Intelligent logistics transportation system and method based on big data fusion

Abstract

The invention discloses an intelligent logistics transportation system and method based on big data fusion, and belongs to the technical field of logistics transportation, and the method specifically comprises the steps: obtaining the planned transfer cargo information of a delayed flight and various data of all flights of a current airport, and carrying out the preprocessing; setting a future time window, screening out flights which normally take off in the time window and of which the flight end points are consistent with the delayed flights, calculating the predicted loading duration of the screened flights, and carrying out three times of screening according to the predicted loading duration to obtain remaining selectable flights; grouping the cargos according to the cargo orders and calculating the weight of each group of cargos; and calculating the sum of the available load and the available loading volume of the flight, comparing the sum with the total weight and the total volume of the cargos to be transferred, and according to the comparison result, allocating the cargos according to the weight priority of each group of cargos, or selecting the flight and allocating the cargos according to the available load and the available loading volume of the flight. According to the invention, the transportation cost during flight logistics transfer is reduced.

Description

Technical Field

[0001] The present invention relates to the field of logistics and transportation technology, and in particular to an intelligent logistics and transportation system and method based on big data fusion. Background Art

[0002] The aviation logistics industry is a strategic industrial system that uses air transportation and other methods to achieve the physical flow of goods and extend services. It integrates multiple service functions such as transportation, warehousing, distribution, and information, and is an important support for the modern industrial system.

[0003] One of the major advantages of air logistics is its timeliness. Air transport can achieve rapid delivery of goods across cities or countries. However, in actual transportation, due to flight delays, in order to ensure the timeliness of air logistics, it is sometimes necessary to transship the goods loaded on the flight.

[0004] However, the remaining available volume and load capacity of the cabin of the aircraft used for transfer may not be sufficient to carry all the goods that need to be transferred. At this time, multiple transfer aircraft are needed to complete the transfer task together. If the best cargo distribution plan cannot be found in time, it will cause economic losses to air logistics. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent logistics transportation system and method based on big data fusion to solve the following technical problems:

[0006] In air logistics transportation, there are flight delays, and the goods on the delayed flights need to be transferred by multiple aircraft. If the best cargo distribution plan cannot be found in time, some important goods may not be transferred first, and the flight load factor cannot be maximized, causing economic losses to air logistics.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An intelligent logistics and transportation system based on big data fusion, comprising:

[0009] The data collection module is used to obtain the planned transshipment cargo information of delayed flights and collect and pre-process various data of all flights at the current airport, including flight scheduled departure time, flight scheduled arrival time, flight route, available loading volume and available load;

[0010] The flight screening module is used to set a future time window, screen out flights that take off normally from the current airport within the future time window, and screen out flights whose destination is the same as the delayed flight for the second time, calculate the estimated loading time L of each flight according to the available load, and screen out flights whose departure time is less than the corresponding estimated loading time L for the third time, mark the number of flights remaining after the third screening as n, and obtain the total time of n flights from the scheduled arrival time;

[0011] The cargo weight module is used to divide the cargo planned for transshipment into m groups according to the cargo order, obtain the value mark and expected delivery time of each group of cargo, and calculate the weight of each group of cargo by the TOPSIS method;

[0012] The transfer allocation module is used to mark the total available load and available loading volume of n flights as M1 and V1 respectively, and mark the total weight and total volume of planned transfer goods as M2 and V2 respectively. If any of M1<M2 and V1<V2 exists, the planned transfer goods are allocated according to the weight priority of each group of goods; if M1≥M2 and V1≥V2 exist at the same time, the n flights are sorted from small to large according to the available load, and the flights are selected in sequence until the available load and available loading volume of the selected flight are both greater than the total weight and total volume of the planned transfer goods, and the planned transfer goods are allocated to the selected flight.

[0013] As a further solution of the present invention: in the data collection module, the preprocessing includes data storage format standardization, data compression and data partitioning, wherein:

[0014] The method for standardizing the data storage format is to unify the storage format of all collected data into XML or JSON format;

[0015] The data compression method is to use Huffman coding, LZW coding or RLE coding for lossless compression;

[0016] The data partitioning method is to construct a time zone, a space zone and a cargo zone, wherein the scheduled flight departure time and the scheduled flight arrival time are stored in the time zone, the flight route, available loading volume and available load are stored in the space zone, and the planned transfer cargo information of the delayed flight is stored in the cargo zone, wherein the planned transfer cargo information includes: cargo volume, cargo weight and cargo value.

