Online intelligent management system for logistics orders based on big data analysis

Abstract

The present invention discloses an online intelligent management system for logistics orders based on big data analysis, which relates to the technical field of logistics order management, including a management center, wherein the management center is communicatively connected with a logistics data acquisition module, a logistics data processing module, a logistics data analysis module and an intelligent decision-making module. The logistics data acquisition module collects logistics-related data of a plurality of logistics warehouses, generates corresponding logistics orders through the logistics data processing module, generates order sets of different groups after grouping and processing the logistics orders, and performs distributed encrypted storage, obtains order sets of a plurality of groups after authorized decryption by the logistics data analysis module, performs logistics transportation route planning on the order sets through big data analysis technology, and generates corresponding logistics decision data sets, constructs a decision model according to the logistics decision data set and the order set by the intelligent decision module, and generates corresponding decision plans through the decision model.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics order management, and in particular to an online intelligent management system for logistics orders based on big data analysis. Background Art

[0002] Big data analysis refers to the process of collecting, processing, storing, managing and analyzing large-scale data sets. It involves the use of various technologies and tools to mine, understand and extract valuable information and insights hidden in big data.

[0003] Logistics order management refers to the process of effectively managing and processing orders in logistics business, which includes a series of operational processes of receiving, processing, tracking and executing orders to ensure that the goods can be delivered to customers on time and accurately.

[0004] For traditional logistics order management, the number of orders is often huge, and the amount of tasks brought by the decentralized processing of each order cannot be ignored, which to a certain extent leads to a disguised reduction in the efficiency of order processing. Therefore, how to speed up the efficiency of logistics order processing? In addition, the logistics orders of different customers have inconsistent time requirements for logistics goods. How to ensure that the goods are delivered within the time expected by the customer? These are the problems and challenges faced by the new logistics order management system in the big data era. Summary of the invention

[0005] In order to solve the above problems, the purpose of the present invention is to provide an online intelligent management system for logistics orders based on big data analysis.

[0006] The object of the present invention can be achieved by the following technical solutions: an online intelligent management system for logistics orders based on big data analysis, comprising a management center, wherein the management center is communicatively connected with a logistics data acquisition module, a logistics data processing module, a logistics data analysis module and an intelligent decision-making module;

[0007] The logistics data collection module is used to collect logistics-related data of several logistics warehouses in real time, and the logistics-related data includes order source, logistics destination, cargo type, cargo quantity and logistics timeliness requirements;

[0008] The logistics data processing module generates corresponding logistics orders according to logistics-related data, groups the logistics orders, generates order sets of different groups, and performs distributed encrypted storage on the order sets;

[0009] The logistics data analysis module obtains several groups of order sets after authorization and decryption, performs logistics transportation route planning for the several groups of order sets through big data analysis technology, and generates corresponding logistics decision data sets;

[0010] The intelligent decision-making module is used to build a decision model based on the logistics decision data set and the order set, and generate a corresponding decision plan through the decision model.

[0011] Furthermore, the process of the logistics data collection module collecting logistics-related data of several logistics warehouses in real time includes:

[0012] Number several logistics warehouses and record them as i, i = 1, 2, 3, ..., n, n is a natural number greater than 0, set the collection period and record it as T 采集 , T 采集 =[t1, t2], t1 is the starting point of the collection period, t2 is the end point of the collection period;

[0013] At the starting point of the time period t1, the logistics data collection module allocates several collection queues to several logistics storage locations, and determines whether the collection parameters corresponding to each collection queue meet the respective preset working parameters;

[0014] If yes, the logistics-related data of the corresponding logistics warehouse is collected through the collection queue. The logistics-related data includes the order source, logistics destination, cargo type, cargo quantity and logistics timeliness requirements of all warehouse goods;

[0015] If not, the corresponding collection queue is marked as a fault queue, and the collection parameters corresponding to the fault queue are uploaded to the management center. The administrator of the management center configures the fault repair parameters according to the collection parameters and returns them to the corresponding fault queue, thereby repairing the fault queue;

[0016] At the end of the time period t2, the logistics-related data of all logistics warehouses are transmitted to the logistics data processing module, and the logistics-related data corresponding to the logistics warehouse numbered i is marked as Info[i].

