Intelligent logistics transport capacity digital reservation management method based on big data

Abstract

The invention discloses an intelligent logistics transport capacity digital reservation management method based on big data, relates to the technical field of logistics management, and provides an intelligent logistics transport capacity digital reservation management method based on a big data platform. Through real-time acquisition, cleaning and fusion of vehicle access data and statistics of the reservation proportion of each time period, the problems of data updating lag and serious information island in a traditional method are effectively solved; data collected in real time can reflect the dynamic state of vehicles in a park in time, a self-adaptive reservation distribution mechanism is adopted, historical vehicle data and real-time feedback are utilized, the operation duration of reserved vehicles and non-reserved vehicles is compared and analyzed, a traffic flow pressure index is introduced, and dynamic adjustment of a reservation window and a reservation proportion is achieved; by balancing the operation time of the two types of vehicles, the risk of local congestion caused by concentrated reservation vehicles in peak hours is obviously reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular to a digital reservation management method for intelligent logistics capacity based on big data. Background Art

[0002] In the existing logistics capacity reservation management, most systems digitize and automate vehicle information based on technologies such as license plate recognition and RFID.

[0003] Traditional solutions generally set fixed reservation time periods, require vehicles to register in advance, and use preset rules to allocate resources. However, in actual applications, there are delays in data updates, and the on-site conditions do not completely match the system's expectations. As a result, although some vehicles that have made reservations in advance can be quickly processed into the park, vehicles that enter the park temporarily need to wait a long time. In addition, there are too many reserved vehicles during peak hours, and the system scheduling flexibility is insufficient, resulting in a very unbalanced overall operation process.

[0004] To deal with this situation, some traditional solutions generally balance the scheduling of scheduled and non-scheduled vehicles by increasing manual intervention and preset proportion control. However, this is still difficult to make up for the shortcomings of delayed data feedback and insufficient dynamic response, affecting the operational efficiency of the entire park. Therefore, a digital reservation management method for smart logistics capacity based on big data is urgently needed to alleviate the queuing chaos in the logistics park. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] The present invention provides a digital reservation management method for intelligent logistics capacity based on big data to solve the problem in the existing logistics capacity reservation management that although there is a reservation function and the reservation seems to be valid on the surface, when the reservation rate is actually too high, reservation saturation occurs, causing some vehicles to temporarily change their reservations, resulting in queuing chaos in subsequent links.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] The embodiment of the present invention provides a digital reservation management method for intelligent logistics capacity based on big data, which includes:

[0009] Step S1, establish a big data platform, collect vehicle entry and exit data in real time through license plate recognition, RFID technology and Internet of Things devices, and count the vehicle reservation ratio in each time period;

[0010] Step S2, based on historical vehicle data and real-time vehicle data, an adaptive reservation allocation method is used to automatically predict the traffic pressure during peak hours, and dynamically adjust the reservation time window and the reservation vehicle ratio;

[0011] In step S3, a prediction model is used to comprehensively predict the vehicle entry and exit situation in the future period, and some reserved vehicles are scheduled in advance according to the prediction results to enter the park during off-peak hours.

[0012] As an optimal solution of the digital reservation management method for intelligent logistics transportation capacity based on big data according to the present invention, wherein: the big data platform also cleans and fuses the vehicle entry and exit park data and the reservation ratio data.

[0013] As an optimal solution of the digital reservation management method for intelligent logistics transportation capacity based on big data according to the present invention, wherein: in step S1, the step of collecting vehicle entry and exit park data in real time through license plate recognition, RFID technology and Internet of Things devices and counting the vehicle reservation ratio in each period includes:

[0014] Define the vehicle data set for the whole period as D:

[0015] D = {d t ∣t ∈ T},

[0016] wherein, D represents the vehicle data set for the whole period, d t represents the vehicle data at the collection time t, t represents the collection time, and T represents all periods.

[0017] Represent the vehicle information obtained by license plate recognition as p t :

[0018]

[0019] wherein, p t represents the license plate information set of all vehicles within the time t, represents the license plate information of the j-th vehicle within the time t, j represents the vehicle serial number, and N t represents the total number of vehicles within the time t;

[0020] Use the size of the data set to represent the total number of vehicles, defined as n t :

[0021] n t = |d t |,

[0022] wherein, n t represents the total number of vehicles within the time t, and |d t | represents the number of elements in the set d t .

