Transfer logistics scheduling method and device, equipment and medium

Abstract

The embodiment of the invention discloses a transfer logistics scheduling method and device, equipment and a medium, and the method comprises the steps: obtaining preset storage and transportation real-time data related to the transfer condition of a target article based on a preset frequency in a process of transferring the target article to an original target warehouse; inputting the preset storage and transportation real-time data into a pre-trained transfer warehouse distribution model, and determining a real-time distribution target warehouse of the target article according to a model output result; and under the condition that the real-time distribution target warehouse is different from the original target warehouse, carrying out transfer warehouse switching prompt early warning so as to realize logistics scheduling of the target article in the transfer process. According to the technical scheme, the problem that the abnormal condition of the target warehouse cannot be responded in time in the article transfer process is solved, the storage state of the target warehouse can be obtained in time, transfer logistics scheduling can be carried out, the logistics scheduling accuracy is improved, and the situation that a large number of articles cannot be transferred and warehoused in time is avoided.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of logistics information technology, and in particular to a method, device, equipment and medium for transport logistics scheduling. Background Art

[0002] When providing bulk cargo transshipment services to manufacturers, the cargo is often transported from a factory or warehouse to a transshipment center, or vice versa, based on the cargo order. For example, when a transshipment task executor performs a warehouse delivery task, they transport the cargo to the target warehouse specified in the cargo order.

[0003] However, in the process of implementing the present invention, it was found that there are at least the following technical problems in the prior art:

[0004] During the transfer process, the target warehouse may experience an overflow or long queues, necessitating a change of destination warehouse. However, the transfer operator cannot obtain real-time information about the target warehouse's status or the change of destination warehouse. This leads to inefficient allocation of warehouse resources and reduced cargo transfer efficiency. Summary of the Invention

[0005] The embodiments of the present invention provide a transshipment logistics scheduling method, device, equipment and medium, which can timely obtain the storage status of the target warehouse and perform transshipment logistics scheduling, thereby improving the accuracy of logistics scheduling to avoid the situation where large quantities of items cannot be transferred into the warehouse in time.

[0006] In a first aspect, an embodiment of the present invention provides a transshipment logistics scheduling method, the method comprising:

[0007] During the process of transferring the target item to the original target warehouse, obtaining preset warehousing and transportation real-time data associated with the transfer status of the target item based on a preset frequency;

[0008] Inputting the preset real-time storage and transportation data into a pre-trained transit warehouse allocation model, and determining the real-time allocation target warehouse of the target item based on the model output result;

[0009] In the case that the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is performed to achieve logistics scheduling of the target items during the transfer process.

[0010] In a second aspect, an embodiment of the present invention provides a transshipment logistics scheduling device, the device comprising:

[0011] A transfer dynamic data acquisition module is used to acquire preset warehousing and transportation real-time data associated with the transfer status of the target item based on a preset frequency during the process of transferring the target item to the original target warehouse;

[0012] A target warehouse real-time analysis module is used to input the preset warehousing and transportation real-time data into a pre-trained transit warehouse allocation model, and determine the real-time allocation target warehouse of the target item based on the model output result;

[0013] The target warehouse switching warning module is used to issue a transfer warehouse switching warning when the real-time assigned target warehouse is different from the original target warehouse, so as to realize the logistics scheduling of the target items during the transfer process.

[0014] In a third aspect, an embodiment of the present invention further provides a computer device, comprising:

[0015] one or more processors;

[0016] a memory for storing one or more programs;

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the transshipment logistics scheduling method provided by any embodiment of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the transshipment logistics scheduling method provided by any embodiment of the present invention.

[0019] The embodiments of the above invention have the following advantages or beneficial effects:

[0020] The embodiment of the present invention obtains preset storage and transportation real-time data related to the transfer status of the target item based on a preset frequency during the process of transferring the target item to the original target warehouse, that is, dynamically detects data that affects the selection and switching of the item transfer warehouse and further performs data analysis, inputs the preset storage and transportation real-time data into a pre-trained transfer warehouse allocation model, and determines the real-time allocation target warehouse of the target item based on the model output result; in the case where the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is performed to realize the logistics scheduling of the target item during the transfer process. The technical solution of the embodiment of the present invention solves the problem of not being able to respond to abnormal situations of the target warehouse in a timely manner during the transfer of items. It can obtain the storage status of the target warehouse in a timely manner and perform transfer logistics scheduling, improve the accuracy of logistics scheduling, and avoid the situation where large quantities of items cannot be transferred into the warehouse in time, which is conducive to alleviating the situation of warehouse queues due to warehouse overflow and realizing the rational use of warehouse resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of a transshipment logistics scheduling method provided by an embodiment of the present invention;

[0022] Figure 2 This is a flow chart of a transshipment logistics scheduling method provided by an embodiment of the present invention;

[0023] Figure 3 This is a flow chart of a transshipment logistics scheduling method provided by an embodiment of the present invention;

[0024] Figure 4 1 is a schematic diagram of a network structure of an online extreme learning machine provided by an embodiment of the present invention;

[0025] Figure 5 This is a structural diagram of a transshipment logistics scheduling device provided by an embodiment of the present invention;

[0026] Figure 6 It is a structural diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0028] Figure 1 This is a flowchart of a transshipment logistics scheduling method provided in an embodiment of the present invention. This embodiment is applicable to transshipment logistics scheduling scenarios, particularly when an abnormal situation during the transshipment of items requires switching the target warehouse. This method can be executed by a transshipment logistics scheduling device, which can be implemented using software and / or hardware and integrated into a computer device with application development capabilities.