[0017] Furthermore, the process of the logistics data processing module generating a corresponding logistics order according to the logistics related data includes:

[0018] Set up several blank orders. When the logistics data processing module receives logistics-related data corresponding to several logistics warehouses, the order source, logistics destination, cargo type, cargo quantity and logistics timeliness requirements included in the logistics-related data are used as order record items respectively;

[0019] Obtain the number of order demands corresponding to each logistics warehouse, allocate a corresponding number of blank orders to each logistics warehouse according to the number of order demands, fill all order record items in the logistics-related data corresponding to each logistics warehouse into the corresponding blank orders, and then generate the logistics order for each logistics warehouse, and combine the number corresponding to each logistics warehouse with the type of goods and the number of goods as the unique identity of the logistics order.

[0020] Furthermore, the process of grouping the logistics orders, generating order sets of different groups, and performing distributed encrypted storage of the order sets includes:

[0021] The logistics orders with the same logistics destination, the same cargo type and the same logistics timeliness requirement are grouped into a set of orders of a certain group. After all the logistics orders are grouped, several sets of orders of a certain group are generated. The order sets are numbered and recorded as j, where j = 1, 2, 3, ..., m, where m is a natural number greater than 0. The order set numbered j is identified as Ω[j];

[0022] A distributed database is set up for distributed encrypted storage of all order sets. The distributed database consists of several sub-databases. The number corresponding to each sub-database is obtained, and a corresponding encryption key is assigned to each sub-database corresponding to the number in ascending order. Several order sets are imported into several sub-databases, and then each order set obtains the encryption key corresponding to the imported sub-database to encrypt itself. All order sets are converted into corresponding encrypted order sets after distributed encrypted storage.

[0023] Furthermore, the process of obtaining a set of orders of several groups after authorization and decryption by the logistics data analysis module includes:

[0024] The logistics data analysis module obtains several encrypted order sets and the encryption keys corresponding to each encrypted order set. Each encryption key is associated with an authorized decryption key. The encrypted order set is authorized to be decrypted by the authorized decryption key, and it is determined whether the encryption key corresponding to the current encrypted order set and the authorized decryption key for authorized decryption can be successfully matched. If so, the corresponding encrypted order set is changed to the order set corresponding to the original group. If not, the administrator authority is obtained, and the administrator decryption key corresponding to the current encrypted order set is defined by the administrator authority. The encryption key corresponding to the encrypted order set is matched by the administrator decryption key, and the encrypted order set is changed to the order set corresponding to the original group.

[0025] Furthermore, the process of planning the logistics transportation route and generating the corresponding logistics decision data set includes:

[0026] The logistics transportation path corresponding to each order set is used to transport all the warehouse goods corresponding to the group of order sets to the logistics destinations corresponding to the respective logistics transportation paths. The logistics transportation path corresponding to the order set Ω[j] is recorded as Stack[j]. Each logistics transportation path consists of several path nodes, which include a path starting point, a path end point and several path intermediate points.

[0027] Take the logistics warehouse corresponding to each order set as the starting point of the path, select a middle point of the path with the shortest distance from the starting point of the path to connect, and then construct the corresponding path segment, take the constructed path segment as the new starting point of the path, and then construct the next path segment corresponding to the connection with the shortest distance from the new starting point of the path, until the connection from each order set to the end point of the path is completed, and then construct the logistics transportation path corresponding to each order set;

[0028] Obtain the distance values ​​of several path segments corresponding to each logistics transportation path, as well as the time cost of the path segment, and then obtain the decision weight of each path segment. The decision weight is expressed as:

[0029]

[0030] The decision weights of all path segments corresponding to each logistics transportation path are summarized as the logistics decision data set of the corresponding order set, and the logistics decision data set corresponding to each order set is sent to the intelligent decision module.