[0017] As a further solution of the present invention: the specific process of calculating the expected loading time L is:

[0018] Get the average cargo loading rate of the current airport and the available load of each flight screened out for the second time. According to the average loading rate and available load, calculate the time required for each flight to load the available load and mark it as the estimated loading time L of the flight.

[0019] As a further solution of the present invention: during the third screening, if the flight has landed at the current airport, the value of the current time from the scheduled departure time of the flight is calculated and compared with the L corresponding to the flight; if the flight has not landed at the current airport, the value of the time from the expected arrival time of the flight at the current airport to the next scheduled departure time is calculated and compared with the L corresponding to the flight.

[0020] As a further solution of the present invention: the expected delivery time of the goods refers to the time it takes for each group of goods to be transported to the flight terminal airport via the delayed flight and then transported from the terminal airport to the corresponding customer of each group of goods.

[0021] As a further solution of the present invention: the specific steps of calculating the weight of each group of goods by the TOPSIS method are:

[0022] Mark the values ​​of m groups of goods as s1, s2, ..., s m , the expected delivery time of the goods is marked as t1, t2, ..., t m , and mark the maximum value of the expected delivery time of the goods as t max ;

[0023] The expected delivery time for each group of goods is calculated using t max -t j Perform a forward operation and reassign the values. After the assignment, re-mark the expected delivery time of m groups of goods as e1, e2, ..., e m , j = 1, 2, ..., m;

[0024] The value of each group of goods and the expected delivery time of the goods are standardized. The standardized calculation formula is:

[0025]

[0026]

[0027] s' j With e' j Indicates the standardized value of goods and the expected delivery time of goods;

[0028] Will s' j With e' j The maximum and minimum values ​​in are marked as s + , e + and -, e - , calculate the Euclidean distance between each group of goods and the maximum and minimum values ​​respectively, and mark them as D j + and D j — , the weight of each group of goods is calculated according to the Euclidean distance, and the calculation formula is:

[0029] w j =D j — / (D j + +D j — );

[0030] where w j Indicates the weight of each group of goods.

[0031] As a further solution of the present invention: if any of the conditions M1<M2 and V1<V2 exists, the specific steps of allocating the goods are:

[0032] S01: Sort the flights in ascending order according to the total duration of the transfer process and mark them as A1.

[0033] A2, ..., A n , sort each group of goods in descending order according to weight, and mark them as B1,

[0034] B2, ..., B m ;

[0035] S02: Select a group of goods B one by one starting from B1 j , select B according to the flight arrangement order j Match all flights in turn. If B j The volume and weight of the flight do not exceed that of a certain flight A i Available loading volume and available load, then B j Assign to A i , i and j are index values, i = 1, 2, ..., n, j = 1, 2, ..., m;

[0036] S03: Determine a group of goods B each time j Assigned to a flight A i After that, according to B j Occupied volume and weight, recalculate A i The current available loading volume and the current available load capacity;

[0037] S04: looping through steps S02 and S03 until the volume or weight of each remaining group of cargo exceeds the currently available loading volume or currently available load of any flight, then terminating the loop and outputting the allocation result.

[0038] As a further solution of the present invention: if M1≥M2 and V1≥V2 exist at the same time, the specific steps of allocating goods are:

[0039] S11: Arrange the flights in ascending order of available load and label them as a1, a2, ..., a n , and mark the available load corresponding to each flight as m1, m2, ..., m n , the available loading spaces are marked as v1, v2, ..., v n ;

[0040] S12: The available load weight and available loading volume of the flights are accumulated item by item in the order of arrangement, and the current total load weight and current total loading volume obtained by each accumulation are marked as sumM respectively. k and sumV k , k=2, 3, ..., n;

[0041] S13: After each accumulation, sumM k Compared with M2, sumV k Compared with V2, when sumM is satisfied at the same time k ≥M2 and sumV k When ≥V2, stop accumulating, record the k value at this time, and output a1 to a k The flight with the same name will be used as a connecting flight, otherwise the number of flights will continue to be accumulated;

[0042] S14: When a1 to a is determined k After the flight is loaded, cargo will be loaded onto the flight with the smallest available load capacity in the order of the flights.