[0023] As an optimal solution of the digital reservation management method for intelligent logistics transportation capacity based on big data according to the present invention, wherein: in step S1, the step of counting the vehicle reservation ratio in each period further includes:

[0024] Define the number of reserved vehicles as n r,t :

[0025]

[0026] where n r,t represents the number of reserved vehicles within time t, I(·) represents the indicator function, which has a value of 1 when the condition in the parentheses holds and 0 otherwise, and R represents the set of reserved vehicles;

[0027] Calculate the reservation ratio for each time period. The calculation formula is:

[0028]

[0029] where ρ t represents the vehicle reservation ratio within time t, n r,t represents the number of reserved vehicles, and n t represents the total number of vehicles.

[0030] As a preferred solution of the digital reservation management method for intelligent logistics transportation capacity based on big data according to the present invention, wherein: the vehicle data includes vehicle in-and-out park data and the vehicle reservation ratio for each time period.

[0031] As a preferred solution of the digital reservation management method for intelligent logistics transportation capacity based on big data according to the present invention, wherein: during the adaptive reservation allocation process:

[0032] When dynamically adjusting the reservation window, the operation durations of reserved and non-reserved vehicles are balanced and regulated based on the operation duration distribution of historical vehicle data and the real-time operation duration distribution.

[0033] As a preferred solution of the digital reservation management method for intelligent logistics transportation capacity based on big data according to the present invention, wherein: in step S2, the steps of adopting the adaptive reservation allocation method are:

[0034] Calculate the average operation duration of reserved vehicles using historical data. The formula is:

[0035]

[0036] where represents the historical average operation duration of reserved vehicles, K1 represents the total number of historical samples, represents the operation duration sample of the kth reserved vehicle;

[0037] Define the average operation duration of non-reserved vehicles as:

[0038]

[0039] where Denote the historical average operation duration of non-reserved vehicles, denote the operation duration sample of the k-th non-reserved vehicle;

[0040] To mark the difference in operation duration between the two types of vehicles, introduce the duration error, expressed as:

[0041]

[0042] where, E1 denotes the absolute difference between the operation durations of reserved and non-reserved vehicles.

[0043] As an optimal solution of the intelligent logistics transportation capacity digital reservation management method based on big data according to the present invention, wherein: in step S2, the steps of adopting the adaptive reservation allocation method further include:

[0044] Define the number of vehicles in the current time period as m t , and set the average number of vehicles in the whole time period as The real-time traffic flow pressure index is:

[0045]

[0046] where, Q s denotes the real-time traffic flow pressure, m t denotes the number of vehicles at the current moment, denotes the average value of the number of vehicles in the whole time period;

[0047] According to the traffic flow pressure, introduce the adjustment factor w s :

[0048] w s =αQ s ,

[0049] where, w s denotes the adjustment factor, α denotes the adjustment coefficient, used to amplify or reduce the influence of the traffic flow pressure,

[0050] Dynamically adjust the reservation ratio, the formula is:

[0051]

[0052] where, denotes the reservation vehicle ratio after adjustment, ρ t denotes the original reservation ratio counted in step S1, and δ1 denotes the adjustment step of the reservation ratio.

[0053] As a preferred solution of the intelligent logistics transportation capacity digital reservation management method based on big data according to the present invention, wherein: in step S3, the step of comprehensively predicting the vehicle entry and exit situation in the future period by using a prediction model and scheduling some reserved vehicles in advance to enter the park during off-peak hours includes:

[0054] Establish a linear prediction model, and the model formula is:

[0055]

[0056] Wherein, represents the number of vehicles at the prediction time t + Δ, β0 represents the model bias parameter, β1 represents the influence coefficient of the current number of vehicles, β2 represents the influence coefficient of the original reservation ratio, and m t represents the number of vehicles at the current moment, ρ t represents the original reservation ratio, and Δ represents the prediction time interval;

[0057] Define the prediction deviation as Δm:

[0058]

[0059] Wherein, Δm represents the deviation between the predicted number of vehicles and the set traffic flow threshold, and θ represents the traffic flow threshold, which is used to define the peak traffic flow level.