[0031] Furthermore, the process of constructing a decision model based on the logistics decision data set and the order set by the intelligent decision module includes:

[0032] Construct an initial convolutional neural network, and input each order set and the decision data set corresponding to the order set into the initial convolutional neural network, and the initial convolutional neural network maps a sub-model area according to each order set;

[0033] The decision data set corresponding to each order set is synchronously input into the corresponding sub-model area, and the adjudication weights corresponding to the several decision weights included in the decision data set in the sub-model area are defined. The adjudication weights are used to determine whether the path segment of the logistics transportation path corresponding to each order set meets the expected requirements;

[0034] Obtain the total logistics time corresponding to the logistics timeliness requirements included in each order set, and then allocate corresponding sub-path time to the path segment corresponding to each distance value according to the ratio of the distance value of the path segment of the logistics transportation path corresponding to each order set to the sum of the total distance values;

[0035] The corresponding decision weight of each path segment is obtained according to the sub-path duration and distance value of each path segment. The decision weight is expressed as:

[0036]

[0037] Obtain the decision weights and adjudication weights of several path segments included in the logistics transportation path corresponding to each order set, and then construct the model decision item corresponding to each path segment, model decision item = <decision weight, adjudication weight>, input all model decision items into the sub-model area corresponding to the order set, and then construct the decision sub-model corresponding to each order set, perform model fusion on the decision sub-models corresponding to several order sets, and then construct the final decision model.

[0038] Furthermore, the process of generating a corresponding decision plan through the decision model includes:

[0039] The decision-making schemes include scheme A, scheme B and scheme C;

[0040] The decision model generates different decision plans corresponding to each order set according to the establishment ratio value of the model decision items, and the establishment ratio value is recorded as R, R = σ` / σ 总 , σ` represents the number of model decision items whose decision weight is not equal to the ruling weight in each order set, σ 总 Indicates the total number of model decision items corresponding to each order set;

[0041] Different decision intervals are set, including the first interval, the second interval and the third interval, which are respectively denoted as Δ1, Δ2 and Δ3, where Δ1 = (0, 0.5], Δ2 = (0.5, 0.8], Δ3 = (0.8, 1);

[0042] When R∈Δ1, the decision model generates plan A, the content of which is: the current order set meets the corresponding condition requirements of the customer, and the current order set is executed so that the warehouse goods order customer corresponding to the order set is satisfied;

[0043] When R∈Δ2, the decision model generates plan B, which is as follows: the logistics transportation path corresponding to the current order set needs to be replanned. After the new logistics transportation path is replanned, the warehouse goods corresponding to the order set are transported to the corresponding customers along the new logistics transportation path;

[0044] When R∈Δ3, the decision plan generated by the decision model is Plan C. The content of Plan C is: mark the current order set as an abnormal order set, replace new logistics personnel for all warehouse goods corresponding to the abnormal order set, and have the new logistics personnel transport the warehouse goods to the corresponding customers, obtain the warehousing information of the logistics warehousing corresponding to the abnormal order set, and generate the warehousing ID of the corresponding logistics warehousing according to the warehousing information. The warehousing ID is the identity authentication mark of the logistics warehousing, and the warehousing ID is included in the set logistics blacklist.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows: the logistics data collection module collects logistics-related data of several logistics warehouses in real time; the logistics data processing module generates corresponding logistics orders according to the logistics-related data, and groups the logistics orders according to the same logistics destination, cargo type and logistics timeliness requirements in the logistics-related data, thereby generating order sets of different groups; the logistics data analysis module plans the logistics transportation routes for several groups of order sets through big data analysis technology, and generates corresponding logistics decision data sets; finally, the intelligent decision-making module constructs a decision model according to the logistics decision data set and the order set, and generates corresponding decision plans through the decision model; on the one hand, the grouping processing to generate the order set speeds up the processing efficiency of the logistics order; on the other hand, the construction of the decision model and the generation of the decision plan for each order set meets the timeliness requirements of the customer in logistics transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0047] like Figure 1 As shown, the online intelligent management system for logistics orders based on big data analysis includes a management center, which is communicatively connected to a logistics data acquisition module, a logistics data processing module, a logistics data analysis module and an intelligent decision-making module;

