Big data real-time analysis and processing device based on deep learning

Abstract

The invention discloses a big data real-time analysis and processing device based on deep learning in the technical field of big data analysis, and is applied to the field of logistics. Comprising a plurality of packaging link subsystems, a plurality of transfer link subsystems, a plurality of storage link subsystems, a plurality of sorting link subsystems, a plurality of transportation link subsystems and a plurality of distribution link subsystems, and further comprises a monitoring module used for predicting operation loads of the subsystems according to real-time operation data and historical operation data of the subsystems. According to the system and the method, the monitoring module and the subsystems can be utilized to acquire and process data of articles, storage, transportation and the like, a processing strategy of a subsequent link is predicted in advance, and the express transportation efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data analysis, and specifically is a big data real-time analysis and processing device based on deep learning. Background Art

[0002] Big data refers to data sets that cannot be captured, managed and processed by conventional software tools within a certain time frame. It is a massive, high-growth and diversified information asset that requires new processing models to have stronger decision-making power, insight discovery and process optimization capabilities. Big data has the characteristics of large volume, high speed, diversity and value. The application of big data has penetrated into all walks of life, including logistics and express delivery, business intelligence, finance, medical care, education, transportation and many other fields.

[0003] The logistics and express delivery process mainly includes packaging, transshipment, warehousing, sorting, transportation, and distribution. A large amount of data will be generated in each link of the express delivery process, mainly including item data (item size, weight, transportation location, etc.), warehousing data (warehouse storage capacity, storage area, etc.), and transportation data (vehicle location, number, etc.). These data are closely related to the smoothness of express delivery. By analyzing and processing these data in real time, we can grasp the item size, weight, destination and other data in detail, as well as the transportation route and real-time location of the item, as well as the warehouse storage capacity, remaining storage area and other conditions.

[0004] During the entire express delivery process, the big data real-time analysis and processing technology in this field usually analyzes and processes data in sequence according to the packaging, transshipment, warehousing, sorting, transportation and distribution links. The use of data in each link is relatively independent, aiming to ensure the smooth progress of subsequent unfinished links, and has limited effect on optimizing and promoting subsequent unfinished links. For example, the links such as transshipment and warehousing after packaging focus on whether the space requirements of transshipment and warehousing are met, but lack the optimization and promotion of subsequent transshipment and warehousing links based on the packaging conditions of the items. Summary of the invention

[0005] In order to solve the above problems, the purpose of the present invention is to provide a big data real-time analysis and processing device based on deep learning. Based on item data, warehousing data, transportation data, etc., deep learning technology is used to optimize each link of logistics express transportation, and intelligent and flexible scheduling is performed to improve the efficiency of express transportation.

[0006] In order to achieve the above-mentioned purpose, the technical solution of the present invention is as follows: a big data real-time analysis and processing device based on deep learning, comprising a plurality of packaging link subsystems, a plurality of transfer link subsystems, a plurality of warehousing link subsystems, a plurality of sorting link subsystems, a plurality of transportation link subsystems and a plurality of distribution link subsystems;

[0007] The packaging subsystem includes an order collection module, an order processing module, and a packaging strategy module; the order collection module is used to collect express order data; the order processing module is used to process and output packaging information based on order data; the packaging strategy module is built based on deep learning technology, and is used to output packaging strategies and transshipment influencing factors based on packaging information;

[0008] The transshipment subsystem includes a packaging information collection module, a transshipment processing module and a transshipment strategy module; the packaging information collection module is used to collect packaging information; the transshipment processing module is used to process and output transshipment information based on packaging information; the transshipment strategy module is built based on deep learning technology, and is used to output transshipment strategies and storage influencing factors based on transshipment information and transshipment influencing factors;

[0009] The warehousing subsystem includes a transit information collection module, a warehousing processing module and a warehousing strategy module; the transit information collection module is used to collect transit information; the warehousing processing module is used to process and output warehousing information based on transit information; the warehousing strategy module is built based on deep learning technology, and is used to output warehousing strategies and sorting influencing factors based on warehousing information and warehousing influencing factors;