[0043] The present invention also includes an intelligent logistics transportation method based on big data fusion, which is applied to the above-mentioned intelligent logistics transportation system based on big data fusion, including:

[0044] Obtain the planned transshipment cargo information of delayed flights, and collect and pre-process various data of all flights at the current airport, including flight scheduled departure time, flight scheduled arrival time, flight route, available loading volume and available load;

[0045] Set a future time window, filter out flights that take off normally from the current airport within the future time window, and filter out flights whose destination is the same as the delayed flight for the second time, calculate the estimated loading time L of each flight based on the available load, filter out flights whose departure time is less than the corresponding estimated loading time L for the third time, mark the number of flights remaining after the third screening as n, and obtain the total time of n flights from the scheduled arrival time;

[0046] The planned transshipment goods are divided into m groups according to the goods order, the value mark and expected delivery time of each group of goods are obtained, and the weight of each group of goods is calculated by the TOPSIS method;

[0047] The sum of the available load and available loading volume of n flights are marked as M1 and V1 respectively, and the total weight and total volume of the planned transfer cargo are marked as M2 and V2 respectively. If any of M1<M2 and V1<V2 exists, the planned transfer cargo is allocated according to the weight priority of each group of cargo; if M1≥M2 and V1≥V2 exist at the same time, the n flights are sorted from small to large according to the available load, and flights are selected in sequence until the available load and available loading volume of the selected flight are both greater than the total weight and total volume of the planned transfer cargo, and the planned transfer cargo is allocated to the selected flight.

[0048] Beneficial effects of the present invention:

[0049] The present invention utilizes big data technology to collect and store various flight data, can realize rapid retrieval of a large amount of data, and can timely screen out all available transfer flights within the future time window; at the same time, the present invention determines whether the total available load and the total available loading volume of the screened flights can load all the planned transfer goods, and selects different cargo distribution plans according to the situation. When the total available load and the available loading volume are insufficient, the goods are grouped according to the order and the cargo weights are calculated, and the goods with high weights are preferentially distributed to flights with fast transportation time, thereby ensuring the timely delivery of important goods. When the total available load and the available loading volume are sufficient, the goods are preferentially distributed to flights with small available load, thereby improving the flight load factor and reducing the additional transportation cost of the transfer goods. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The present invention will be further described below in conjunction with the accompanying drawings.

[0051] Figure 1 It is a module schematic diagram of an intelligent logistics transportation system based on big data fusion of the present invention;

[0052] Figure 2 It is a schematic diagram of the flow of the flight screening module of the present invention;

[0053] Figure 3 It is a schematic diagram of the flow of the transfer and distribution module of the present invention. DETAILED DESCRIPTION

[0054] 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.

[0055] See also Figure 1-Figure 3 As shown, the present invention is an intelligent logistics transportation system based on big data fusion, comprising:

[0056] The data collection module is used to obtain the planned transfer cargo information of delayed flights, and collect and pre-process various data of all flights at the current airport, including the scheduled departure time of the flight, the scheduled arrival time of the flight, the flight route, the available loading volume and the available load.

[0057] In the data collection module, the preprocessing includes data storage format standardization, data compression and data partitioning, wherein:

[0058] Since big data technology needs to access various platforms when collecting and processing various types of data, the data storage formats between different platforms may differ. Therefore, in order to improve data compatibility and data readability, as well as data processing speed, it is necessary to standardize the data storage format and unify the storage format of all collected data into XML or JSON format.

[0059] The amount of aviation logistics-related data is huge. If the data is not properly compressed, it will affect the system's operating rate. Therefore, Huffman coding, LZW coding or RLE coding is used to losslessly compress the collected data, and then store or transmit the data after compression.