[0048] The logistics data collection module is used to collect logistics-related data of several logistics warehouses in real time, and the logistics-related data includes order source, logistics destination, cargo type, cargo quantity and logistics timeliness requirements;

[0049] The logistics data processing module generates corresponding logistics orders according to logistics-related data, groups the logistics orders, generates order sets of different groups, and performs distributed encrypted storage on the order sets;

[0050] The logistics data analysis module obtains several groups of order sets after authorization and decryption, performs logistics transportation route planning for the several groups of order sets through big data analysis technology, and generates corresponding logistics decision data sets;

[0051] The intelligent decision-making module is used to build a decision model based on the logistics decision data set and the order set, and generate a corresponding decision plan through the decision model.

[0052] It should be further explained that, in the specific implementation process, the process of the logistics data collection module collecting logistics-related data of several logistics warehouses in real time includes:

[0053] Number several logistics warehouses and record the number as i, then i = 1, 2, 3, ..., n, where n is a natural number greater than 0. Set the collection period of the logistics data collection module and record the collection period as T 采集 , then T 采集 =[t1, t2], where t1 is the start point of the collection period, and t2 is the end point of the collection period;

[0054] At the starting point of the time period t1, the logistics data collection module allocates several collection queues to several logistics storage locations, and determines whether the collection parameters corresponding to each collection queue meet the respective preset working parameters;

[0055] If yes, then collect the logistics-related data of the corresponding logistics warehouse through the collection queue, and the logistics-related data includes the order source, logistics destination, cargo type, cargo quantity and logistics timeliness requirements of all warehoused goods;

[0056] If not, the corresponding collection queue is marked as a fault queue, and the collection parameters corresponding to the fault queue are uploaded to the management center. The administrator of the management center performs data analysis based on the collection parameters, configures corresponding fault repair parameters and returns them to the corresponding fault queue. The fault queue is repaired using the fault repair parameters.

[0057] At the end of the time period t2, the logistics-related data of all logistics warehouses are transmitted to the logistics data processing module, wherein the logistics-related data corresponding to the logistics warehouse numbered i is marked as Info[i].

[0058] It should be further explained that, in the specific implementation process, the process of the logistics data processing module generating the corresponding logistics order according to the logistics related data includes:

[0059] Set up several blank orders, which are data carriers for recording logistics-related data and generating logistics orders. When the logistics data processing module receives the logistics-related data corresponding to several logistics warehouses sent by the logistics data acquisition module, the order source, logistics destination, cargo type, cargo quantity and logistics timeliness requirements included in the logistics-related data are respectively used as order record items;

[0060] Obtain the number of order requirements corresponding to each logistics warehouse, allocate a corresponding number of blank orders to each logistics warehouse according to the number of order requirements, fill all order record items in the logistics-related data corresponding to each logistics warehouse into the corresponding several blank orders, and then generate the logistics order of each logistics warehouse, and combine the number corresponding to each logistics warehouse with the type of goods and the number of goods as the unique identity of the logistics order;

[0061] Among them, the order source in the order record item indicates the object that raises the logistics demand, the logistics destination is the final geographical location where the warehoused goods need to arrive, and the logistics timeliness requirement indicates the time cost for each warehoused goods to arrive at the final geographical location.

[0062] It should be further explained that, in the specific implementation process, the process of grouping logistics orders, generating order sets of different groups, and performing distributed encrypted storage of order sets includes:

[0063] Obtain all logistics orders for grouping and processing, grouping the logistics orders with the same logistics destination, the same cargo type and the same logistics timeliness requirement into a set of orders of a certain group, and then generate several sets of orders of a certain group after the grouping and processing of all logistics orders is completed;

[0064] Number the order sets of several groups, and record the number as j, then j = 1, 2, 3, ..., m, where m is a natural number greater than 0. After the numbering is completed, the order set numbered j is identified as Ω[j];

[0065] A distributed database is set up, and the distributed database is used to perform distributed encrypted storage on all order sets. The distributed database is composed of a plurality of sub-databases, and a number corresponding to each sub-database is obtained;

[0066] According to the order of numbers from small to large, a corresponding encryption key is assigned to the sub-database corresponding to each number, and several order sets are imported into several sub-databases. Then each order set obtains the encryption key corresponding to the imported sub-database to encrypt itself. All order sets are distributed and encrypted and stored and then converted into corresponding encrypted order sets.