[0010] The sorting subsystem includes a storage information collection module, a sorting processing module and a sorting strategy module; the storage information collection module is used to collect storage information; the sorting processing module is used to output sorting information according to storage information processing; the sorting strategy module is built based on deep learning technology, and the sorting strategy module is used to output sorting strategies and transportation influencing factors according to sorting information and sorting influencing factors;

[0011] The transportation subsystem includes a sorting information collection module, a transportation processing module and a transportation strategy module; the sorting information collection module is used to collect sorting information; the transportation processing module is used to process and output transportation information based on the sorting information; the transportation strategy module is built based on deep learning technology, and is used to output transportation strategies and distribution influencing factors based on transportation information and transportation influencing factors;

[0012] The distribution subsystem includes a transportation information collection module, a distribution processing module and a distribution strategy module; the transportation information collection module is used to collect transportation information; the distribution processing module is used to output distribution information based on transportation information processing; the distribution strategy module is built based on deep learning technology, and the distribution strategy module is used to output distribution strategies based on distribution information and distribution influencing factors.

[0013] Further, the packaging strategy includes a first packaging strategy, a second packaging strategy, and a third packaging strategy;

[0014] First packaging strategy: determine the quantity and size of items through express order information and then determine the quantity and size of packaging containers;

[0015] Second packaging strategy: determine the quantity and volume of the filling in the packaging container according to the size of the item and the size of the packaging container;

[0016] The third packaging strategy: determine the storage location of the express during transportation based on the type of item.

[0017] Furthermore, the transport influencing factors include the number of packaging containers, the volume of packaging containers and the mass of packaging containers. The number of packaging containers is associated with the number of items, the volume of packaging containers is associated with the size of items, and the mass of packaging containers is associated with the size of items and the type of items.

[0018] Furthermore, the storage influencing factors include the warehouse to which the items are to be transferred and the number of items that the warehouse is to accommodate.

[0019] Furthermore, the sorting influencing factors include the regions where the items are to be sorted and the quantity of the items to be sorted to each region.

[0020] Furthermore, the sorting link subsystem also includes a sorting mechanism, which includes a number of conveying devices, a number of scanning devices and a number of sorting devices;

[0021] The conveying device is used to convey items, the scanning device is used to scan the express barcode of the items, and the sorting device is used to sort the items according to the scanning results of the express barcode of the items;

[0022] The sorting strategy includes a first sorting strategy and a second sorting strategy;

[0023] The first sorting strategy: obtain the number of items to be sorted in each region, and allocate a matching number of sorting devices to the regions where the number of items to be sorted is greater than a threshold;

[0024] Second sorting strategy: obtain the number of items to be sorted in each region, call the sorting equipment in the region where the number of items to be sorted is less than the threshold, and sort the items in the region where the number of items to be sorted is greater than the threshold.

[0025] Furthermore, the transportation influencing factors include the regions to which the items are intended to be transported, and the quantity of the items to be transported to each region; the distribution influencing factors include the regions to which the items are intended to be delivered, and the quantity of the items to be delivered to each region;

[0026] Transportation strategies include planning transportation routes and transportation destinations based on the areas to which the items are to be transported and the quantities of the items to be transported to each area;

[0027] The distribution strategy includes planning the distribution area and unit distribution quantity according to the regions to which the items are to be delivered and the quantity of the items to be delivered to each region.

[0028] Furthermore, it also includes a monitoring module, which is respectively connected to the signals of several packaging link subsystems, several transfer link subsystems, several warehousing link subsystems, several sorting link subsystems, several transportation link subsystems and several distribution link subsystems. The monitoring module is constructed based on deep learning technology. The monitoring module is used to predict the operating load of each subsystem according to the real-time operating data and historical operating data of each subsystem, and schedule the coordinated operation of each subsystem according to the operating load of each subsystem.

[0029] Furthermore, the operation data includes packaging strategy, transshipment influencing factor, transshipment strategy, warehousing influencing factor, warehousing strategy, sorting influencing factor, sorting strategy, transportation influencing factor, transportation strategy, distribution influencing factor and distribution strategy.

[0030] Furthermore, it also includes a display module, which is used to display the operating load of each subsystem monitored by the monitoring module.

