Cargo transportation method and device

Abstract

The invention discloses a cargo transportation method and device, and relates to the technical field of warehouse logistics. A specific embodiment of the cargo transportation method comprises the following steps: in response to a received delivery request, obtaining corresponding order information and real-time warehouse information of a plurality of warehouses; inputting the order information and the real-time warehouse information into a preset warehouse recommendation model, and determining a target warehouse from the plurality of warehouses by using the warehouse recommendation model; and generating a transportation task according to the target warehouse, and transporting target goods corresponding to the delivery request to the target warehouse. According to the embodiment, the target warehouse more suitable for receiving the goods can be screened out from the multiple warehouses before the goods are transported, so that the number of times of temporarily modifying the target warehouse in the goods transportation process is reduced, and the goods transportation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of warehousing logistics, and in particular to a method and device for transporting goods. Background Art

[0002] Before transporting the target goods, it is usually necessary to determine the target warehouse that receives the target goods based on factors such as warehouse location and warehouse storage capacity, and generate the corresponding transportation task. After transporting the target goods to the target warehouse, if the target warehouse can no longer store the target goods because it stores other goods, or there are a large number of other goods waiting to be unloaded and put into storage, so that the target goods need to wait for a long time before being stored in the target warehouse, it is necessary to modify the warehouse that receives the target goods and transport the target goods to other warehouses to complete the transportation task.

[0003] In the process of implementing the present invention, the inventors found that the prior art has at least the following problems:

[0004] The factors considered when screening warehouses are mainly the basic information of the warehouse, which leads to the frequent need to modify the target warehouse during the transportation of goods, resulting in high transportation costs. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method and device for transporting goods, which can determine a target warehouse after comprehensively considering various factors, reduce the number of times the target warehouse is temporarily modified during the cargo transportation process, and reduce the cargo transportation cost.

[0006] To achieve the above object, according to a first aspect of an embodiment of the present invention, a method for transporting goods is provided, comprising:

[0007] In response to receiving a delivery request, obtaining corresponding order information and real-time warehouse information of multiple warehouses;

[0008] Inputting the order information and the real-time warehouse information into a preset warehouse recommendation model, and using the warehouse recommendation model to determine a target warehouse from the multiple warehouses;

[0009] A transportation task is generated according to the target warehouse, so that the target goods corresponding to the delivery request are transported to the target warehouse.

[0010] Optionally, before transporting the target goods corresponding to the delivery request to the target warehouse, the method further includes:

[0011] In response to receiving the information update request, acquiring again the real-time warehouse information of the plurality of warehouses;

[0012] Inputting the real-time warehouse information acquired again into the warehouse recommendation model, and using the warehouse recommendation model to determine a warehouse prediction value and warehouse recommendation values ​​of the plurality of warehouses;

[0013] When the warehouse recommendation value of the target warehouse is less than a preset warehouse recommendation threshold, the recommended warehouse is determined according to the warehouse prediction value, and the transportation task is modified according to the recommended warehouse so that the target goods corresponding to the delivery request are transported to the recommended warehouse.

[0014] Optionally, determining a recommended warehouse according to the warehouse prediction value includes:

[0015] Integrating the difference between the warehouse recommendation value of the target warehouse and the warehouse prediction value;

[0016] summing the integral result and the warehouse prediction value;

[0017] A warehouse prediction interval corresponding to the summation result is determined, and the warehouse corresponding to the warehouse prediction interval is used as a recommended warehouse.

[0018] Optionally, when the warehouse recommendation value of the target warehouse is greater than or equal to the warehouse recommendation threshold, the method further includes:

[0019] In response to receiving the warehouse replacement request, determining a corresponding replacement warehouse;

[0020] When the warehouse recommendation value of the replacement warehouse is greater than or equal to the warehouse recommendation threshold, modifying the transportation task according to the replacement warehouse so that the target goods corresponding to the delivery request are transported to the replacement warehouse;

[0021] When the warehouse recommendation value of the replacement warehouse is less than the warehouse recommendation threshold, a prompt message is generated.

[0022] Optionally, there are multiple target warehouses; generating a transportation task according to the target warehouses includes:

[0023] In response to receiving the task generation request, determining a corresponding request repository;

[0024] In the case that the requesting warehouse is one of a plurality of target warehouses, a transportation task is generated according to the requesting warehouse, so that the target goods corresponding to the delivery request are transported to the requesting warehouse.

[0025] Optionally, the method further comprises:

[0026] Performing online training on the warehouse recommendation model using the order information and the real-time warehouse information;

[0027] The sparrow search algorithm is used to optimize the weights and biases of the warehouse recommendation model after online training.

[0028] Optionally, before using the sparrow search algorithm to optimize the weights and biases of the warehouse recommendation model after online training, the method further includes:

[0029] Determining whether the hidden layer output matrix of the warehouse recommendation model after the online training is reversible;

[0030] When the hidden layer output matrix is ​​not reversible, the data in the hidden layer output matrix is ​​replaced until the hidden layer output matrix is ​​reversible.

[0031] According to a second aspect of an embodiment of the present invention, there is provided a device for transporting goods, comprising:

[0032] an acquisition module, for acquiring corresponding order information and real-time warehouse information of multiple warehouses in response to receiving a delivery request;

[0033] a determination module, configured to input the order information and the real-time warehouse information into a preset warehouse recommendation model, and determine a target warehouse from the plurality of warehouses using the warehouse recommendation model;

[0034] A generation module is used to generate a transportation task according to the target warehouse, so that the target goods corresponding to the delivery request are transported to the target warehouse.

[0035] Optionally, the device further comprises:

[0036] a repeated acquisition module, configured to acquire again the real-time warehouse information of the plurality of warehouses in response to receiving the information update request;

[0037] a value determination module, configured to input the real-time warehouse information acquired again into the warehouse recommendation model, and use the warehouse recommendation model to determine a warehouse prediction value and warehouse recommendation values ​​of the plurality of warehouses;

[0038] The first modification module is used to determine the recommended warehouse according to the warehouse prediction value when the warehouse recommendation value of the target warehouse is less than a preset warehouse recommendation threshold value, and to modify the transportation task according to the recommended warehouse so that the target goods corresponding to the delivery request are transported to the recommended warehouse.

[0039] Optionally, determining a recommended warehouse according to the warehouse prediction value includes:

[0040] Integrating the difference between the warehouse recommendation value of the target warehouse and the warehouse prediction value;

[0041] summing the integral result and the warehouse prediction value;

[0042] A warehouse prediction interval corresponding to the summation result is determined, and the warehouse corresponding to the warehouse prediction interval is used as a recommended warehouse.