[0067] It should be further explained that, in the specific implementation process, the process of obtaining a set of orders of several groups after the logistics data analysis module authorizes decryption includes:

[0068] The logistics data analysis module obtains a number of encrypted order sets generated after distributed encrypted storage, and then obtains the encryption key corresponding to each encrypted order set, and each encryption key is associated with a corresponding authorized decryption key;

[0069] The encrypted order set is authorized to be decrypted through the authorized decryption key. The content of the authorized decryption is as follows: determine whether the encryption key corresponding to the current encrypted order set can successfully match the authorized decryption key for authorized decryption. If so, the corresponding encrypted order set is changed to the order set corresponding to the original group. If not, obtain administrator authority, define the administrator decryption key corresponding to the current encrypted order set through administrator authority, match the encryption key corresponding to the encrypted order set with the administrator decryption key, and then change the encrypted order set to the order set corresponding to the original group.

[0070] It should be further explained that, in the specific implementation process, the process of planning the logistics transportation route and generating the corresponding logistics decision data set includes:

[0071] Planning logistics transportation routes corresponding to a number of groups of order sets, where the logistics transportation route corresponding to each order set is used to transport all types and quantities of warehouse goods corresponding to the group of order sets to the logistics destinations corresponding to the logistics transportation routes;

[0072] The logistics transportation path corresponding to the order set Ω[j] is recorded as Stack[j]. The logistics transportation path consists of a number of path nodes. The types of path nodes include the path starting point at the corresponding position of the logistics warehouse, the path end point at the corresponding position of the logistics destination, and the path middle point between the path starting point and the path end point. Several path middle points correspond to several logistics transfer stations, which are used for temporary storage of warehouse goods.

[0073] The number of path starting points is recorded as S1, the number of path midpoints is recorded as S2, and the number of path end points is recorded as S3, then S1 = S3, S2 is an integer greater than 0, that is, one path starting point, one path end point, and several path midpoints between the path starting point and the path end point constitute a logistics transportation path corresponding to each order set;

[0074] The specific content of logistics transportation path planning is: take the logistics warehouse corresponding to each order set as the path starting point, select a path middle point with the shortest distance from the path starting point to connect, and then construct the corresponding path segment, take the constructed path segment as the new path starting point, and then construct the next path segment corresponding to the connection with the shortest distance from the new path starting point, until the connection from each order set to the path end point is completed, and then the logistics transportation path corresponding to each order set is constructed;

[0075] Obtain the distance values ​​of several path segments corresponding to each logistics transportation path, as well as the time cost of the path segment, and then obtain the decision weight of each path segment. The decision weight is expressed as follows:

[0076]

[0077] The decision weights of all path segments corresponding to each logistics transportation path are summarized as the logistics decision data set of the corresponding order set, and the logistics decision data set corresponding to each order set is sent to the intelligent decision module.

[0078] It should be further explained that, in the specific implementation process, the process of the intelligent decision module building a decision model based on the logistics decision data set and the order set includes:

[0079] An initial convolutional neural network is constructed using deep learning technology, and each order set and the decision data set corresponding to the order set are input into the initial convolutional neural network, which maps a sub-model area according to each order set.

[0080] Synchronously input the decision data set corresponding to each order set into its corresponding sub-model area, and define the adjudication weights corresponding to the several decision weights included in the decision data set in the sub-model area, wherein the adjudication weights are used to determine whether the path segment of the logistics transportation path corresponding to each order set meets the expected requirements;

[0081] When the decision weight of a path segment is equal to the corresponding ruling weight, it means that the path segment meets the expected requirements. When the decision weight of a path segment is not equal to the corresponding ruling weight, it means that the path segment does not meet the expected requirements.