[0031] The above scheme has the following beneficial effects:

[0032] 1. The present invention, through the order collection module, the order processing module and the packaging decision module, can fully collect the quantity, weight and size data information of the items in the order information, and then output the packaging strategy and transportation influencing factors, which is conducive to predicting the quantity, weight and size data information of the items in advance through deep learning technology and then helping the transportation subsystem to make judgments.

[0033] 2. The present invention, through the packaging information collection module, the transfer processing module and the transfer strategy module, can collect the quantity of items in the packaging information, the volume and quality information of the packaging container, and then output the transfer strategy and warehousing influencing factors, which is helpful to help managers arrange the transfer vehicles and transfer time in advance.

[0034] 3. The present invention, through the transfer information collection module, the warehousing processing module and the warehousing strategy module, can determine the warehouse to which the items are to be transferred and the number of items to be accommodated in the warehouse according to the warehousing strategy and sorting influencing factors, which is conducive to the management personnel to allocate various storage warehouses in advance.

[0035] 4. The present invention, through the storage information collection module, the sorting processing module and the sorting strategy module, can collect information based on the warehouse and the number of items to be accommodated in the warehouse in the storage information, and can identify the area where the items are to be sorted and the number of items to be sorted to each area through the order information, and then predict the transportation direction of each express in advance through deep learning technology, and sort it through the sorting mechanism, which is beneficial to reduce the load of the sorting equipment. Multiple sorting equipment cooperates to sort the express from the same distribution area to the same transmission equipment, which is beneficial to improve the efficiency of express sorting.

[0036] 5. The present invention, through the sorting information collection module, the transportation processing module and the transportation strategy module, can arrange the number and size of vehicles according to the number of express deliveries passing through different distribution areas in the sorting information, which is conducive to the management personnel to arrange the vehicles in advance and improve the efficiency of express delivery.

[0037] 6. The present invention, through the transportation information collection module, the distribution processing module and the distribution strategy module, can collect information according to the arrangement of vehicles in the transportation information and the distribution area, and then compare the express delivery volume after the transportation is completed with the express delivery sorted by the sorting strategy, which is beneficial for the staff to check whether there is any express delivery omission. Through deep learning technology, the distribution route can be continuously optimized, which is beneficial to reduce the delivery time of the staff and reduce the occurrence of express delivery timeouts.

[0038] 7. In the present invention, the monitoring module is respectively connected to the signal of each subsystem. Through deep learning technology, the monitoring module can predict the operating load of each subsystem based on the real-time operating data and historical operating data of each subsystem, and schedule each subsystem to operate collaboratively according to the operating load of each subsystem, which is beneficial to reducing the carrying load of each subsystem.

[0039] 8. The display module is helpful to display the operating load of each subsystem monitored by the monitoring module, so that the staff can understand the operating status of each subsystem. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 Schematic diagram of the structure of a big data real-time analysis and processing device based on deep learning in an embodiment of the present invention.

[0041] Figure 2 This is a schematic diagram of the subsystem modules of the big data real-time analysis and processing device based on deep learning in an embodiment of the present invention.

[0042] Figure 3 Schematic diagram of the monitoring module structure of the big data real-time analysis and processing device based on deep learning in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following is further described in detail through specific implementation methods:

[0044] Embodiment 1:

[0045] Basically as attached Figure 1 and Figure 2 As shown: A big data real-time analysis and processing device based on deep learning, including several packaging link subsystems, several transfer link subsystems, several warehousing link subsystems, several sorting link subsystems, several transportation link subsystems and several distribution link subsystems;

[0046] The packaging subsystem includes order collection module, order processing module and packaging strategy module; the order collection module is used to collect express order data; the order processing module is used to process and output packaging information according to order data; the packaging strategy module is built based on deep learning technology, and the packaging strategy module is used to output packaging strategy and transshipment influencing factors according to packaging information. The packaging strategy includes the first packaging strategy, the second packaging strategy and the third packaging strategy, as follows:

[0047] First packaging strategy: determine the quantity and size of items through express order information and then determine the quantity and size of packaging containers;

[0048] Second packaging strategy: determine the quantity and volume of the filling in the packaging container according to the size of the item and the size of the packaging container;

[0049] The third packaging strategy: determine the storage location of the express during transportation based on the type of item.