[0029] like Figure 1 As shown, the transshipment logistics scheduling method of this embodiment includes the following steps:

[0030] S110 . During the process of transferring the target item to the original target warehouse, obtain preset warehousing and transportation real-time data associated with the transfer status of the target item based on a preset frequency.

[0031] The target item can be any item selected by the user on the item selection platform, meaning it needs to be transshipped. This means the target item can be transported from a factory or transshipment center to a target warehouse for storage management. The original target warehouse is the warehouse determined to store the target item after the target item is identified. This can be the target warehouse initially assigned to the user's selected target item by the item selection platform, or a target warehouse selected by the user based on a list of selectable warehouses.

[0032] Once the target item and its corresponding original destination warehouse have been identified, a transfer task is generated. The executor of the transfer task, known as the forwarder, will transfer the target item to the original destination warehouse based on its address. Typically, during the transportation process, the forwarder is unaware of the original destination warehouse's business conditions, nor does it know whether the upstream entity that issued the transfer task has changed its destination warehouse. It's possible that by the time the target item is transferred to the original destination warehouse, it will be discovered that the warehouse is full and many other items are waiting to be stored. This can prevent the target item from being stored in time, impacting the carrier's transfer task execution efficiency and causing losses for the user who selected the target item.

[0033] To alleviate or avoid the aforementioned issues, this embodiment dynamically monitors the operational status of each warehouse to promptly predict and proactively respond to events such as warehouse overflows. During the dynamic monitoring of the operational status of each warehouse, preset real-time warehousing and transportation data associated with the transfer status of target items can be acquired at a preset frequency (e.g., every ten minutes or half an hour).

[0034] Real-time, pre-set warehousing and transportation data related to the target item's transshipment status can include parameters that influence decisions about switching target warehouses during the transshipment process. These parameters can be used to promptly determine whether the target warehouse to which the target item is being transshipped needs to be changed. For example, this data can include the target item's inventory level in warehouses within a specific region (e.g., nationwide), the queue status of warehouses capable of storing the target item, the number of transshipment vehicles in transit to each warehouse, and the geographic area within which transshipment vehicles can deliver.

[0035] S120: Input the preset real-time storage and transportation data into a pre-trained transfer warehouse allocation model, and determine the real-time allocation target warehouse of the target item according to the model output result.

[0036] Among them, the transshipment warehouse allocation model can be a pre-trained warehouse allocation prediction model, which can analyze various data in the preset warehousing and transportation real-time data, output a model prediction value, and then determine a warehouse allocation result based on the threshold range of the model prediction value.

[0037] The mapping relationship between the model prediction value and different warehouses can be determined based on a large amount of model training sample data. The model training sample data can be data collected during the actual practice of item transshipment tasks, and the data includes data corresponding to all possible abnormal storage operations of the warehouse.

[0038] After inputting the preset real-time warehousing and transportation data into the pre-trained transshipment warehouse allocation model, a model prediction value obtained by the model based on the current real-time data analysis can be obtained, and then the current real-time allocation target warehouse can be determined based on the current model prediction value.

[0039] S130: When the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is issued to achieve logistics scheduling of the target items during the transfer process.

[0040] If, during the transfer process of the target item, the model analysis shows that the real-time distribution target warehouse of the target item is the same as the original target warehouse, it means that the current item transfer is normal and the transfer task can be continued according to the original transfer route.

[0041] If, during the transfer of a target item, the model analyzes that the target item's real-time assigned destination warehouse is different from the original destination warehouse, this indicates that the original destination warehouse may be experiencing an anomaly and is no longer the best choice for storing the target item. There is a possibility of a warehouse overflow or excessively long warehousing queues. In this case, a warehouse switching alert is issued to promptly inform the user of the actual business status of the original destination warehouse and to decide whether to switch it to the assigned destination warehouse, thereby achieving logistics scheduling for the target item during transfer.

[0042] Furthermore, the system can estimate the arrival time of target items at different warehouses based on real-time storage data, in-transit vehicle data, and other information from each warehouse, providing users with more intuitive data as a reference for making logistics scheduling decisions during the item transfer process. This eliminates the need to wait until the transferee has delivered the target item to the original destination warehouse before discovering the need to change the transfer route.