[0082] Obtain the total logistics time corresponding to the logistics timeliness requirements included in each order set, and then allocate corresponding sub-path time to the path segment corresponding to each distance value according to the ratio of the distance value of the path segment of the logistics transportation path corresponding to each order set to the sum of the total distance values;

[0083] The total logistics time of the order set is recorded as T 物流 , the sum of the total distance values ​​of all path segments under the corresponding logistics transportation path is recorded as L 总 , the distance value of a certain path segment is recorded as L, and the duration of the sub-path assigned to the path segment is recorded as T;

[0084]

[0085] The corresponding decision weight of each path segment is obtained according to the sub-path duration and distance value of each path segment. The decision weight is expressed as follows:

[0086]

[0087] Obtain the decision weights and adjudication weights of several path segments included in the logistics transportation path corresponding to each order set, and then construct the model decision item corresponding to each path segment, where model decision item = <decision weight, adjudication weight>, input all model decision items into the sub-model area corresponding to the order set, and then construct the decision sub-model corresponding to each order set;

[0088] The decision sub-models corresponding to several order sets are integrated to construct the final decision model.

[0089] It should be further explained that, in the specific implementation process, the process of generating corresponding decision plans through the decision model includes:

[0090] The decision-making schemes include scheme A, scheme B and scheme C;

[0091] The decision model generates different decision plans corresponding to each order set according to the establishment ratio value of the model decision items. The establishment ratio value is recorded as R, then R = σ` / σ 总 , where σ` represents the number of model decision items whose decision weight is not equal to the ruling weight in each order set, σ 总 It represents the total number of model decision items corresponding to each order set;

[0092] Different decision intervals are set, the decision intervals include a first interval, a second interval and a third interval, which are respectively denoted as Δ1, Δ2 and Δ3, wherein Δ1=(0, 0.5], Δ2=(0.5, 0.8], Δ3=(0.8, 1);

[0093] When R∈Δ1, the decision plan generated by the decision model is Plan A. The content of Plan A is: the current order set meets the corresponding condition requirements of the customer side, and the current order set is executed so that the warehouse goods order customer side corresponding to the order set;

[0094] When R∈Δ2, the decision plan generated by the decision model is Plan B. The content of Plan B is: the logistics transportation path corresponding to the current order set needs to be replanned. After the new logistics transportation path is replanned, the warehouse goods corresponding to the order set are transported to the corresponding customers according to the new logistics transportation path;

[0095] When R∈Δ3, the decision plan generated by the decision model is Plan C. The content of Plan C is: mark the current order set as an abnormal order set, replace new logistics personnel for all warehouse goods corresponding to the abnormal order set, and have the new logistics personnel transport the warehouse goods to the corresponding customers, obtain the warehousing information of the logistics warehousing corresponding to the abnormal order set, and generate the warehousing ID of the corresponding logistics warehousing according to the warehousing information. The warehousing ID is the identity authentication mark of the logistics warehousing, and the warehousing ID is included in the set logistics blacklist.