[0050] Specifically, the factors affecting transportation include the number of packaging containers, the volume of packaging containers, and the mass of packaging containers. The number of packaging containers is related to the number of items, the volume of packaging containers is related to the size of items, and the mass of packaging containers is related to the size of items and the type of items. These factors affecting transportation will affect the subsequent transportation environment and determine the demand for vehicles and personnel for subsequent transportation.

[0051] The transshipment subsystem includes a packaging information collection module, a transshipment processing module and a transshipment strategy module; the packaging information collection module is used to collect packaging information; the transshipment processing module is used to output transshipment information based on packaging information processing; the transshipment strategy module is built based on deep learning technology, and the transshipment strategy module is used to output transshipment strategies and warehousing influencing factors based on transshipment information and transshipment influencing factors.

[0052] Specifically, storage influencing factors include the warehouse to which the items are intended to be transferred and the number of items that the warehouse is intended to accommodate; these storage influencing factors will have an impact on subsequent storage links and determine the space, environment and other conditions required for subsequent storage.

[0053] The warehousing subsystem includes a transfer information collection module, a warehousing processing module and a warehousing strategy module; the transfer information collection module is used to collect transfer information; the warehousing processing module is used to output warehousing information based on transfer information processing; the warehousing strategy module is built based on deep learning technology, and the warehousing strategy module is used to output warehousing strategies and sorting influencing factors based on warehousing information and warehousing influencing factors.

[0054] Specifically, the sorting influencing factors include the area where the items are to be sorted and the number of items to be sorted to each area; these sorting influencing factors will have an impact on subsequent sorting links, such as: sorting equipment requirements, efficiency requirements, and personnel requirements.

[0055] The sorting subsystem also includes a sorting mechanism, which includes several conveying devices, several scanning devices and several sorting devices; the conveying devices are used to convey items, the scanning devices are used to scan the express barcodes of the items, and the sorting devices are used to sort the items according to the scanning results of the express barcodes of the items. The sorting strategy includes the first sorting strategy and the second sorting strategy, which are as follows:

[0056] The first sorting strategy: obtain the number of items to be sorted in each region, and allocate a matching number of sorting devices to the regions where the number of items to be sorted is greater than a threshold;

[0057] Second sorting strategy: obtain the number of items to be sorted in each region, call the sorting equipment in the region where the number of items to be sorted is less than the threshold, and sort the items in the region where the number of items to be sorted is greater than the threshold.

[0058] The sorting subsystem includes a warehouse information collection module, a sorting processing module and a sorting strategy module; the warehouse information collection module is used to collect warehouse information; the sorting processing module is used to output sorting information based on warehouse information processing; the sorting strategy module is built based on deep learning technology, and the sorting strategy module is used to output sorting strategies and transportation influencing factors based on sorting information and sorting influencing factors.

[0059] Specifically, the transportation influencing factors include the region to which the items are intended to be transported, and the quantity of the items to be transported to each region; the distribution influencing factors include the region to which the items are intended to be delivered, and the quantity of the items to be delivered to each region.

[0060] The transportation link subsystem includes a sorting information collection module, a transportation processing module and a transportation strategy module; the sorting information collection module is used to collect sorting information; the transportation processing module is used to output transportation information based on sorting information processing; the transportation strategy module is built based on deep learning technology, and the transportation strategy module is used to output transportation strategies and distribution influencing factors based on transportation information and transportation influencing factors.

[0061] The distribution subsystem includes a transportation information collection module, a distribution processing module and a distribution strategy module; the transportation information collection module is used to collect transportation information; the distribution processing module is used to output distribution information based on transportation information processing; the distribution strategy module is built based on deep learning technology, and the distribution strategy module is used to output distribution strategies based on distribution information and distribution influencing factors.

[0062] Specifically, the transportation strategy includes planning the transportation routes and destinations according to the regions to which the items are to be transported and the quantity of items to be transported to each region; the distribution strategy includes planning the distribution areas and unit distribution quantities according to the regions to which the items are to be delivered and the quantity of items to be delivered to each region.