[0043] Optionally, the device further comprises:

[0044] A warehouse determination module, configured to determine a corresponding replacement warehouse in response to receiving a warehouse replacement request;

[0045] A second modification module is used to modify the transportation task according to the replacement warehouse so that the target goods corresponding to the delivery request are transported to the replacement warehouse when the warehouse recommendation value of the replacement warehouse is greater than or equal to the warehouse recommendation threshold;

[0046] The prompt module is used to generate a prompt message when the warehouse recommendation value of the replacement warehouse is less than the warehouse recommendation threshold.

[0047] Optionally, there are multiple target warehouses; generating a transportation task according to the target warehouses includes:

[0048] In response to receiving the task generation request, determining a corresponding request repository;

[0049] In the case that the requesting warehouse is one of a plurality of target warehouses, a transportation task is generated according to the requesting warehouse, so that the target goods corresponding to the delivery request are transported to the requesting warehouse.

[0050] Optionally, the device further comprises:

[0051] An online training module, used to perform online training on the warehouse recommendation model using the order information and the real-time warehouse information;

[0052] The optimization module is used to optimize the weights and biases of the warehouse recommendation model after online training using the sparrow search algorithm.

[0053] Optionally, the device further comprises:

[0054] A determination module, used to determine whether the hidden layer output matrix of the warehouse recommendation model after online training is reversible;

[0055] A replacement module is used to replace the data in the hidden layer output matrix when the hidden layer output matrix is ​​not reversible, until the hidden layer output matrix is ​​reversible.

[0056] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0057] one or more processors;

[0058] a storage device for storing one or more programs,

[0059] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any one of the above embodiments.

[0060] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method described in any one of the above embodiments is implemented.

[0061] One embodiment of the above invention has the following advantages or beneficial effects: order information includes the quantity, weight and other information related to the target goods, and real-time warehouse information includes the current warehouse commodity inventory, warehouse queue status and other information related to the warehouse and transportation tasks. According to the above information, a target warehouse that is more suitable for receiving the goods can be screened out, thereby reducing the probability and frequency of temporary modification of the target warehouse during the transportation of the goods, and reducing the cost of goods transportation; during the transportation of the goods, the warehouse recommendation value of the target warehouse is determined according to the order information and the real-time warehouse information obtained again. When the warehouse recommendation value of the target warehouse is less than the warehouse recommendation threshold, the target warehouse is modified, so that the warehouse can be discovered and modified in time. Target warehouses with insufficient storage space and long waiting time for warehousing can improve the efficiency of cargo transportation; determine the replacement warehouse corresponding to the warehouse replacement request, and modify the transportation task when the warehouse recommendation value of the replacement warehouse is greater than or equal to the warehouse recommendation threshold, so that the target user can modify the target warehouse within the recommended range according to actual needs, thereby improving the flexibility of cargo transportation; when there are multiple target warehouses, the transportation task can also be generated according to the request warehouse corresponding to the task generation request, so that the target user can select the target warehouse within the recommended range according to actual needs, thereby further improving the flexibility of cargo transportation; online training and weight optimization of the warehouse recommendation model can further improve the recommendation accuracy of the warehouse recommendation model.

[0062] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0064] Figure 1 is a schematic diagram of the main process of the method for transporting goods according to an embodiment of the present invention;

[0065] Figure 2 It is a schematic diagram of the overall process of a method for transporting goods according to a reference embodiment of the present invention;

[0066] Figure 3 is a schematic diagram of a network structure of a warehouse recommendation model according to a reference embodiment of the present invention;

[0067] Figure 4 It is a schematic diagram of the main process of a method for transporting goods according to a reference embodiment of the present invention;

[0068] Figure 5 is a schematic diagram of the main process of a method for transporting goods according to another reference embodiment of the present invention;

[0069] Figure 6 is a schematic diagram of the main process of a method for transporting goods according to yet another reference embodiment of the present invention;

[0070] Figure 7 is a schematic diagram of main modules of a device for transporting goods according to an embodiment of the present invention;

[0071] Figure 8 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0072] Fig. 9 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0074] It should be noted that in the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0075] Before transporting the target goods, it is usually necessary to determine the target warehouse that receives the target goods based on factors such as warehouse location and warehouse storage capacity, and generate the corresponding transportation task. After transporting the target goods to the target warehouse, if the target warehouse can no longer store the target goods because it is storing other goods, or there are a large number of other goods waiting to be unloaded and put into storage, so that the target goods need to wait for a long time before being stored in the target warehouse, it is necessary to modify the warehouse that receives the target goods and transport the target goods to other warehouses to complete the transportation task. The modified warehouse information will be synchronized to the goods procurement system and other warehouses that receive the goods.

[0076] Since the factors considered when screening warehouses are mainly based on the basic information of the warehouses, the target warehouse often needs to be modified during the execution of the transportation task, which results in high transportation costs. In addition, it is difficult to judge the usage of the target warehouse during transportation. It is often only after arriving at the target warehouse that it is discovered that goods are piled up, queued for warehousing, and there is insufficient remaining storage space in the warehouse, resulting in low cargo transportation efficiency.

[0077] In view of this, according to a first aspect of an embodiment of the present invention, a method for transporting cargo is provided.

[0078] Figure 1 FIG. 1 is a schematic diagram of the main process of the method for transporting goods according to an embodiment of the present invention. Figure 1 As shown, the cargo transportation method according to an embodiment of the present invention mainly includes the following steps S101 to S103.

[0079] Step S101, in response to receiving a delivery request, obtaining corresponding order information and real-time warehouse information of multiple warehouses.

[0080] A delivery request is a request to transport the target goods to a warehouse. The execution subject of the embodiment of the present invention parses the received delivery request to obtain order information and real-time warehouse information of multiple warehouses. The order information includes: information such as the quantity of goods, weight of goods, volume of goods, category of goods, location of goods, etc. The real-time warehouse information includes: information such as the current inventory of goods in each warehouse, the current amount of goods waiting to be put into the warehouse in each warehouse, and the current amount of goods in transit in each warehouse. The warehouse is pre-established, and the execution subject of the embodiment of the present invention sends an information acquisition request to each warehouse to obtain the real-time warehouse information of each warehouse; or each warehouse sends real-time warehouse information to the execution subject of the embodiment of the present invention at regular intervals. The multiple warehouses corresponding to the delivery request are all warehouses that meet the transportation requirements. For example, after the procurement system purchases the target goods in area A1, it sends a delivery request to the execution subject of the embodiment of the present invention. The delivery request does not specifically indicate a warehouse as the target warehouse, but requests that the purchased target goods be transported to a warehouse near area A1. There are multiple warehouses near area A1, so it is necessary to screen out the target warehouse for storing the target goods from multiple warehouses.

[0081] Figure 2 FIG. 1 is a schematic diagram of the overall process of a method for transporting goods according to a reference embodiment of the present invention. Figure 2 As shown, the method of cargo transportation is completed by the execution subject, transfer center and warehouse of the embodiment of the present invention in collaboration, wherein the execution subject of the embodiment of the present invention includes a process control module and a warehouse recommendation model. After the process control module receives the delivery request, the delivery request is parsed to obtain order information, and then the process control module communicates with multiple warehouses to obtain real-time warehouse information of multiple warehouses.