[0096] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An online intelligent management system for logistics orders based on big data analysis, including a management center, characterized in that: The management center is communicatively connected with a logistics data acquisition module, a logistics data processing module, a logistics data analysis module and an intelligent decision-making module; The logistics data collection module is used to collect logistics-related data of several logistics warehouses in real time, and the logistics-related data includes order source, logistics destination, cargo type, cargo quantity and logistics timeliness requirements; The logistics data processing module generates corresponding logistics orders according to logistics-related data, groups the logistics orders, generates order sets of different groups, and performs distributed encrypted storage on the order sets; The logistics data analysis module obtains several groups of order sets after authorization and decryption, performs logistics transportation route planning for the several groups of order sets through big data analysis technology, and generates corresponding logistics decision data sets; The intelligent decision-making module is used to build a decision model based on the logistics decision data set and the order set, and generate a corresponding decision plan through the decision model; The process of planning logistics transportation routes and generating corresponding logistics decision data sets includes: The logistics transportation path corresponding to each order set is used to transport all the warehouse goods corresponding to the group order set to the logistics destination corresponding to each logistics transportation path. The logistics transportation path corresponding to the order set Ω[j] is recorded as Stack[j]. Each logistics transportation path consists of a number of path nodes, and the path nodes include a path starting point, a path end point and a number of path intermediate points. Take the logistics warehouse corresponding to each order set as the starting point of the path, select a middle point of the path with the shortest distance from the starting point of the path to connect, and then construct the corresponding path segment, take the constructed path segment as the new starting point of the path, and then construct the next path segment corresponding to the connection with the shortest distance from the new starting point of the path, until the connection from each order set to the end point of the path is completed, and then construct the logistics transportation path corresponding to each order set; Obtain the distance values ​​of several path segments corresponding to each logistics transportation path, as well as the time cost of the path segment, and then obtain the decision weight of each path segment. The decision weight is expressed as: The decision weights of all path segments corresponding to each logistics transportation path are summarized as the logistics decision data set of the corresponding order set, and the logistics decision data set corresponding to each order set is sent to the intelligent decision module; The process of building a decision model based on the logistics decision data set and order set by the intelligent decision module includes: Construct an initial convolutional neural network, and input each order set and the decision data set corresponding to the order set into the initial convolutional neural network, and the initial convolutional neural network maps a sub-model area according to each order set; The decision data set corresponding to each order set is synchronously input into the corresponding sub-model area, and the adjudication weights corresponding to the several decision weights included in the decision data set in the sub-model area are defined. The adjudication weights are used to determine whether the path segment of the logistics transportation path corresponding to each order set meets the expected requirements; Obtain the total logistics time corresponding to the logistics timeliness requirements included in each order set, and then allocate corresponding sub-path time to the path segment corresponding to each distance value according to the ratio of the distance value of the path segment of the logistics transportation path corresponding to each order set to the sum of the total distance values; The corresponding decision weight of each path segment is obtained according to the sub-path duration and distance value of each path segment. The decision weight is expressed as: Obtain the decision weights and adjudication weights of several path segments included in the logistics transportation path corresponding to each order set, and then construct the model decision item corresponding to each path segment, model decision item = <decision weight, adjudication weight>, input all model decision items into the sub-model area corresponding to the order set, and then construct the decision sub-model corresponding to each order set, perform model fusion on the decision sub-models corresponding to several order sets, and then construct the final decision model; The process of generating corresponding decision plans through decision models includes: The decision-making schemes include scheme A, scheme B and scheme C; The decision model generates different decision plans corresponding to each order set according to the establishment ratio value of the model decision items, and the establishment ratio value is recorded as R, R = σ` / σ 总 , σ` represents the number of model decision items whose decision weight is not equal to the ruling weight in each order set, σ 总 Indicates the total number of model decision items corresponding to each order set; Different decision intervals are set, including the first interval, the second interval and the third interval, which are respectively denoted as Δ1, Δ2 and Δ3, where Δ1 = (0, 0.5], Δ2 = (0.5, 0.8], Δ3 = (0.8, 1); When R∈Δ1, the decision model generates plan A, which is: the current order set meets the corresponding condition requirements of the customer, and the current order set is executed so that the warehouse goods corresponding to the order set are transported to the order customer; When R∈Δ2, the decision model generates plan B, which is as follows: the logistics transportation path corresponding to the current order set needs to be replanned. After the new logistics transportation path is replanned, the warehouse goods corresponding to the order set are transported to the corresponding customers along the new logistics transportation path; When R∈Δ3, the decision plan generated by the decision model is Plan C. The content of Plan C is: mark the current order set as an abnormal order set, replace new logistics personnel for all warehouse goods corresponding to the abnormal order set, and have the new logistics personnel transport the warehouse goods to the corresponding customers, obtain the warehousing information of the logistics warehousing corresponding to the abnormal order set, and generate the warehousing ID of the corresponding logistics warehousing according to the warehousing information. The warehousing ID is the identity authentication mark of the logistics warehousing, and the warehousing ID is included in the set logistics blacklist.