[0060] As a preferred solution of the intelligent logistics transportation capacity digital reservation management method based on big data according to the present invention, wherein: in step S3, the step of comprehensively predicting the vehicle entry and exit situation in the future period by using a prediction model and scheduling some reserved vehicles in advance to enter the park during off-peak hours further includes:

[0061] According to the prediction deviation, the number of vehicles to be scheduled in advance is s:

[0062] s = min(Δm, r 3,t ),

[0063] Wherein, s represents the number of vehicles to be scheduled in advance, and r 3,t represents the number of reserved vehicles within the time t, and min(·) represents the minimum value function;

[0064] Finally, update the reservation ratio through scheduling adjustment to achieve off-peak entry into the park. The formula is:

[0065]

[0066] Wherein, represents the updated off-peak entry reservation ratio after scheduling, represents the adjusted reservation ratio in step S2, and λ represents the scheduling adjustment factor, which is used to control the influence of the number of vehicles scheduled in advance on the reservation ratio.

[0067] The beneficial effects of the present invention are as follows: The present invention provides a digital reservation management method for intelligent logistics transportation capacity based on a big data platform. By collecting, cleaning, and integrating vehicle entry and exit data in real time and counting the reservation ratios in each time period, it effectively solves the problems of lagging data update and serious information islands in traditional methods.

[0068] The data collected in real time can timely reflect the vehicle dynamics in the park. By adopting an adaptive reservation allocation mechanism, using historical vehicle data and real-time feedback, comparing and analyzing the operation durations of reserved vehicles and non-reserved vehicles, and introducing a traffic flow pressure index, the dynamic adjustment of reservation windows and reservation ratios is realized. By balancing the operation durations of the two types of vehicles, the risk of local congestion caused by the concentration of reserved vehicles during peak hours is significantly reduced.

[0069] The present invention further introduces a prediction and scheduling module, establishes a linear prediction model, comprehensively predicts the vehicle entry and exit situations in future time periods, and schedules some reserved vehicles to enter the park during off-peak hours in advance according to the prediction deviation. The advance scheduling mechanism can predict peak risks, disperse some reserved vehicles to off-peak hours, thereby optimizing resource allocation and improving the overall operation efficiency.

[0070] In summary, the present invention not only improves the real-time performance and accuracy of vehicle information collection, but also realizes the dynamic response to traffic flow fluctuations, effectively reducing the vehicle waiting time and the fluctuation of operation duration. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0072] Figure 1 It is a schematic flowchart of the digital reservation management method for intelligent logistics transportation capacity based on big data of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0073] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the drawings of the specification.

[0074] Many specific details are set forth in the following description in order to fully understand the present invention, but the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0075] Second, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that are mutually exclusive of other embodiments.

[0076] Embodiment 1, referring to Figure 1 , this embodiment provides a digital reservation management method for intelligent logistics transportation capacity based on big data, including:

[0077] Step S1, establish a big data platform, collect vehicle entry and exit data in the park in real time through license plate recognition, RFID technology, and Internet of Things devices, and count the vehicle reservation ratio in each time period;

[0078] The big data platform also cleans and fuses the vehicle entry and exit data and the reservation ratio data;

[0079] In step S1, the steps of collecting vehicle entry and exit data in real time through license plate recognition, RFID technology, and Internet of Things devices, and counting the vehicle reservation ratio in each time period include:

[0080] Define the full-time vehicle data set as D:

[0081] D = {d t ∣t ∈ T},

[0082] where D represents the full-time vehicle data set, d t represents the vehicle data at the collection time t, t represents the collection time, and T represents all time periods,

[0083] Represent the vehicle information obtained by license plate recognition as p t :

[0084]

[0085] where p t represents the set of license plate information of all vehicles within the time t, represents the license plate information of the jth vehicle within the time t, j represents the vehicle serial number, and N t represents the total number of vehicles within the time t;

[0086] Use the size of the data set to represent the total number of vehicles, defined as n t :

[0087] n t = |d t |,

[0088] where n t represents the total number of vehicles within the time t, |d t|Indicates the number of elements in set d t ;

[0089] In step S1, the step of statistically analyzing the vehicle reservation ratio within each time period further includes:

