal resources to be adjusted, including: according to the familiarity of a driver dri to each roundabout intersection and roundabout lane, the familiarity value of the driver dri to the congestion section X is obtained as: Wherein, W1 and W2 are intersection weight value and lane weight value respectively, the sum of W1 and W2 is 1, e is a natural constant, A is the number of roundabout intersections in the congestion section X, G i is the familiarity of the driver dri to the i-th roundabout intersection, B is the number of roundabout lanes in the congestion section X, H j is the familiarity of the driver dri to the j-th roundabout lane; According to the familiarity value of each congestion road section of the driver dri and the congestion probability of each congestion road section, the reliability of the driver dri is obtained: , Z v is the familiarity value of the i-th congestion road section of the driver dri, U v is the congestion probability of the i-th congestion road section, the reliability of each driver is calculated, and the driver with the maximum reliability is taken as the optimal driver for transporting the to-be-adjusted materials.

2. The method for mobilization of resources based on multi-source data analysis according to claim 1, characterized in that, The target road section corresponding to the detour record is extracted, including: extracting a certain detour record R, the start time of the detour record R being the time T1 at which the vehicle starts detouring, the position of the vehicle at the time T1 being P1, the end time of the detour record R being the time T2 at which the vehicle ends detouring, the position of the vehicle at the time T2 being P2, the road section between the positions P1 to P2 being S R , the period between the time T1 and the time T2 being D R ; extracting a section S0 in the section S R and a time period D0 in the time period D R ; calling traffic monitoring video at the section S0, extracting monitoring picture at a time in the time period D0, obtaining specific position of each vehicle in the monitoring picture, obtaining vehicle C2 closest to vehicle C1, taking distance between the vehicle C1 and the vehicle C2 as characteristic distance of the vehicle C1; extracting characteristic distance of several vehicles in different monitoring pictures, and obtaining target distance of the detour record R by averaging. The driving speed of the vehicle C1 is obtained according to the driving distance of the vehicle C1 in the time period D0, the target speed of the detour record R is obtained by averaging the driving speeds of a plurality of vehicles, if the target distance is less than the preset distance threshold value and the target speed is less than the preset speed threshold value, the road section S0 is regarded as the target road section corresponding to the detour record R.

3. The method for mobilization of resources based on multi-source data analysis according to claim 2, characterized in that, All congestion road sections in the to-be-traveled route and the congestion probability of each congestion road section are obtained, including: The historical detour records of several days are acquired, the target road sections corresponding to each detour record are obtained, adjacent target road sections are aggregated as a congestion road section, and all congestion road sections in the to-be-traveled route are obtained; the departure time of the vehicle transporting the to-be-adjusted material is acquired, the minimum travel duration and the maximum travel duration of the current vehicle traveling in the to-be-traveled route are obtained according to the historical transportation records of the vehicle traveling in the to-be-traveled route, and the time period of the vehicle passing through each congestion road section is predicted according to the positions of the congestion road sections in the to-be-traveled route; Obtain the predicted time period P for vehicles to pass through a congested road segment X. X Retrieve historical data for Q days, and pinpoint the location of congested road segment X within each day's time period P. X If, in the traffic monitoring segment on day q, it is determined that there is a target road segment in the congested road segment X, then day q is taken as the congestion date, and the total number of congestion days Q0 is obtained. The ratio of Q0 to Q is taken as the congestion probability of a driver passing through the congested road segment X.

4. A material mobilization system based on multi-source data analysis, for performing the material mobilization method based on multi-source data analysis according to any one of claims 1-3, characterized in that, The system comprises a target road section extraction module, a congestion probability calculation module, a familiarity calculation module and an optimal driver selection module; The target road section extraction module is used to call historical transportation schemes of material adjustment, extract and follow the starting place and the destination of the material, obtain a preset route of the material transportation through a navigation platform, acquire an actual route traveled by the vehicle in the transportation process, obtain detour records in the transportation process based on the preset route and the actual route, extract the starting time and the ending time of the detour records, and extract the target road section corresponding to the detour records according to the positions of the vehicle at the starting time and the ending time; The congestion probability calculation module is used to acquire the starting place and the destination of the current to-be-adjusted material, obtain a to-be-traveled route of the to-be-adjusted material through a navigation platform, obtain all congestion road sections in the to-be-traveled route and the congestion probability of each congestion road section according to the detour records; The familiarity calculation module is used to extract all detour intersections corresponding to each congestion road section, call historical transportation records of the driver, determine the familiarity of the driver to each detour intersection according to the turning behavior of the driver when passing through the detour intersection in the transportation records, extract all detour lanes corresponding to each congestion road section, and determine the familiarity of the driver to each detour lane according to the lane change of the driver when entering and leaving the detour lane in the transportation records; The optimal driver selection module is used to determine the familiarity value of the driver to the congestion road section according to the familiarity of the driver to the detour intersection and the detour lane, obtain the reliability of the driver according to the familiarity value and the congestion probability of each congestion road section, and select the optimal driver transporting the to-be-adjusted material.

5. The multi-source data analysis based logistics mobilization system of claim 4, wherein, The congestion probability calculation module comprises a time period prediction unit and a congestion probability calculation unit; The time period prediction unit is used to acquire historical detour records, obtain the target road sections corresponding to each detour record, and obtain all congestion road sections in the to-be-traveled route; acquire the departure time of the vehicle transporting the to-be-adjusted material, obtain the minimum travel duration and the maximum travel duration of the current vehicle traveling in the to-be-traveled route according to the historical transportation records of the vehicle traveling in the to-be-traveled route, and predict the time period of the vehicle passing through each congestion road section according to the positions of the congestion road sections in the to-be-traveled route; The congestion probability calculation unit is used to acquire the predicted time period of the vehicle passing through a certain congestion road section, call traffic monitoring segments of the congestion road section in each day of the time period in the historical several days, and obtain the congestion probability of the driver passing through the congestion road section.

6. The multi-source data analysis based logistics mobilization system of claim 4, wherein, The optimal driver selection module comprises an optimal driver selection unit. The optimal driver selection unit is used to obtain the familiarity value of the driver to the congestion road section according to the familiarity of the driver to each bypass intersection and bypass lane, obtain the reliability of the driver based on the familiarity value of the driver to each congestion road section and the congestion probability of each congestion road section, calculate the reliability of each driver, and select the optimal driver for transporting the material to be adjusted.

Images