[0060] In order to improve the query performance of data and facilitate the management of data life cycle, time zone, space zone and cargo zone are constructed when storing data. The scheduled departure time and arrival time of flights are stored in the time zone, the flight routes, available loading volume and available load are stored in the space zone, and the planned transshipment cargo information of delayed flights is stored in the cargo zone. The planned transshipment cargo information includes: cargo volume, cargo weight and cargo value. Partitioning can help the system to expand horizontally more easily. New data can be assigned to new partitions without reorganizing existing data. At the same time, partitioning makes data management more flexible. For example, independent backup and recovery operations can be performed on different partitions without affecting other partitions.

[0061] The flight screening module is used to set a future time window, screen out flights that take off normally from the current airport within the future time window, and screen out flights whose destination is the same as the delayed flight for the second time, and calculate the estimated loading time L of each flight based on the available load. The specific process of calculating the estimated loading time L is: obtain the average cargo loading rate of the current airport and the available load of each flight screened for the second time, and calculate the time required for each flight to load the available load based on the average loading rate and the available load, and mark it as the estimated loading time L of the flight.

[0062] The flights are screened three times according to L. If the flight has landed at the current airport, the distance between the current time and the scheduled departure time of the flight is calculated and compared with the L corresponding to the flight. If the flight has not landed at the current airport, the distance between the estimated arrival time at the current airport and the next scheduled departure time is calculated and compared with the L corresponding to the flight. All flights whose calculated values ​​are less than L are screened out, and the number of flights remaining after three screenings is marked as n, and the total duration of the n flights from the scheduled arrival time is obtained.

[0063] The purpose of the third screening is to avoid the situation where the scheduled departure time of the flight has not yet been completed for the flights selected by the second screening. Selecting the available load of the flight to calculate L means that each flight will be fully loaded with the available load by default, which can ensure sufficient time redundancy.

[0064] The cargo weight module is used to divide the planned transshipped cargo into m groups according to the cargo order, obtain the value mark and expected delivery time of each group of cargo, and calculate the weight of each group of cargo by the TOPSIS method. The expected delivery time of cargo refers to the time it takes for each group of cargo to be transported to the flight terminal airport through the delayed flight and then transported from the terminal airport to the corresponding customers of each group of cargo. This is because air logistics needs to collect various types of cargo first, and the target customers for the final delivery of such cargo may not be the same. Even if the cargo arrives at the same airport on the same flight, the cargo still needs to be transshipped from the destination airport to different target customers by other means.

[0065] The specific steps of calculating the weight of each group of goods by the TOPSIS method are:

[0066] Step 1: Mark the values ​​of m groups of goods as s1, s2, ..., s m , the expected delivery time of the goods is marked as t1, t2, ..., t m , and mark the maximum value of the expected delivery time of the goods as t max ;

[0067] Step 2: Use t to calculate the expected delivery time for each group of goods. max -tj The reason for performing the positive operation and only positively normalizing the expected delivery time of the goods is that when the weight is evaluated according to the value of the goods, the higher the value, the higher the weight, but when the weight is evaluated according to the expected delivery time of the goods, the shorter the time, the higher the weight. There is a difference in the judgment logic of the two. When the weight of the goods is judged by combining the two, it is necessary to make the judgment logic of the two the same by positively normalizing the expected delivery time of the goods. After positive normalization, the expected delivery time is reassigned and marked as e1, e2, ..., e m , j=1, 2, ..., m.

[0068] Step 3: Standardize the value of each group of goods and the expected delivery time of the goods. The standardized calculation formula is:

[0069]

[0070]

[0071] s' j With e' j Indicates the standardized value of goods and the expected delivery time of the goods.

[0072] Step 4: s' j With e' j The maximum and minimum values ​​in are marked as s + , e + and - , e - , calculate the Euclidean distance between each group of goods and the maximum and minimum values ​​respectively, and mark them as D j + and D j — , the weight of each group of goods is calculated according to the Euclidean distance, and the calculation formula is:

[0073] w j =D j — / (D j + +D j — );

[0074] where w j Indicates the weight of each group of goods.