[0090] Define the number of reserved vehicles as n r,t :

[0091]

[0092] where n r,t represents the number of reserved vehicles at time t, I(·) represents the indicator function, which has a value of 1 when the condition in the parentheses holds, and 0 otherwise, and R represents the set of reserved vehicles;

[0093] Calculate the reservation ratio within each time period, and the calculation formula is:

[0094]

[0095] where ρ t represents the vehicle reservation ratio at time t, n r,t represents the number of reserved vehicles, and n t represents the total number of vehicles;

[0096] Specifically, various sensor devices are used here to collect real-time data on vehicle entry and exit from the park, and the data is cleaned and fused through a unified big data platform. By defining the vehicle data set for the entire time period, the platform can cover vehicle information for each time period. Using the vehicle information obtained through license plate recognition, the vehicle identity and quantity at each moment are determined. Then, by counting the number of reserved vehicles in each time period, the reservation ratio is calculated to quantify the vehicle flow and reservation situation in the entire park;

[0097] The data platform ensures the timeliness and integrity of the data, and can not only reflect the vehicle entry and exit status in real time, but also dynamically capture the ratio change of reserved vehicles to non-reserved vehicles;

[0098] In step S2, based on the historical vehicle data and real-time vehicle data, an adaptive reservation allocation method is adopted to automatically predict the traffic flow pressure during peak hours and dynamically adjust the reservation time window and the reservation vehicle ratio;

[0099] The vehicle data includes vehicle entry and exit data from the park and the vehicle reservation ratio within each time period;

[0100] During the process of adaptive reservation allocation:

[0101] When dynamically adjusting the reservation window, according to the vehicle operation duration distribution in the historical vehicle data and the real-time operation duration distribution, the operation durations of reserved and non-reserved vehicles are balanced and regulated;

[0102] In step S2, the steps of adopting the adaptive reservation allocation method are as follows:

[0103] Calculate the average operation duration of reserved vehicles using historical data. The formula is:

[0104]

[0105] Where, represents the historical average operation duration of reserved vehicles, K1 represents the total number of historical samples, represents the operation duration sample of the k-th reserved vehicle;

[0106] Define the average operation duration of non-reserved vehicles as:

[0107]

[0108] Where, represents the historical average operation duration of non-reserved vehicles, represents the operation duration sample of the k-th non-reserved vehicle;

[0109] To mark the difference in the operation duration of the two types of vehicles, introduce a duration error, expressed as:

[0110]

[0111] Where, E1 represents the absolute difference between the operation durations of reserved and non-reserved vehicles;

[0112] In step S2, the steps of adopting the adaptive reservation allocation method also include:

[0113] Define the number of vehicles in the current period as m t , and set the average number of vehicles in the whole period as The real-time traffic flow pressure index is:

[0114]

[0115] Where, Q s represents the real-time traffic flow pressure, m t represents the number of vehicles at the current moment, represents the average value of the number of vehicles in the whole period;

[0116] According to the traffic flow pressure, introduce an adjustment factor w s :

[0117] w s =αQ s ,

[0118] Where, w s represents the adjustment factor, α represents the adjustment coefficient, which is used to amplify or reduce the influence of traffic flow pressure,

[0119] Dynamically adjust the reservation ratio, and the formula is:

[0120]

[0121] Wherein, represents the reservation vehicle ratio after adjustment, ρ t represents the original reservation ratio counted in step S1, and δ1 represents the adjustment step of the reservation ratio;

[0122] Specifically, historical sample data and real-time traffic flow data are introduced here. The operation durations of reservation vehicles and non-reservation vehicles are counted, and a difference index of the operation duration is defined. With the help of the traffic flow pressure index composed of the real-time vehicle number and the full-time average value, the adjustment factor is further calculated, so as to dynamically correct the original reservation ratio. Through adaptive reservation allocation, the reservation window can be adjusted in advance during peak hours to reduce the risk of local congestion caused by too many reservation vehicles, and at the same time achieve the balance of the operation durations of reservation and non-reservation vehicles;

[0123] Step S3: Use a prediction model to comprehensively predict the vehicle entry and exit conditions in the future period, and schedule some reservation vehicles to enter the park during off-peak hours according to the prediction results;