[0063] The model selection when constructing the above-mentioned distribution strategy module, packaging strategy module, transshipment strategy module, warehousing strategy module, sorting strategy module, transportation strategy module and distribution strategy module is as follows:

[0064] Determine the data sources that need to be analyzed in the entire express delivery process, including order information data, transfer vehicle data, storage space data, sorting data, transport vehicle data and distribution data; select an appropriate deep learning model according to the task type, which can be a convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory network (LSTM), etc. This embodiment requires a large amount of scanning of express order information and needs to arrange work in chronological order. Therefore, convolutional neural network (CNN) is preferred. Convolutional neural network (CNN) performs well in image recognition and detection, and identification of goods, barcodes, storage locations and the status of logistics facilities.

[0065] In the specific implementation, the express delivery must be packaged first. The order processing module and the packaging decision module give priority to using convolutional neural network (CNN) for deep learning. The order collection module collects order information to determine the size, volume, weight, material and type of the items that need to be transported by express delivery. Then, the order processing module can process the order information collected by the collection module, and then the packaging decision module outputs the packaging strategy. The packaging strategy includes the first packaging strategy, which determines the number and size of the items through the express order information and then determines the number and size of the packaging containers; the second packaging strategy determines the number and volume of the filler in the packaging container through the size of the item and the size of the packaging container; the third packaging strategy determines the storage location of the express delivery during transportation through the type of item. The items are packaged through the first packaging strategy, the second packaging strategy and the third packaging strategy. The packaging information collection module can collect the packaging information of the items in real time. The transfer processing module gives priority to using convolutional neural network (CNN) for deep learning. The transfer processing module will combine the transfer influencing factors, and then the transfer strategy module will allocate vehicles that can carry the number and weight of express delivery for transfer.

[0066] The transfer information collection module in the warehousing subsystem will collect the vehicle information assigned by the transfer strategy module in real time, and then the warehousing processing module will output the warehousing information based on the transfer information processing, and finally the warehousing strategy module will output the warehousing strategy. The warehousing processing module can predict the storage volume required for the warehouse. The warehousing processing module gives priority to using convolutional neural networks (CNN) for deep learning. The warehousing processing module will monitor each warehouse in real time, integrate the number of express deliveries that each warehouse can accommodate, and adjust the express delivery storage quantity of each warehouse in a timely manner.

[0067] After the express is transported to the warehouse, express sorting can begin. The scanning device will first scan the express information on each express package and pass the express information to the sorting processing module. The sorting strategy module gives priority to using convolutional neural network (CNN) for deep learning. The sorting strategy module outputs the sorting strategy according to the express information processed by the sorting processing module. The first sorting strategy obtains the number of items to be sorted in each region, and allocates a matching number of sorting devices to the region where the number of items to be sorted is greater than the threshold; the second sorting strategy obtains the number of items to be sorted in each region, calls the sorting devices in the region where the number of items to be sorted is less than the threshold, and sorts the items in the region where the number of items to be sorted is greater than the threshold. The sorting strategy is implemented by the sorting mechanism. For example, if there are multiple items that need to be transported in the same direction, the scanning device must first be used to identify the transportation direction of these expresses. After determining that these items need to be transported in the same direction, the sorting strategy module will predict the position of these expresses on the conveyor belt in advance. Through the sorting device, multiple sorting devices can be used to turn and transport these expresses in the same direction to the same conveying device, which is beneficial to the load of the sorting device and improves the efficiency of sorting.

[0068] After the express is distributed to different distribution areas through the conveying equipment, the distributed express can be transported by vehicles. The transportation strategy module gives priority to using convolutional neural networks (CNN) for deep learning. The transportation strategy module will predict in advance the areas where the items are to be transported and the quantity of items to be transported to each area. According to different areas and quantities, different types of vehicles are dispatched in advance for transportation, which is conducive to improving transportation efficiency. The transportation strategy module can plan transportation routes and transportation destinations according to the areas where the items are to be transported and the quantity of items to be transported to each area.