[0082] For example, the delivery request is parsed to obtain "{'goodsWeight':'100'; 'goodsVolume':'10'; 'targetArea':'A1'; 'location':'A2'}", where "'goodsWeight':'100'" indicates that the weight of the target goods is 100 kg, and "'goodsVolume':'10'" indicates that the volume of the target goods is 10 m 3 , "'targetArea':'A1'" indicates that the target goods are requested to be transported to a warehouse within the scope of area A1, "'location':'A2'" indicates that the location of the goods is A2; therefore, according to the pre-set warehouse area division, it is determined that area A1 includes 3 warehouses, and the real-time warehouse information of these 3 warehouses is obtained, and "{'B1':'100,50,10,20,5'; 'B2':'150,80,30,10,4'; 'B3':'200,100,25,15,3'}" is obtained, among which "'B1':'100,50,10,20,5'" indicates that the real-time warehouse information of warehouse B1 includes: the warehouse capacity is 100m 3 , the current storage volume is 50m 3 , the amount of goods waiting to be stored is 10m 3 , the amount of goods in transit is 20m 3 , the distance between warehouse B1 and location A2 is 5km; the real-time warehouse information of warehouse B2 and warehouse B3 is similar.

[0083] Obtaining order information and real-time warehouse information can provide a large amount of reference information for screening target warehouses, including not only the basic information of the target warehouse, but also the dynamic association information between other transportation tasks and various warehouses, which is conducive to screening out target warehouses suitable for storing target goods.

[0084] Step S102: input the order information and the real-time warehouse information into a preset warehouse recommendation model, and use the warehouse recommendation model to determine a target warehouse from the multiple warehouses.

[0085] The warehouse recommendation model is a trained neural network model. During training, the training samples (X i ,t i ), where X i =[x i1 ,x i2 ,...,x in ], x i1 ,x i2 ,...,x inrepresents n factors that affect the selection of target warehouses, such as the inventory of goods in the warehouse, the queuing of goods in the warehouse, the transportation vehicles in transit corresponding to the warehouse, the location of the warehouse, etc., i represents the order of training samples; t i Indicates the actual result corresponding to the warehouse that actually receives the target goods. For example, the warehouse prediction intervals of warehouse C1, warehouse C2, and warehouse C3 are: 0 to 9, 10 to 19, and 20 to 29, respectively. If warehouse C1 is the warehouse that actually receives the target goods, then t i The value of is any value between 0 and 10. The neural network model is trained using the above training samples to obtain a warehouse recommendation model. Exemplarily, the neural network model to be trained is an online sequential extreme learning machine (OS-ELM), and the training samples are divided into two parts with different data volumes. In the first training stage, the weights of the single hidden layer feedforward neural network (SLFN) of the online sequential extreme learning machine are initialized using part of the training samples with less data volume. In the second training stage, the weights of the single hidden layer feedforward neural network are iteratively adjusted using part of the training samples with more data volume, and the trained online sequential extreme learning machine is used as the warehouse recommendation model.

[0086] The acquired order information and real-time warehouse information are used as multiple input parameters that affect the target warehouse screening and are input into the warehouse recommendation model. The trained warehouse recommendation model sets corresponding input weights, biases, and output weights for each input parameter, maps each input parameter according to the input weights and biases, obtains the mapping result of each input parameter, multiplies the mapping result of each input parameter with the corresponding output weight and sums them, and determines the corresponding target warehouse according to the output result. For example, Figure 2 As shown, the process control module sends the acquired order information and real-time warehouse information to the warehouse recommendation model, so that the warehouse recommendation model determines the target warehouse from multiple warehouses.

[0087] Figure 3 Schematic diagram of the network structure of a warehouse recommendation model according to a reference embodiment of the present invention. Figure 3 As shown in the figure, the warehouse recommendation model is a trained online sequential extreme learning machine that takes the acquired order information such as cargo category, cargo weight, cargo volume, cargo location, and real-time warehouse information such as cargo storage volume, cargo waiting to be stored, and cargo in transit in multiple warehouses as input parameters [x1, x2, ..., x m ], each input parameter has a corresponding input weight [w1,w2,...,w p ] and bias [b1,b2,...,b q], map the input parameters to the hidden layer h according to the weights and biases, and map the output weights [β1,β2,...,β r ], perform weighted summation on the mapping results of each input parameter, and obtain the output result y; pre-set the corresponding warehouse prediction interval for each warehouse, the warehouse prediction interval is a range value, which is used to screen the target warehouse, and there is no intersection between the warehouse prediction intervals corresponding to each warehouse; determine which warehouse prediction interval the output result falls into, for example, the warehouse prediction intervals of warehouse C4, warehouse C5 and warehouse C6 are: 5 to 14, 15 to 24 and 25 to 34 respectively. If the output result is equal to 20, it is determined that the target warehouse is warehouse C5. As another example, the warehouse recommendation model outputs a result matrix [C7:3, C8:6, C9:9], and each element in the result matrix corresponds to the output result of a warehouse, where the output result corresponding to warehouse C7 is 3, the output result corresponding to warehouse C8 is 6, and the output result corresponding to warehouse C9 is 9. It is determined that the warehouse corresponding to the output result with the largest value is warehouse C9, and warehouse C9 is used as the target warehouse.

[0088] By using order information, real-time warehouse information and the corresponding actual warehouse as training samples, a warehouse recommendation model with higher prediction accuracy can be trained; the order information and real-time warehouse information corresponding to the delivery request are input into the warehouse recommendation model, and each influencing factor input into the warehouse recommendation model has a corresponding weight to distinguish the importance of different influencing factors, so that the warehouse recommendation model can quickly determine the target warehouse suitable for receiving the target goods based on multiple influencing factors, and try to avoid modifying the target warehouse during transportation.

[0089] Step S103, generating a transportation task according to the target warehouse, so that the target goods corresponding to the delivery request are transported to the target warehouse.

[0090] After determining the target warehouse, a transportation task with the target warehouse as the destination is generated, and the generated transportation task is sent to the transportation personnel, who transport the target goods to the target warehouse according to the transportation task. The transportation task is sent to the initiator of the delivery request (for example, the procurement system for purchasing the target goods) so that the initiator of the delivery request can understand the transportation progress of the target goods, and the transportation task is sent to the target warehouse so that the target warehouse stores the corresponding transportation task, so that when the real-time warehouse information of the target warehouse is obtained next time, the real-time warehouse information containing the above transportation task is obtained. For example, before generating the transportation task, the real-time warehouse information of the target warehouse is queried, and the in-transit transportation vehicle situation corresponding to the target warehouse includes: vehicles transporting goods D1 and vehicles transporting goods D2; after sending the transportation task of goods D3 to the target warehouse, the real-time warehouse information of the target warehouse is queried again, and the in-transit transportation vehicle situation corresponding to the target warehouse includes: vehicles transporting goods D1, vehicles transporting goods D2, and vehicles transporting goods D3.