[0075] The transshipment allocation module is used to mark the total available load weight and available loading volume of n flights as M1 and V1 respectively, and mark the total weight and total volume of planned transshipment goods as M2 and V2 respectively. If any of M1<M2 and V1<V2 exists, the planned transshipment goods are allocated according to the weight priority of each group of goods. The specific steps of allocation are:

[0076] S01: Sort the flights in ascending order according to the total duration of the transfer process and mark them as A1.

[0077] A2, ..., A n , sort each group of goods in descending order according to weight, and mark them as B1,

[0078] B2, ..., B m ;

[0079] S02: Select a group of goods B one by one starting from B1 j , select B according to the flight arrangement order j Match all flights in turn. If B j The volume and weight of the flight do not exceed that of a certain flight A i Available loading volume and available load, then B j Assign to A i , i and j are index values, i = 1, 2, ..., n, j = 1, 2, ..., m. The purpose of this step is to ensure that the goods with high weights are preferentially allocated to the aircraft with short transportation time, so as to ensure that important goods can be delivered in time;

[0080] S03: Determine a group of goods B each time j Assigned to a flight A i After that, according to B j Occupied volume and weight, recalculate A i The current available loading volume and the current available load capacity;

[0081] S04: looping through steps S02 and S03 until the currently available loading volume or currently available load of any flight is insufficient to load any remaining group of cargoes, then terminating the loop and outputting the allocation result.

[0082] Through steps S01-S04, high-weight goods can be allocated to flights with short transportation time first, ensuring that important goods can be delivered in time.

[0083] If M1≥M2 and V1≥V2 exist at the same time, the n flights are sorted from small to large according to the available load, and the flights are selected in sequence until the available load and available loading volume of the selected flight are both greater than the total weight and total volume of the planned transshipment cargo, and the planned transshipment cargo is allocated to the selected flight. The specific steps of allocation are:

[0084] S11: Arrange the flights in ascending order of available load and label them as a1, a2, ..., a n , and mark the available load corresponding to each flight as m1, m2, ..., m n, the available loading spaces are marked as v1, v2, ..., v n .

[0085] S12: The available load weight and available loading volume of the flights are accumulated item by item in the order of arrangement, and the current total load weight and current total loading volume obtained by each accumulation are marked as sumM respectively. k and sumV k , k=2, 3, ..., n.

[0086] S13: After each accumulation, sumM k Compared with M2, sumV k Compared with V2, when sumM is satisfied at the same time k ≥M2 and sumV k When ≥V2, stop accumulating, record the k value at this time, and output a1 to a k The flight with the required flight number will be regarded as a connecting flight, otherwise the number of passengers will continue to be accumulated.

[0087] S14: When a1 to a is determined k After the flight is loaded, cargo will be loaded onto the flight with the smallest available load capacity in the order of the flights.

[0088] S13 and S14 can ensure maximum utilization of aircraft cabin space and load capacity, increase flight load factor, and give priority to flights with smaller available load capacity to load cargo, which can maximize the spread of air logistics transportation costs and reduce additional transfer costs incurred when transferring cargo on delayed flights.

[0089] The present invention also includes an intelligent logistics transportation method based on big data fusion, which is applied to the above-mentioned intelligent logistics transportation system based on big data fusion, including:

[0090] Obtain the planned transshipment cargo information of delayed flights, and collect and pre-process various data of all flights at the current airport, including flight scheduled departure time, flight scheduled arrival time, flight route, available loading volume and available load;

[0091] Set a future time window, filter out flights that take off normally from the current airport within the future time window, and filter out flights whose destination is the same as the delayed flight for the second time, calculate the estimated loading time L of each flight based on the available load, filter out flights whose departure time is less than the corresponding estimated loading time L for the third time, mark the number of flights remaining after the third screening as n, and obtain the total time of n flights from the scheduled arrival time;

[0092] The planned transshipment goods are divided into m groups according to the goods order, the value mark and expected delivery time of each group of goods are obtained, and the weight of each group of goods is calculated by the TOPSIS method;

[0093] The sum of the available load and available loading volume of n flights are marked as M1 and V1 respectively, and the total weight and total volume of the planned transfer cargo are marked as M2 and V2 respectively. If any of M1<M2 and V1<V2 exists, the planned transfer cargo is allocated according to the weight priority of each group of cargo; if M1≥M2 and V1≥V2 exist at the same time, the n flights are sorted from small to large according to the available load, and flights are selected in sequence until the available load and available loading volume of the selected flight are both greater than the total weight and total volume of the planned transfer cargo, and the planned transfer cargo is allocated to the selected flight.