[0069] After the express arrives safely at the destination, it will be delivered through the distribution link. First, the transportation information collection module will compare the actual express that arrives with the number of express assigned by the distribution processing module to confirm whether there is any omission. Then the distribution strategy module will output the distribution strategy. The distribution strategy module gives priority to using convolutional neural networks (CNN) for deep learning. The distribution strategy module can plan the distribution area and unit distribution volume according to the area where the items are to be delivered and the quantity of items to be delivered to each area, which is conducive to improving the delivery efficiency of the delivery staff.

[0070] Embodiment 2:

[0071] Basically as attached Figure 3 As shown: The difference from the above embodiment is that it also includes a monitoring module, which is respectively connected to the signals of several packaging link subsystems, several transfer link subsystems, several warehousing link subsystems, several sorting link subsystems, several transportation link subsystems and several distribution link subsystems. The monitoring module is constructed based on deep learning technology. The monitoring module is used to predict the operating load of each subsystem according to the real-time operating data and historical operating data of each subsystem, and schedule the coordinated operation of each subsystem according to the operating load of each subsystem; the operating data includes packaging strategy, transfer influencing factor, transfer strategy, warehousing influencing factor, warehousing strategy, sorting influencing factor, sorting strategy, transportation influencing factor, transportation strategy, distribution influencing factor and distribution strategy; it also includes a display module, which is used to display the operating load of each subsystem monitored by the monitoring module.

[0072] The specific implementation process is as follows: the monitoring module is connected to the signals of each subsystem. The monitoring module can monitor the task volume and operating load of each subsystem in real time. The monitoring module can compare the load and task volume of each subsystem and is built based on deep learning technology. It can combine historical data and real-time data to predict the task volume of each subsystem. If it is predicted that the task volume of a subsystem exceeds the standard and reaches the load of this subsystem, the monitoring module will adjust other subsystems in time to help the original subsystem to process data. For example, a large amount of order information in a certain area needs to be processed by the packaging link subsystem at one time, which seriously exceeds the load of the packaging link subsystem in this area. At this time, after the detection module monitors that the task volume of the packaging link subsystem in this area exceeds the standard, it will allocate other packaging link subsystems with lower task volumes, and the packaging link subsystems in other areas will share the burden of the packaging link subsystem in this area.

[0073] The display module can display the operating load of each subsystem monitored by the monitoring module, which is convenient for managers to discover and deal with problems in time. The monitoring module will display the operating status of each subsystem in real time on the display module, which is beneficial for managers to grasp the operation status of the entire system.

[0074] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0075] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A big data real-time analysis and processing device based on deep learning, applied in the field of logistics, characterized by: It includes several packaging link subsystems, several transfer link subsystems, several warehousing link subsystems, several sorting link subsystems, several transportation link subsystems and several distribution link subsystems; The packaging subsystem includes order collection module, order processing module and packaging strategy module; the order collection module is used to collect express order data; The order processing module is used to process and output packaging information based on order data; the packaging strategy module is built based on deep learning technology and is used to output packaging strategies and transshipment influencing factors based on packaging information; The transshipment subsystem includes a packaging information collection module, a transshipment processing module and a transshipment strategy module; the packaging information collection module is used to collect packaging information; the transshipment processing module is used to process and output transshipment information according to the packaging information; The transshipment strategy module is built based on deep learning technology. The transshipment strategy module is used to output transshipment strategies and storage influencing factors based on transshipment information and transshipment influencing factors; The warehousing subsystem includes a transshipment information collection module, a warehousing processing module and a warehousing strategy module; the transshipment information collection module is used to collect transshipment information; the warehousing processing module is used to process and output warehousing information according to the transshipment information; The warehousing strategy module is built based on deep learning technology. It is used to output warehousing strategies and sorting influencing factors based on warehousing information and warehousing influencing factors. The sorting subsystem includes a storage information collection module, a sorting processing module and a sorting strategy module; the storage information collection module is used to collect storage information; the sorting processing module is used to process and output sorting information according to storage information; The sorting strategy module is built based on deep learning technology. The sorting strategy module is used to output sorting strategies and transportation influencing factors based on sorting information and sorting influencing factors; The transportation link subsystem includes a sorting information collection module, a transportation processing module and a transportation strategy module; the sorting information collection module is used to collect sorting information; the transportation processing module is used to process and output transportation information according to the sorting information; The transportation strategy module is built based on deep learning technology. The transportation strategy module is used to output transportation strategies and distribution influencing factors based on transportation information and transportation influencing factors; The distribution subsystem includes a transportation information collection module, a distribution processing module and a distribution strategy module; the transportation information collection module is used to collect transportation information; the distribution processing module is used to output distribution information based on transportation information processing; the distribution strategy module is built based on deep learning technology, and the distribution strategy module is used to output distribution strategies based on distribution information and distribution influencing factors.