[0091] For example, Figure 2 As shown in the figure, the warehouse recommendation model sends the relevant information of the determined target warehouse to the process control module, which generates the corresponding transportation task according to the target warehouse, and then sends the transportation task to the transfer center, so that the transfer center notifies the transportation personnel to perform the transportation task, and then sends the transportation task to the target warehouse and the delivery request initiator. After the target goods arrive at the target warehouse, the target warehouse will store the target goods.

[0092] Sending the generated transportation task to the transportation personnel can enable the transportation personnel to perform the transportation task in a timely manner. Sending the transportation task to the initiator of the delivery request can enable the initiator of the delivery request to understand the transportation status of the target goods in a timely manner. Sending the transportation task to the target warehouse can update the real-time warehouse information of the target warehouse in a timely manner, improve the accuracy of the real-time warehouse information, and help ensure the prediction accuracy of the warehouse recommendation model.

[0093] According to a reference embodiment of the present invention, before the target goods corresponding to the delivery request are transported to the target warehouse, the method further includes: after receiving the information update request, re-acquiring the real-time warehouse information of multiple warehouses, the real-time warehouse information acquired again may be different from the real-time warehouse information acquired previously, for example, the goods waiting to be stored in the warehouse have been stored or are being transported to other warehouses, for example, the goods previously in transit have changed the warehouse receiving the goods, for example, some goods in the target warehouse have been sold, resulting in an increase in the storage space available in the target warehouse, etc. The real-time warehouse information acquired again is input into the warehouse recommendation model, and the warehouse recommendation model is used to determine the warehouse prediction value and the warehouse recommendation values ​​of multiple warehouses; the warehouse prediction value represents the prediction value corresponding to the newly predicted warehouse suitable for receiving the target goods, each warehouse has a corresponding warehouse prediction interval, and when the warehouse prediction value falls within the warehouse prediction interval of a certain warehouse, it is determined that the warehouse is used to receive the target goods. Since the real-time warehouse information may have changed, the warehouse recommendation model may also be different from the previously predicted target warehouse. Each warehouse corresponds to a warehouse recommendation value, which indicates whether the warehouse is suitable for receiving the target goods. For example, the higher the warehouse recommendation value, the more suitable the warehouse is for receiving the target goods, which means that the warehouse has more sufficient storage space, less goods waiting to be stored, and less goods in transit compared to other warehouses.

[0094] A warehouse recommendation threshold is set in advance. The warehouse recommendation threshold represents the minimum warehouse recommendation value of the warehouse that can receive the target goods. When the warehouse recommendation value of the target warehouse is less than the warehouse recommendation threshold, it means that the previously predicted target warehouse no longer meets the minimum requirements for receiving the target goods and is not suitable for receiving the target goods. Then, the warehouse whose warehouse prediction interval contains the warehouse prediction value is used as the recommended warehouse, and the target warehouse in the transportation task is modified to the recommended warehouse, so that the target goods are transported to the recommended warehouse, and the target goods are no longer transported to the target warehouse. For example, the warehouse prediction interval corresponding to warehouse E1 is 0-14, the warehouse prediction interval corresponding to warehouse E2 is 15-29, and the warehouse prediction interval corresponding to warehouse E3 is 30-44. Since the warehouse prediction value is equal to 10, warehouse E1 is used as the recommended warehouse. The modified transportation task is sent to the transportation personnel, so that the target goods corresponding to the delivery request are transported to the recommended warehouse; the modified transportation task is sent to the initiator of the delivery request, so that it can understand the transportation progress of the target goods; a prompt message "the transportation task has been modified" is sent to the target warehouse, so that the target warehouse deletes the corresponding transportation task, and the modified transportation task is sent to the recommended warehouse, so that the recommended warehouse stores the corresponding transportation task.

[0095] For example, Figure 2 As shown, the process control module obtains the real-time warehouse information again according to the received information update request; the process control module sends the real-time warehouse information obtained again to the warehouse recommendation model, so that the warehouse recommendation model determines whether the warehouse recommendation value of the target warehouse is greater than or equal to the warehouse recommendation threshold. When the warehouse recommendation threshold of the target warehouse is greater than or equal to the warehouse recommendation threshold, the prompt information that the target warehouse meets the requirements is returned, so that the process control module continues to wait for the next information update request. When the warehouse recommendation threshold of the target warehouse is less than the warehouse recommendation threshold, it is determined that the target warehouse does not meet the transportation requirements, and the recommended warehouse is selected from other warehouses, and the relevant information of the recommended warehouse is sent to the process control module. The process control module modifies the transportation task according to the recommended warehouse, and sends the modified transportation task to the transfer center, so that the transfer center executes the modified transportation task and notifies the target warehouse, the recommended warehouse and the delivery request initiator. After the target goods arrive at the recommended warehouse, the recommended warehouse will store the target goods in the warehouse.

[0096] Based on the warehouse recommendation value, it is possible to quickly and accurately determine whether the previously predicted target warehouse is still suitable for receiving the target goods. When the target warehouse is no longer suitable for receiving the target goods, the recommended warehouse can be quickly and accurately determined based on the warehouse prediction value, and the transportation task can be modified in time and sent to the transportation personnel, thereby ensuring transportation efficiency and accuracy, avoiding the transportation personnel finding that the target goods cannot be received after arriving at the target warehouse, and reducing transportation costs.

[0097] According to another reference embodiment of the present invention, when determining the recommended warehouse according to the warehouse prediction value, a self-learning method is used to improve the prediction accuracy. Specifically, the warehouse recommendation value and the warehouse prediction value of the target warehouse are subtracted, the subtraction result is integrated over time, and the integral result and the warehouse prediction value are summed to determine the warehouse prediction interval corresponding to the summation result, each warehouse prediction interval corresponds to a warehouse, and the warehouse corresponding to the warehouse prediction interval is used as the recommended warehouse.

[0098] For example, assuming that the warehouse recommendation value of the target warehouse is A(i), and the warehouse prediction value at the i-th moment after the target warehouse is determined is Y(i), the warehouse recommendation value of the target warehouse and the warehouse prediction value are subtracted to obtain the subtraction result A(i)-Y(i); then, from the moment the target warehouse is determined to the moment the warehouse prediction value is determined, the subtraction result is integrated over time to obtain Use the preset self-learning coefficient α to multiply the integral result to obtain Add the integral result after multiplying the self-learning coefficient to the warehouse forecast value at the i-th moment to get the sum result For example, there are currently multiple warehouse prediction intervals, including: warehouse prediction interval 1-10 corresponding to warehouse F1, warehouse prediction interval 11-20 corresponding to warehouse F2, and warehouse prediction interval 21-30 corresponding to warehouse F3. The corresponding warehouse will be used as the recommended warehouse if the sum result is within the warehouse prediction interval.