2. The online intelligent management system for logistics orders based on big data analysis according to claim 1 is characterized in that: The process of real-time collection of logistics-related data of several logistics warehouses by the logistics data collection module includes: Number several logistics warehouses and record them as i, i = 1, 2, 3, ..., n, n is a natural number greater than 0, set the collection period and record it as T 采集 , T 采集 =[t1, t2], t1 is the starting point of the collection period, t2 is the end point of the collection period; At the starting point of the time period t1, the logistics data collection module allocates several collection queues to several logistics storage locations, and determines whether the collection parameters corresponding to each collection queue meet the respective preset working parameters; If yes, the logistics-related data of the corresponding logistics warehouse is collected through the collection queue. The logistics-related data includes the order source, logistics destination, cargo type, cargo quantity and logistics timeliness requirements of all warehouse goods; If not, the corresponding collection queue is marked as a fault queue, and the collection parameters corresponding to the fault queue are uploaded to the management center. The administrator of the management center configures the fault repair parameters according to the collection parameters and returns them to the corresponding fault queue, thereby repairing the fault queue; At the end of the time period t2, the logistics-related data of all logistics warehouses are transmitted to the logistics data processing module, and the logistics-related data corresponding to the logistics warehouse numbered i is marked as Info[i].

3. The online intelligent management system for logistics orders based on big data analysis according to claim 2 is characterized in that: The process of the logistics data processing module generating corresponding logistics orders based on logistics-related data includes: Set up several blank orders. When the logistics data processing module receives logistics-related data corresponding to several logistics warehouses, the order source, logistics destination, cargo type, cargo quantity and logistics timeliness requirements included in the logistics-related data are used as order record items respectively; Obtain the number of order demands corresponding to each logistics warehouse, allocate a corresponding number of blank orders to each logistics warehouse according to the number of order demands, fill all order record items in the logistics-related data corresponding to each logistics warehouse into the corresponding blank orders, and then generate the logistics order for each logistics warehouse, and combine the number corresponding to each logistics warehouse with the type of goods and the number of goods as the unique identity of the logistics order.

4. The online intelligent management system for logistics orders based on big data analysis according to claim 3 is characterized in that: The process of grouping logistics orders, generating order sets of different groups, and performing distributed encrypted storage of order sets includes: The logistics orders with the same logistics destination, the same cargo type and the same logistics timeliness requirement are grouped into a set of orders of a certain group. After all the logistics orders are grouped, several sets of orders of a certain group are generated. The order sets are numbered and recorded as j, where j = 1, 2, 3, ..., m, where m is a natural number greater than 0. The order set numbered j is identified as Ω[j]; A distributed database is set up for distributed encrypted storage of all order sets. The distributed database consists of several sub-databases. The number corresponding to each sub-database is obtained, and a corresponding encryption key is assigned to each sub-database corresponding to the number in ascending order. Several order sets are imported into several sub-databases, and then each order set obtains the encryption key corresponding to the imported sub-database to encrypt itself. All order sets are converted into corresponding encrypted order sets after distributed encrypted storage.

5. The online intelligent management system for logistics orders based on big data analysis according to claim 4 is characterized in that: The process of obtaining a set of orders for several groups after authorization and decryption by the logistics data analysis module includes: The logistics data analysis module obtains several encrypted order sets and the encryption keys corresponding to each encrypted order set. Each encryption key is associated with an authorized decryption key. The encrypted order set is authorized to be decrypted by the authorized decryption key, and it is determined whether the encryption key corresponding to the current encrypted order set and the authorized decryption key for authorized decryption can be successfully matched. If so, the corresponding encrypted order set is changed to the order set corresponding to the original group. If not, the administrator authority is obtained, and the administrator decryption key corresponding to the current encrypted order set is defined by the administrator authority. The encryption key corresponding to the encrypted order set is matched by the administrator decryption key, and the encrypted order set is changed to the order set corresponding to the original group.

Images