[0124] In step S3, the steps of using a prediction model to comprehensively predict the vehicle entry and exit conditions in the future period and scheduling some reservation vehicles to enter the park during off-peak hours according to the prediction results include:

[0125] Establish a linear prediction model, and the model formula is:

[0126]

[0127] Wherein, represents the vehicle number at the prediction moment t + Δ, β0 represents the model bias parameter, β1 represents the current vehicle number influence coefficient, β2 represents the original reservation ratio influence coefficient, m t represents the vehicle number at the current moment, ρ t represents the original reservation ratio, and Δ represents the prediction time interval;

[0128] Define the prediction deviation as Δm:

[0129]

[0130] Wherein, Δm represents the deviation between the predicted vehicle number and the set traffic flow threshold, and θ represents the traffic flow threshold, which is used to define the peak traffic flow level;

[0131] In step S3, the steps of using a prediction model to comprehensively predict the vehicle entry and exit conditions in the future period and scheduling some reservation vehicles to enter the park during off-peak hours according to the prediction results also include:

[0132] The number of vehicles scheduled in advance is s according to the prediction deviation:

[0133] s = min(Δm, r 3,t )

[0134] where s represents the number of vehicles scheduled in advance, r 3,t represents the number of reserved vehicles within time t, and min(·) represents the minimum value function;

[0135] Finally, the reservation ratio is updated through scheduling adjustment to achieve off-peak park entry. The formula is:

[0136]

[0137] where represents the updated off-peak park entry reservation ratio after scheduling, represents the adjusted reservation ratio in step S2, and λ represents the scheduling adjustment factor used to control the impact of the number of vehicles scheduled in advance on the reservation ratio;

[0138] Specifically, a linear prediction model is established here to predict the vehicle inflow and outflow in the future period. The predicted number of vehicles is calculated by combining the current traffic flow and the reservation ratio and compared with the preset traffic flow threshold. The prediction deviation reflects the peak risk. Based on this, the number of vehicles scheduled in advance is determined. By introducing the scheduling adjustment factor, the prediction result is converted into an actual scheduling strategy to achieve off-peak park entry for reserved vehicles. This prediction and scheduling mechanism effectively alleviates the congestion risk caused by the concentration of vehicles during peak hours and improves the balance of overall resource allocation in the park and the vehicle operation efficiency at the same time.

[0139] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not restrictive. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A digital reservation management method for intelligent logistics capacity based on big data, characterized by: include, Step S1, establish a big data platform, collect vehicle entry and exit data in real time through license plate recognition, RFID technology and Internet of Things devices, and count the vehicle reservation ratio in each time period; Step S2, based on historical vehicle data and real-time vehicle data, an adaptive reservation allocation method is used to automatically predict the traffic pressure during peak hours, and dynamically adjust the reservation time window and the reservation vehicle ratio; Step S3, using the prediction model to make a comprehensive prediction of the vehicle entry and exit situation in the future time period, and dispatching some reserved vehicles in advance to enter the park in staggered time according to the prediction results.

2. The method for digital reservation management of intelligent logistics capacity based on big data as claimed in claim 1, characterized in that: The big data platform also cleans and integrates the vehicle entry and exit data and reservation ratio data.

3. A digital reservation management method for intelligent logistics capacity based on big data as claimed in claim 2, characterized in that: In step S1, the steps of collecting vehicle entry and exit data in real time through license plate recognition, RFID technology and Internet of Things devices, and collecting statistics on vehicle reservation ratios in each time period include: Define the full-time vehicle data set as D: D={d t ∣t∈T}, Where D represents the full-time vehicle data set, d t represents the vehicle data collected at time t, t represents the collection time, T represents all time periods, The vehicle information obtained by license plate recognition is represented as p t : Among them, p t represents the license plate information set of all vehicles at time t, represents the license plate information of the jth vehicle at time t, j represents the vehicle serial number, N t represents the total number of vehicles at time t; The total number of vehicles is represented by the data set size, defined as n t : n t =|d t |, Among them, n t represents the total number of vehicles at time t, |d t | represents the set d t The number of elements in .