[0099] Using self-learning methods to predict the warehouse used to receive the target goods can further consider the impact of time factors on the screening warehouse, determine the recommended warehouse based on the warehouse recommendation value, warehouse prediction value and other data at multiple times of the target warehouse, improve the accuracy of warehouse prediction, timely discover and modify the target warehouse, and improve the efficiency of cargo transportation.

[0100] According to another reference embodiment of the present invention, when the warehouse recommendation value of the target warehouse is greater than or equal to the warehouse recommendation threshold, it means that the target warehouse is still suitable for receiving the target goods, and the method further includes: parsing the received warehouse replacement request to determine the corresponding replacement warehouse; searching for the warehouse recommendation value of the replacement warehouse in the warehouse recommendation values ​​of multiple warehouses; when the warehouse recommendation value of the replacement warehouse is greater than or equal to the warehouse recommendation threshold, it means that the replacement warehouse is also suitable for receiving the target warehouse, then modifying the transportation task according to the replacement warehouse, that is, modifying the target warehouse in the transportation task to the replacement warehouse, sending the modified transportation task to the transportation personnel, so that the target goods corresponding to the delivery request are transported to the replacement warehouse; sending the modified transportation task to the initiator of the delivery request so that it can understand the transportation progress of the target goods; sending a prompt message of "transportation task has been modified" to the target warehouse, so that the target warehouse deletes the corresponding transportation task, sends the modified transportation task to the replacement warehouse, and makes the replacement warehouse store the corresponding transportation task. When the warehouse recommendation value of the replacement warehouse is less than the warehouse recommendation threshold, it means that the replacement warehouse is not suitable for receiving the target goods, therefore, a prompt message is generated, indicating that the replacement warehouse does not meet the conditions for receiving the target goods, and the target warehouse in the transportation task cannot be modified to the replacement warehouse.

[0101] Exemplarily, the pre-set warehouse recommendation threshold is 75, and the warehouse recommendation values ​​of multiple warehouses include "{'Warehouse G1':'80'; 'Warehouse G2':'75'; 'Warehouse G3':'60'; 'Warehouse G4':'85'; 'Warehouse G5':'50'}", where the target warehouse is warehouse G1. Although the target warehouse is suitable for receiving the target goods, the manager can still modify the transportation task. The warehouse replacement request sent by the manager is parsed to determine that the replacement warehouse is warehouse G4. Since the warehouse recommendation value of warehouse G4 is greater than the warehouse recommendation threshold, it means that warehouse G4 is also suitable for receiving the target goods. Therefore, the target warehouse in the transportation task is changed to a replacement warehouse, that is, the target goods are transported to warehouse G4.

[0102] Determine the replacement warehouse corresponding to the warehouse replacement request, and modify the transportation task when the warehouse recommendation value of the replacement warehouse is greater than or equal to the warehouse recommendation threshold. This allows the target user to modify the target warehouse within the recommended range according to actual needs, thereby improving the flexibility of cargo transportation.

[0103] According to another reference embodiment of the present invention, there are multiple target warehouses determined by the warehouse recommendation model; when generating a transportation task based on the target warehouse, the received task generation request is parsed to determine the corresponding request warehouse; it is determined whether the request warehouse belongs to one of the multiple target warehouses. If the request warehouse is one of the multiple target warehouses, a transportation task is generated based on the request warehouse, and the transportation task is sent to the transportation personnel so that the target goods corresponding to the delivery request are transported to the request warehouse; the transportation task is sent to the initiator of the delivery request so that it can understand the transportation progress of the target goods; the transportation task is sent to the request warehouse so that the request warehouse stores the corresponding transportation task. If the request warehouse is not one of the multiple target warehouses,

[0104] Exemplarily, the target warehouses determined by the warehouse recommendation model include warehouse H1, warehouse H2 and warehouse H3. These three warehouses can all be used to receive the target goods, and the manager decides which warehouse to select to receive the target goods; the task generation request sent by the manager is parsed to determine that the corresponding request warehouse is warehouse H2. Since warehouse H2 is one of the target warehouses determined by the warehouse recommendation model, a transportation task is generated based on warehouse H2; if the request warehouse obtained by parsing is warehouse H4, since warehouse H4 is not the target warehouse determined by the warehouse recommendation model, a prompt message is generated, indicating that warehouse H4 is not suitable for receiving the target warehouse and the transportation task cannot be generated. Please select a warehouse for receiving the target goods from the target warehouses determined by the warehouse recommendation model.

[0105] When there are multiple target warehouses, a transportation task can also be generated according to the request warehouse corresponding to the task generation request, allowing the target user to select the target warehouse within the recommended range according to actual needs, further improving the flexibility of cargo transportation.

[0106] According to a reference embodiment of the present invention, the method further includes: inputting the acquired order information and real-time warehouse information into a warehouse recommendation model, and performing online training on the warehouse recommendation model. Taking the warehouse recommendation model as an example, the output weight of the hidden layer of the warehouse recommendation model is β = [β1, β2, ..., β m ], the output matrix of the hidden layer is:

[0107]

[0108] Among them, w1,...,w m represents the input weights, b1,...,b m represents the bias, X1,...,X N0represents the input parameters, i.e., order information and real-time warehouse information, and g(...) is the activation function. Therefore, the output result of the warehouse recommendation model is H0*β, and the actual result corresponding to the warehouse that actually receives the target goods determined based on the order information and real-time warehouse information is The training goal of online training is to reduce the error between the output result and the true result, that is, min||H0β-T0|| is as small as possible. When the online ELM is trained online, the output weight β of the hidden layer needs to be adjusted continuously. Assume that the output matrix of the hidden layer after the K+1th online training is H k+1 , then the output weight Among them, β k represents the output weight obtained after the kth online training, T k+1 represents the true result of the K+1th online training, P k+1 Represents the intermediate matrix constructed from the generalized inverse matrix of the hidden layer output matrix.

[0109] Use the sparrow search algorithm to optimize the weights and biases of the warehouse recommendation model after online training. Take the warehouse recommendation model as an example, which is a trained online extreme learning machine. Assume that the matrix corresponding to the output weights and biases to be optimized is:

[0110]

[0111] Where n represents the number of output weights and biases, and d represents the dimension of the output weights and biases. In each optimization process of the output weights and biases, the update results are as follows:

[0112]

[0113] Among them, t+1 represents the current optimization times, itermax represents the maximum optimization times, and X ij Represents the element in the i-th row and j-th column of the matrix corresponding to the output weight and bias; α is a coefficient, between 0 and 1; L represents the 1*d unit matrix, Q represents a normally distributed random number; R2 is the warning value of the element, which is a random number between 0 and 1; ST is the safety value of the element, which is a constant between 0.5 and 1. When the warning value of the element is less than the safety value, the element value is updated by performing an exponential operation on the number of optimizations. When the warning value of the element is greater than or equal to the safety value, the element value is updated using the unit matrix and a normally distributed random number.