[0094] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0095] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0096] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent logistics transportation system based on big data fusion, characterized in that: include: The data collection module is used to obtain the planned transshipment cargo information of delayed flights and collect and pre-process various data of all flights at the current airport, including flight scheduled departure time, flight scheduled arrival time, flight route, available loading volume and available load; The flight screening module is used to set a future time window, screen out flights that take off normally from the current airport within the future time window, and screen out flights whose destination is the same as the delayed flight for the second time, calculate the estimated loading time L of each flight according to the available load, and screen out flights whose departure time is less than the corresponding estimated loading time L for the third time, mark the number of flights remaining after the third screening as n, and obtain the total time of n flights from the scheduled arrival time; The cargo weight module is used to divide the cargo planned for transshipment into m groups according to the cargo order, obtain the value mark and expected delivery time of each group of cargo, and calculate the weight of each group of cargo by the TOPSIS method; The transfer allocation module is used to mark the total available load and available loading volume of n flights as M1 and V1 respectively, and mark the total weight and total volume of planned transfer goods as M2 and V2 respectively. If any of M1<M2 and V1<V2 exists, the planned transfer goods are allocated according to the weight priority of each group of goods; if M1≥M2 and V1≥V2 exist at the same time, the n flights are sorted from small to large according to the available load, and the flights are selected in sequence until the available load and available loading volume of the selected flight are both greater than the total weight and total volume of the planned transfer goods, and the planned transfer goods are allocated to the selected flight.

2. According to claim 1, the intelligent logistics and transportation system based on big data fusion is characterized in that: In the data collection module, the preprocessing includes data storage format standardization, data compression and data partitioning, wherein: The method for standardizing the data storage format is to unify the storage format of all collected data into XML or JSON format; The data compression method is to use Huffman coding, LZW coding or RLE coding for lossless compression; The data partitioning method is to construct a time zone, a space zone and a cargo zone, wherein the scheduled flight departure time and the scheduled flight arrival time are stored in the time zone, the flight route, available loading volume and available load are stored in the space zone, and the planned transfer cargo information of the delayed flight is stored in the cargo zone, wherein the planned transfer cargo information includes: cargo volume, cargo weight and cargo value.

3. According to claim 1, the intelligent logistics and transportation system based on big data fusion is characterized in that: The specific process of calculating the expected loading time L is as follows: Get the average cargo loading rate of the current airport and the available load of each flight screened out for the second time. According to the average loading rate and available load, calculate the time required for each flight to load the available load and mark it as the estimated loading time L of the flight.

4. The intelligent logistics and transportation system based on big data fusion according to claim 3 is characterized in that: During the third screening, if the flight has landed at the current airport, the value of the current time from the scheduled departure time of the flight is calculated and compared with the L corresponding to the flight; if the flight has not landed at the current airport, the value of the flight's estimated arrival time at the current airport from the next scheduled departure time is calculated and compared with the L corresponding to the flight.

5. The intelligent logistics transportation system based on big data fusion according to claim 1 is characterized in that: The expected delivery time of the goods refers to the time it takes for each group of goods to be transported to the flight's terminal airport via the delayed flight and then transported from the terminal airport to the corresponding customer of each group of goods.

6. The intelligent logistics and transportation system based on big data fusion according to claim 5 is characterized in that: The specific steps of calculating the weight of each group of goods by the TOPSIS method are: Mark the values ​​of m groups of goods as s1, s2, ..., s m , the expected delivery time of the goods is marked as t1, t2, ..., t m , and mark the maximum value of the expected delivery time of the goods as t max ; The expected delivery time for each group of goods is calculated using t max -t j Perform a forward operation and re-assign the values. After the assignment, re-mark the expected delivery time of m groups of goods as e1, e2, ..., e m , j = 1, 2，...，m； The value of each group of goods and the expected delivery time of the goods are standardized. The standardized calculation formula is: s' j With e' j Indicates the standardized value of goods and the expected delivery time of goods; Will s' j With e' j The maximum and minimum values ​​in are marked as s + , e + and - , e - , calculate the Euclidean distance between each group of goods and the maximum and minimum values, and mark them as D j + and D j — , the weight of each group of goods is calculated according to the Euclidean distance, and the calculation formula is: w j =D j — / (D j + +D j — ); where w j Indicates the weight of each group of goods.