2. The big data real-time analysis and processing device based on deep learning according to claim 1, characterized in that: Packaging strategies include the first packaging strategy, the second packaging strategy and the third packaging strategy; First packaging strategy: determine the quantity and size of items through express order information and then determine the quantity and size of packaging containers; Second packaging strategy: determine the quantity and volume of the filling in the packaging container according to the size of the item and the size of the packaging container; The third packaging strategy: determine the storage location of the express during transportation based on the type of item.

3. The big data real-time analysis and processing device based on deep learning according to claim 2 is characterized in that: Transshipment influencing factors include the number of packaging containers, the volume of packaging containers and the mass of packaging containers. The number of packaging containers is related to the number of items, the volume of packaging containers is related to the size of items, and the mass of packaging containers is related to the size of items and the type of items.

4. The big data real-time analysis and processing device based on deep learning according to claim 1, characterized in that: Warehousing influencing factors include the warehouse to which the items are to be transferred and the number of items that the warehouse is to accommodate.

5. The big data real-time analysis and processing device based on deep learning according to claim 1, characterized in that: Sorting influencing factors include the region where the items are to be sorted and the number of items to be sorted to each region.

6. The big data real-time analysis and processing device based on deep learning according to claim 5, characterized in that: The sorting link subsystem also includes a sorting mechanism, which includes a number of conveying devices, a number of scanning devices and a number of sorting devices; The conveying device is used to convey items, the scanning device is used to scan the express barcode of the items, and the sorting device is used to sort the items according to the scanning results of the express barcode of the items; The sorting strategy includes a first sorting strategy and a second sorting strategy; The first sorting strategy: obtain the number of items to be sorted in each region, and allocate a matching number of sorting devices to the regions where the number of items to be sorted is greater than a threshold; Second sorting strategy: obtain the number of items to be sorted in each region, call the sorting equipment in the region where the number of items to be sorted is less than the threshold, and sort the items in the region where the number of items to be sorted is greater than the threshold.

7. The big data real-time analysis and processing device based on deep learning according to claim 1, characterized in that: The transportation influencing factors include the regions to which the items are to be transported and the quantity of the items to be transported to each region; the distribution influencing factors include the regions to which the items are to be delivered and the quantity of the items to be delivered to each region; Transportation strategies include planning transportation routes and transportation destinations based on the areas to which the items are to be transported and the quantities of the items to be transported to each area; The distribution strategy includes planning the distribution area and unit distribution quantity according to the regions to which the items are to be delivered and the quantity of the items to be delivered to each region.

8. The big data real-time analysis and processing device based on deep learning according to claim 1, characterized in that: It also includes a monitoring module, which is respectively connected to signals of several packaging link subsystems, several transfer link subsystems, several warehousing link subsystems, several sorting link subsystems, several transportation link subsystems and several distribution link subsystems. The monitoring module is constructed based on deep learning technology. The monitoring module is used to predict the operating load of each subsystem according to the real-time operating data and historical operating data of each subsystem, and schedule the coordinated operation of each subsystem according to the operating load of each subsystem.

9. The big data real-time analysis and processing device based on deep learning according to claim 8, characterized in that: Operational data includes packaging strategy, transshipment influencing factor, transshipment strategy, warehousing influencing factor, warehousing strategy, sorting influencing factor, sorting strategy, transportation influencing factor, transportation strategy, distribution influencing factor and distribution strategy.

10. The big data real-time analysis and processing device based on deep learning according to claim 9, characterized in that: It also includes a display module, which is used to display the operating load of each subsystem monitored by the monitoring module.

Images