[0114] Online training and weight optimization of the warehouse recommendation model can further improve the recommendation accuracy of the warehouse recommendation model and ensure prediction accuracy.

[0115] According to another reference embodiment of the present invention, before using the sparrow search algorithm to optimize the weights and biases of the warehouse recommendation model after online training, the method further includes: determining whether the hidden layer output matrix of the warehouse recommendation model after online training is reversible. When optimizing the output weight β, the output weight β needs to satisfy the condition: β = H + *T, where H + represents the generalized inverse matrix of the hidden layer output matrix, and T represents the actual result corresponding to the warehouse that actually receives the target goods. If the hidden layer output matrix is ​​not reversible, the output weight cannot be optimized, resulting in stagnation of the optimization process. Therefore, when the hidden layer output matrix is ​​not reversible, the data in the hidden layer output matrix is ​​replaced until the hidden layer output matrix is ​​reversible. The hidden layer output matrix is ​​an n*n matrix, for example, a 5*5 matrix or a 10*10 matrix.

[0116] Exemplarily, if it is determined that the hidden layer output matrix is ​​not reversible, it means that the hidden layer output matrix includes at least two rows of data with the same elements or at least two rows of data with elements in a multiple relationship. Therefore, each row of elements is traversed in turn to find the elements that are the same as other rows of data or elements that are multiples of other rows of data, and then use random numbers to replace the elements in this row, and then determine again whether the hidden layer output matrix after random replacement is reversible. If it is still not reversible, continue to look for the same or multiple elements and perform random replacement until the hidden layer output matrix is ​​reversible.

[0117] When the hidden layer output matrix is ​​irreversible, randomly replacing the corresponding elements can ensure the smooth progress of the optimization process and further improve the recommendation accuracy of the warehouse recommendation model.

[0118] Figure 4 FIG. 1 is a schematic diagram of the main process of a method for transporting goods according to a reference embodiment of the present invention. Figure 4 As shown, the cargo transportation method may include:

[0119] Step S401, in response to receiving a delivery request, obtaining corresponding order information and real-time warehouse information of multiple warehouses;

[0120] Step S402, inputting the order information and the real-time warehouse information into a preset warehouse recommendation model, and using the warehouse recommendation model to determine a plurality of target warehouses from a plurality of warehouses;

[0121] Step S403, in response to receiving the task generation request, determining a corresponding request warehouse;

[0122] Step S404, determine whether the requested warehouse is the target warehouse, if so, jump to step S405, otherwise, jump to step S406;

[0123] Step S405, generating a transport task according to the requested warehouse, so that the target goods corresponding to the delivery request are transported to the requested warehouse;

[0124] Step S406, generating a prompt message, indicating that the requested warehouse is not suitable for receiving the target goods, and please select from multiple target warehouses.

[0125] The specific implementation content of the cargo transportation method of the above-mentioned reference embodiment of the present invention has been described in detail in the above-mentioned cargo transportation method, so the repeated content will not be described again here.

[0126] Figure 5 FIG. 1 is a schematic diagram of the main process of a method for transporting goods according to another reference embodiment of the present invention. Figure 5 As shown, the cargo transportation method may include:

[0127] Step S501, in response to receiving a delivery request, obtaining corresponding order information and real-time warehouse information of multiple warehouses;

[0128] Step S502, inputting the order information and the real-time warehouse information into a preset warehouse recommendation model, and using the warehouse recommendation model to determine a plurality of target warehouses from a plurality of warehouses;

[0129] Step S503, in response to receiving the task generation request, determining a corresponding request warehouse;

[0130] Step S504, determine whether the requested warehouse is the target warehouse, if so, jump to step S506, otherwise, jump to step S505;

[0131] Step S505, generating a prompt message indicating that the requested warehouse is not suitable for receiving the target goods, and requesting selection from multiple target warehouses;

[0132] Step S506, generating a transport task according to the requested warehouse, so that the target goods corresponding to the delivery request are transported to the requested warehouse;

[0133] Step S507, in response to receiving the information update request, obtaining real-time warehouse information of the plurality of warehouses again;

[0134] Step S508, inputting the real-time warehouse information acquired again into the warehouse recommendation model, and using the warehouse recommendation model to determine the warehouse prediction value and the warehouse recommendation values ​​of the plurality of warehouses;

[0135] Step S509, determining whether the warehouse recommendation value of the target warehouse is greater than or equal to the preset warehouse recommendation threshold, if yes, jump to step S507, otherwise, jump to step S510;

[0136] Step S510, determining a recommended warehouse according to the warehouse prediction value, and modifying the transportation task according to the recommended warehouse, so that the target goods corresponding to the delivery request are transported to the recommended warehouse instead of the target warehouse.

[0137] The specific implementation content of the cargo transportation method of another reference embodiment of the present invention has been described in detail in the cargo transportation method described above, so the repeated content will not be described here.

[0138] Figure 6 FIG. 1 is a schematic diagram of the main process of a method for transporting goods according to another reference embodiment of the present invention. Figure 6 As shown, the cargo transportation method may include:

[0139] Step S601, in response to receiving a delivery request, obtaining corresponding order information and real-time warehouse information of multiple warehouses;

[0140] Step S602, inputting the order information and the real-time warehouse information into a preset warehouse recommendation model, and using the warehouse recommendation model to determine a plurality of target warehouses from a plurality of warehouses;

[0141] Step S603, in response to receiving the task generation request, determining a corresponding request warehouse;

[0142] Step S604, determine whether the requested warehouse is the target warehouse, if so, jump to step S606, otherwise, jump to step S605;

[0143] Step S605, generating a prompt message, indicating that the requested warehouse is not suitable for receiving the target goods, and requesting selection from multiple target warehouses;

[0144] Step S606, generating a transport task according to the requested warehouse, so that the target goods corresponding to the delivery request are transported to the requested warehouse;

[0145] Step S607, in response to receiving the information update request, obtaining real-time warehouse information of the plurality of warehouses again;

[0146] Step S608, inputting the real-time warehouse information acquired again into the warehouse recommendation model, and using the warehouse recommendation model to determine the warehouse prediction value and the warehouse recommendation values ​​of the plurality of warehouses;

[0147] Step S609, determining whether the warehouse recommendation value of the target warehouse is greater than or equal to a preset warehouse recommendation threshold, if yes, jump to step S611, otherwise, jump to step S610;

[0148] Step S610, determining a recommended warehouse according to the warehouse prediction value, and modifying the transportation task according to the recommended warehouse so that the target goods corresponding to the delivery request are transported to the recommended warehouse instead of the target warehouse;

[0149] Step S611, in response to receiving the warehouse replacement request, determining a corresponding replacement warehouse;

[0150] Step S612, determining whether the warehouse recommendation value of the replacement warehouse is greater than or equal to a preset warehouse recommendation threshold, if yes, jump to step S614, otherwise, jump to step S613;

[0151] Step S613, generating a prompt message indicating that the replacement warehouse is not suitable for receiving the target goods;

[0152] Step S614, modifying the transport task according to the replacement warehouse so that the target goods corresponding to the delivery request are transported to the replacement warehouse.