7. The intelligent logistics and transportation system based on big data fusion according to claim 6 is characterized in that: If any of the situations M1<M2 and V1<V2 exists, the specific steps for allocating goods are as follows: S01: Sort the flights in ascending order according to the total duration of the transfer process and mark them as A1. A2, ..., A n , sort each group of goods in descending order according to weight, and mark them as B1, B2,...,B m ; S02: Select a group of goods B one by one starting from B1 j , select B according to the flight arrangement order j Match all flights in turn. If B j The volume and weight of the flight do not exceed that of a certain flight A i Available loading volume and available load, then B j Assign to A i , i and j are index values, i = 1, 2, ..., n, j = 1, 2, ..., m; S03: Determine a group of goods B each time j Assigned to a flight A i After that, according to B j Occupied volume and weight, recalculate A i The current available loading volume and the current available load capacity; S04: looping through steps S02 and S03 until the volume or weight of each remaining group of cargo exceeds the currently available loading volume or currently available load of any flight, then terminating the loop and outputting the allocation result.

8. The intelligent logistics transportation system based on big data fusion according to claim 1 is characterized in that: If M1≥M2 and V1≥V2 exist at the same time, the specific steps for allocating goods are: S11: Arrange the flights in ascending order of available load and label them as a1, a2, ..., a n , and mark the available load corresponding to each flight as m1, m2, ..., m n , the available loading spaces are marked as v1, v2, ..., v n ; S12: The available load weight and available loading volume of the flights are accumulated item by item in the order of arrangement, and the current total load weight and current total loading volume obtained by each accumulation are marked as sumM respectively. k and sumV k , k=2, 3, ..., n; S13: After each accumulation, sumM k Compared with M2, sumV k Compared with V2, when sumM is satisfied at the same time k ≥M2 and sumV k When ≥V2, stop accumulating, record the k value at this time, and output a1 to a k The flight with the same name will be used as a connecting flight, otherwise the number of flights will continue to be accumulated; S14: When a1 to a is determined k After the flight is loaded, cargo will be loaded onto the flight with the smallest available load capacity in the order of the flights.

9. An intelligent logistics transportation method based on big data fusion, applied to an intelligent logistics transportation system based on big data fusion as claimed in any one of claims 1 to 8, characterized in that: include: Obtain the planned transshipment cargo information of delayed flights, and collect and pre-process various data of all flights at the current airport, including flight scheduled departure time, flight scheduled arrival time, flight route, available loading volume and available load; Set a future time window, filter out flights that take off normally from the current airport within the future time window, and filter out flights whose destination is the same as the delayed flight for the second time, calculate the estimated loading time L of each flight based on the available load, filter out flights whose departure time is less than the corresponding estimated loading time L for the third time, mark the number of flights remaining after the third screening as n, and obtain the total time of n flights from the scheduled arrival time; The planned transshipment goods are divided into m groups according to the goods order, the value mark and expected delivery time of each group of goods are obtained, and the weight of each group of goods is calculated by the TOPSIS method; The total available load weight and available loading volume of n flights are marked as M1 and V1 respectively, and the total weight and total volume of planned transshipment cargo are marked as M2 and V2 respectively. If any of the situations of M1<M2 and V1<V2 exists, the planned transshipment cargo is allocated according to the weight priority of each group of cargo; If M1≥M2 and V1≥V2 exist at the same time, the n flights are sorted from small to large according to the available load, and the flights are selected in sequence until the available load and available loading volume of the selected flight are both greater than the total weight and total volume of the planned transfer cargo, and the planned transfer cargo is then allocated to the selected flight.

Images