4. A digital reservation management method for intelligent logistics capacity based on big data as claimed in claim 3, characterized in that: In step S1, the step of calculating the vehicle reservation ratio in each time period also includes: Define the number of reserved vehicles as n r,t : Among them, n r,t represents the number of reserved vehicles at time t, I(·) represents the indicator function, the value is 1 when the condition in the brackets is met, otherwise it is 0, and R represents the set of reserved vehicles; Calculate the reservation ratio in each time period using the following formula: Among them, ρ t represents the proportion of vehicle reservations within time t, n r,t Indicates the number of reserved vehicles, n t Represents the total number of vehicles.

5. A digital reservation management method for intelligent logistics capacity based on big data as claimed in claim 4, characterized in that: The vehicle data includes vehicle entry and exit data and vehicle reservation ratios in each time period.

6. A digital reservation management method for intelligent logistics capacity based on big data as claimed in claim 5, characterized in that: During the adaptive appointment allocation process: When dynamically adjusting the reservation window, the operation time of scheduled and non-scheduled vehicles is balanced and regulated based on the vehicle operation time distribution in historical vehicle data and the real-time operation time distribution.

7. A digital reservation management method for intelligent logistics capacity based on big data as claimed in claim 6, characterized in that: In step S2, the steps of using the adaptive reservation allocation method are: The average operation time of the scheduled vehicle is calculated using historical data. The formula is: in, represents the historical average operation time of the reserved vehicle, K1 represents the total number of historical samples, represents the operation time sample of the kth reserved vehicle; The average operation time of non-booked vehicles is defined as: in, Indicates the historical average operation time of non-booked vehicles. represents the operation time sample of the kth non-booked vehicle; Introducing the duration error, expressed as: Among them, E1 represents the absolute difference between the operation time of scheduled and non-scheduled vehicles.

8. A digital reservation management method for intelligent logistics capacity based on big data as claimed in claim 7, characterized in that: In step S2, the step of using the adaptive reservation allocation method also includes: Define the number of vehicles in the current period as m t , and the average number of vehicles in the whole period is The real-time traffic pressure indicators are: Among them, Q s Indicates the real-time traffic pressure, m t Indicates the number of vehicles at the current moment, It represents the average number of vehicles in the whole period; According to the traffic pressure, the adjustment factor w is introduced s : w s =αQ s , Among them, w s represents the adjustment factor, α represents the adjustment coefficient, which is used to amplify or reduce the impact of traffic pressure. Dynamically adjust the reservation ratio, the formula is: in, represents the adjusted proportion of reserved vehicles, ρ t represents the original reservation ratio counted in step S1, and δ1 represents the adjustment step of the reservation ratio.

9. A digital reservation management method for intelligent logistics capacity based on big data as claimed in claim 8, characterized in that: In step S3, the step of using the prediction model to comprehensively predict the vehicle entry and exit situation in the future period, and scheduling some reserved vehicles to enter the park in advance according to the prediction results during the staggered period includes: A linear prediction model is established, and the model formula is: in, represents the number of vehicles at the predicted time t+Δ, β0 represents the model bias parameter, β1 represents the influence coefficient of the current number of vehicles, β2 represents the influence coefficient of the original reservation ratio, and m t represents the number of vehicles at the current moment, ρ t represents the original appointment ratio, Δ represents the prediction time interval; Define the prediction deviation as Δm: Among them, Δm represents the deviation between the predicted number of vehicles and the set traffic flow threshold, and θ represents the traffic flow threshold, which is used to define the peak traffic flow level.

10. A digital reservation management method for intelligent logistics capacity based on big data as claimed in claim 9, characterized in that: In step S3, the step of using the prediction model to comprehensively predict the vehicle entry and exit situation in the future period, and scheduling some reserved vehicles to enter the park in advance according to the prediction results during the staggered period also includes: According to the forecast deviation, the number of vehicles scheduled in advance is s: s=min(Δm,r 3,t ), Among them, s represents the number of vehicles scheduled in advance, r 3,t represents the number of reserved vehicles at time t, min(·) represents the minimum value function; Finally, the reservation ratio is updated through scheduling to achieve staggered admission. The formula is: in, Indicates the updated proportion of staggered park admission reservations after scheduling. represents the reservation ratio adjusted in step S2, and λ represents the scheduling adjustment factor, which is used to control the impact of the number of vehicles scheduled in advance on the reservation ratio.

Images