[0153] The specific implementation content of the method for transporting goods in another reference embodiment of the present invention has been described in detail in the above-mentioned method for transporting goods, so the repeated content will not be described here.

[0154] According to a second aspect of an embodiment of the present invention, a device for transporting cargo is provided.

[0155] Figure 7 Schematic diagram of the main modules of the device for transporting goods according to an embodiment of the present invention. Figure 7 As shown, the cargo transportation device 700 mainly includes:

[0156] An acquisition module 701 is used to acquire corresponding order information and real-time warehouse information of multiple warehouses in response to receiving a delivery request;

[0157] A determination module 702, configured to input the order information and the real-time warehouse information into a preset warehouse recommendation model, and use the warehouse recommendation model to determine a target warehouse from the multiple warehouses;

[0158] The generating module 703 is used to generate a transportation task according to the target warehouse, so that the target goods corresponding to the delivery request are transported to the target warehouse.

[0159] According to a reference embodiment of the present invention, the cargo transportation device 700 further includes:

[0160] a repeated acquisition module, configured to acquire again the real-time warehouse information of the plurality of warehouses in response to receiving the information update request;

[0161] a value determination module, configured to input the real-time warehouse information acquired again into the warehouse recommendation model, and use the warehouse recommendation model to determine a warehouse prediction value and warehouse recommendation values ​​of the plurality of warehouses;

[0162] The first modification module is used to determine the recommended warehouse according to the warehouse prediction value when the warehouse recommendation value of the target warehouse is less than a preset warehouse recommendation threshold value, and to modify the transportation task according to the recommended warehouse so that the target goods corresponding to the delivery request are transported to the recommended warehouse.

[0163] According to another reference embodiment of the present invention, determining a recommended warehouse according to the warehouse prediction value includes:

[0164] Integrating the difference between the warehouse recommendation value of the target warehouse and the warehouse prediction value;

[0165] summing the integral result and the warehouse prediction value;

[0166] A warehouse prediction interval corresponding to the summation result is determined, and the warehouse corresponding to the warehouse prediction interval is used as a recommended warehouse.

[0167] According to another reference embodiment of the present invention, the cargo transportation device 700 further includes:

[0168] A warehouse determination module, configured to determine a corresponding replacement warehouse in response to receiving a warehouse replacement request;

[0169] A second modification module is used to modify the transportation task according to the replacement warehouse so that the target goods corresponding to the delivery request are transported to the replacement warehouse when the warehouse recommendation value of the replacement warehouse is greater than or equal to the warehouse recommendation threshold;

[0170] The prompt module is used to generate a prompt message when the warehouse recommendation value of the replacement warehouse is less than the warehouse recommendation threshold.

[0171] According to another reference embodiment of the present invention, there are multiple target warehouses; generating a transportation task according to the target warehouses includes:

[0172] In response to receiving the task generation request, determining a corresponding request repository;

[0173] In the case that the requesting warehouse is one of a plurality of target warehouses, a transportation task is generated according to the requesting warehouse, so that the target goods corresponding to the delivery request are transported to the requesting warehouse.

[0174] According to another reference embodiment of the present invention, the cargo transportation device 700 further includes:

[0175] An online training module, used to perform online training on the warehouse recommendation model using the order information and the real-time warehouse information;

[0176] The optimization module is used to optimize the weights and biases of the warehouse recommendation model after online training using the sparrow search algorithm.

[0177] According to a reference embodiment of the present invention, the cargo transportation device 700 further includes:

[0178] A determination module, used to determine whether the hidden layer output matrix of the warehouse recommendation model after online training is reversible;

[0179] A replacement module is used to replace the data in the hidden layer output matrix when the hidden layer output matrix is ​​not reversible, until the hidden layer output matrix is ​​reversible.

[0180] It should be noted that the specific implementation content of the device for transporting goods in the embodiment of the present invention has been described in detail in the method for transporting goods described above, so the repeated content will not be described again here.

[0181] According to the technical solution of the embodiment of the present invention, the order information includes various information related to the target goods, such as the quantity and weight, and the real-time warehouse information includes various information related to the warehouse and transportation tasks, such as the current warehouse commodity inventory, warehouse queue status, etc. Based on the above information, a target warehouse that is more suitable for receiving the goods can be screened out, thereby reducing the probability and frequency of temporary modification of the target warehouse during the transportation of the goods, thereby reducing the cost of goods transportation; during the transportation of the goods, the warehouse recommendation value of the target warehouse is determined according to the order information and the real-time warehouse information obtained again. When the warehouse recommendation value of the target warehouse is less than the warehouse recommendation threshold, the target warehouse is modified, so that the warehouse storage space can be discovered and modified in time. The target warehouses with insufficient inventory or long waiting time for warehousing can be selected to improve the efficiency of cargo transportation. The replacement warehouse corresponding to the warehouse replacement request can be determined, and the transportation task can be modified when the warehouse recommendation value of the replacement warehouse is greater than or equal to the warehouse recommendation threshold. This allows the target user to modify the target warehouse within the recommended range according to actual needs, thereby improving the flexibility of cargo transportation. When there are multiple target warehouses, a transportation task can also be generated according to the requested warehouse corresponding to the task generation request, allowing the target user to select the target warehouse within the recommended range according to actual needs, thereby further improving the flexibility of cargo transportation. Online training and weight optimization of the warehouse recommendation model can further improve the recommendation accuracy of the warehouse recommendation model.

[0182] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for transporting cargo, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided by the first aspect of the embodiment of the present invention.

[0183] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0184] Figure 8 An exemplary system architecture 800 is shown to which the method or apparatus for transporting goods according to the embodiments of the present invention may be applied.

[0185] like Figure 8 As shown, system architecture 800 may include terminal devices 801, 802, 803, a network 804, and a server 805. Network 804 is used to provide a medium for communication links between terminal devices 801, 802, 803 and server 805. Network 804 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0186] Users can use terminal devices 801, 802, and 803 to interact with server 805 through network 804 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 801, 802, and 803, such as cargo transportation applications, warehouse information viewing applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0187] The terminal devices 801 , 802 , and 803 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0188] Server 805 may be a server that provides various services, such as a background management server (for example only) that provides support for the request for cargo transportation sent by the upstream terminal devices 801, 802, and 803. In response to receiving the delivery request, the background management server may obtain the corresponding order information and the real-time warehouse information of multiple warehouses; input the order information and the real-time warehouse information into a preset warehouse recommendation model, and use the warehouse recommendation model to determine the target warehouse from the multiple warehouses; generate a transportation task according to the target warehouse, so that the target cargo corresponding to the delivery request is transported to the target warehouse; and feedback the cargo transportation situation (for example only) to the terminal device.

[0189] It should be noted that the cargo transportation method provided in the embodiment of the present invention is generally executed by the server 805, and accordingly, the cargo transportation device is generally set in the server 805. The cargo transportation method provided in the embodiment of the present invention can also be executed by the terminal devices 801, 802, and 803, and accordingly, the cargo transportation device can be set in the terminal devices 801, 802, and 803.

[0190] It should be understood that Figure 8 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0191] Reference below Fig. 9 , which shows a schematic diagram of the structure of a computer system 900 of a terminal device suitable for implementing an embodiment of the present invention. Fig. 9 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0192] like Fig. 9 As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the system 900 are also stored. The CPU 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0193] The following components are connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage section 908 as needed.

[0194] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the central processing unit (CPU) 901, the above-mentioned functions defined in the system of the embodiment of the present invention are executed.

[0195] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In an embodiment of the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0196] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0197] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor, for example, it may be described as: a processor includes an acquisition module, a determination module, and a generation module, wherein the names of these modules do not constitute a limitation on the modules themselves in certain circumstances, for example, the acquisition module may also be described as a "module for acquiring order information and real-time warehouse information".

[0198] As another aspect, an embodiment of the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device implements the following method: in response to receiving a delivery request, obtaining corresponding order information and real-time warehouse information of multiple warehouses; inputting the order information and the real-time warehouse information into a preset warehouse recommendation model, and using the warehouse recommendation model to determine a target warehouse from the multiple warehouses; generating a transportation task according to the target warehouse, so that the target goods corresponding to the delivery request are transported to the target warehouse.

[0199] According to the technical solution of the embodiment of the present invention, the order information includes various information related to the target goods, such as the quantity and weight, and the real-time warehouse information includes various information related to the warehouse and transportation tasks, such as the current warehouse commodity inventory, warehouse queue status, etc. Based on the above information, a target warehouse that is more suitable for receiving the goods can be screened out, thereby reducing the probability and frequency of temporary modification of the target warehouse during the transportation of the goods, thereby reducing the cost of goods transportation; during the transportation of the goods, the warehouse recommendation value of the target warehouse is determined according to the order information and the real-time warehouse information obtained again. When the warehouse recommendation value of the target warehouse is less than the warehouse recommendation threshold, the target warehouse is modified, so that the warehouse storage space can be discovered and modified in time. The target warehouses with insufficient inventory or long waiting time for warehousing can be selected to improve the efficiency of cargo transportation. The replacement warehouse corresponding to the warehouse replacement request can be determined, and the transportation task can be modified when the warehouse recommendation value of the replacement warehouse is greater than or equal to the warehouse recommendation threshold. This allows the target user to modify the target warehouse within the recommended range according to actual needs, thereby improving the flexibility of cargo transportation. When there are multiple target warehouses, a transportation task can also be generated according to the requested warehouse corresponding to the task generation request, allowing the target user to select the target warehouse within the recommended range according to actual needs, thereby further improving the flexibility of cargo transportation. Online training and weight optimization of the warehouse recommendation model can further improve the recommendation accuracy of the warehouse recommendation model.

[0200] The above specific implementations do not constitute a limitation on the protection scope of the embodiments of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. A method for transporting goods, characterized in that: include: In response to receiving a delivery request, obtaining corresponding order information and real-time warehouse information of multiple warehouses; Inputting the order information and the real-time warehouse information into a preset warehouse recommendation model, and using the warehouse recommendation model to determine a target warehouse from the multiple warehouses; A transportation task is generated according to the target warehouse, so that the target goods corresponding to the delivery request are transported to the target warehouse.

2. The method according to claim 1, characterized in that Before transporting the target goods corresponding to the delivery request to the target warehouse, the method further includes: In response to receiving the information update request, acquiring again the real-time warehouse information of the plurality of warehouses; Inputting the real-time warehouse information acquired again into the warehouse recommendation model, and using the warehouse recommendation model to determine a warehouse prediction value and warehouse recommendation values ​​of the plurality of warehouses; When the warehouse recommendation value of the target warehouse is less than a preset warehouse recommendation threshold, the recommended warehouse is determined according to the warehouse prediction value, and the transportation task is modified according to the recommended warehouse so that the target goods corresponding to the delivery request are transported to the recommended warehouse.

3. The method according to claim 2, characterized in that Determining a recommended warehouse according to the warehouse prediction value includes: Integrating the difference between the warehouse recommendation value of the target warehouse and the warehouse prediction value; summing the integral result and the warehouse prediction value; A warehouse prediction interval corresponding to the summation result is determined, and the warehouse corresponding to the warehouse prediction interval is used as a recommended warehouse.

4. The method according to claim 2, characterized in that: When the warehouse recommendation value of the target warehouse is greater than or equal to the warehouse recommendation threshold, the method further includes: In response to receiving the warehouse replacement request, determining a corresponding replacement warehouse; When the warehouse recommendation value of the replacement warehouse is greater than or equal to the warehouse recommendation threshold, modifying the transportation task according to the replacement warehouse so that the target goods corresponding to the delivery request are transported to the replacement warehouse; When the warehouse recommendation value of the replacement warehouse is less than the warehouse recommendation threshold, a prompt message is generated.

5. The method according to claim 1, characterized in that: There are multiple target warehouses; generating a transportation task according to the target warehouses includes: In response to receiving the task generation request, determining a corresponding request repository; In the case that the requesting warehouse is one of a plurality of target warehouses, a transportation task is generated according to the requesting warehouse, so that the target goods corresponding to the delivery request are transported to the requesting warehouse.

6. The method according to claim 1, characterized in that The method further comprises: Performing online training on the warehouse recommendation model using the order information and the real-time warehouse information; The sparrow search algorithm is used to optimize the weights and biases of the warehouse recommendation model after online training.

7. The method according to claim 6, characterized in that Before optimizing the weights and biases of the warehouse recommendation model after online training using the sparrow search algorithm, the method further includes: Determining whether the hidden layer output matrix of the warehouse recommendation model after the online training is reversible; When the hidden layer output matrix is ​​not reversible, the data in the hidden layer output matrix is ​​replaced until the hidden layer output matrix is ​​reversible.

8. A device for transporting goods, characterized in that: include: an acquisition module, for acquiring corresponding order information and real-time warehouse information of multiple warehouses in response to receiving a delivery request; a determination module, configured to input the order information and the real-time warehouse information into a preset warehouse recommendation model, and determine a target warehouse from the plurality of warehouses using the warehouse recommendation model; A generation module is used to generate a transportation task according to the target warehouse, so that the target goods corresponding to the delivery request are transported to the target warehouse.

9. An electronic device, characterized in that: include: One or more processors; A storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images