[0043] Furthermore, in addition to performing target warehouse analysis through the transfer warehouse allocation model, in this embodiment, the real-time storage safety analysis value of the original target warehouse is determined based on the preset warehousing and transportation real-time data, that is, each data in the preset warehousing and transportation real-time data is evaluated; then, when the real-time storage safety analysis value is greater than the preset storage safety threshold, the target transfer warehouse of the target item is switched from the original target warehouse to the real-time allocation target warehouse.

[0044] For example, a preset storage safety threshold can be set for each item in the preset real-time warehousing and transportation data. When the real-time value of any data item exceeds the corresponding preset storage safety threshold, the item selection platform can directly make a decision to switch the target warehouse. Alternatively, a comprehensive analysis of multiple items in the preset real-time warehousing and transportation data can be performed. When the combined analysis result of multiple items exceeds the corresponding preset storage safety threshold, the item selection platform can also directly make a decision to switch the target warehouse.

[0045] Furthermore, during the target item transfer process, any decision results regarding transfer logistics scheduling will be synchronized to the target transfer task carrier and the warehouse management party. This allows the carrier to adjust the route in a timely manner and transport the target item to the new target warehouse for smooth warehousing. This can improve the transfer efficiency of the transfer party, avoid economic losses caused by users who choose the target item due to the item not being able to enter the warehouse in time, and alleviate abnormal conditions in the original target warehouse. The technical solution of this embodiment, in the process of transferring the target item to the original target warehouse, obtains the preset warehousing and transportation real-time data related to the transfer situation of the target item based on a preset frequency, that is, dynamically detects the data that affects the selection and switching of the item transfer warehouse and further performs data analysis, inputs the preset warehousing and transportation real-time data into the pre-trained transfer warehouse allocation model, and determines the real-time allocation target warehouse of the target item based on the output result of the model; when the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is issued to achieve logistics scheduling of the target item during the transfer process. The technical solution of the embodiment of the present invention solves the problem of not being able to respond to abnormal situations in the target warehouse in a timely manner during the transfer of items. It can obtain the storage status of the target warehouse in a timely manner and perform transfer logistics scheduling, thereby improving the accuracy of logistics scheduling to avoid the situation where large quantities of items cannot be transferred into the warehouse in a timely manner. It is conducive to alleviating the queues in warehouses that are overwhelmed and realizing the rational use of warehouse resources.

[0046] Figure 2 This is a flowchart of a transshipment logistics scheduling method provided in an embodiment of the present invention. This embodiment shares the same inventive concept as the transshipment logistics scheduling method described above, further describing the initial process of determining the original destination warehouse for transshipped items and switching warehouses. This method can be executed by a transshipment logistics scheduling device, which can be implemented using software and / or hardware and integrated into a computer device with application development capabilities.

[0047] like Figure 2 As shown, the transshipment logistics scheduling method of this embodiment includes the following steps:

[0048] S210: When a transfer demand of a target item is obtained, determine the original preset warehousing and transportation real-time data corresponding to the moment when the transfer demand is obtained.

[0049] On any item selection platform, users can select the target item they need. Once the user confirms the target item, the item selection platform will generate a corresponding target item transfer task, thereby obtaining the transfer demand of the target item.

[0050] The original preset warehousing and transportation real-time data corresponding to the moment of transshipment demand is obtained, which can be understood as obtaining the preset warehousing and transportation real-time data at that moment when the target warehouse is selected for the target item.

[0051] Preset real-time warehousing and transportation data can include parameters that influence target warehouse selection during the transshipment process. For example, this data can include the target product inventory level at various warehouses within a specific region (e.g., nationwide), the queue status of warehouses capable of storing the target product, the number of transshipment vehicles in transit to various warehouses, and the delivery areas accessible to transshipment vehicles. These parameters can be comprehensively analyzed to determine the target warehouse that is most suitable for the target product.

[0052] S220: Input the original preset warehousing and transportation real-time data into a preset transshipment warehouse allocation model, and determine a candidate target warehouse based on the model output result.

[0053] The transshipment warehouse allocation model can be a pre-trained warehouse allocation prediction model, which can analyze various data in the preset warehousing and transportation real-time data, output a model prediction value, and then determine a warehouse allocation result based on the threshold range of the model prediction value.

[0054] Specifically, by inputting the original preset warehousing and transportation real-time data obtained in the above steps into the preset transshipment warehouse allocation model, the corresponding model prediction value can be obtained, and then the candidate target warehouse can be further determined based on the model prediction value.

[0055] It's understandable that the candidate target warehouse determined by the model's predictions isn't the only candidate, but it can be considered the one with the highest recommendation index. Furthermore, some candidate warehouses can be excluded based on the original preset warehousing and transportation real-time data. For example, warehouses with severe queues or a high number of vehicles in transit may be excluded from consideration.

[0056] This step is equivalent to screening all warehouses, removing unselectable warehouses, identifying candidate warehouses that can be selected by the user, and determining warehouses with high recommendation indexes. All candidate warehouses can be displayed in a list with warehouse data. The order of each warehouse in the list can be determined by parameters such as distance, recommendation index, or queue length.

[0057] S230. Determine the original target warehouse from the candidate target warehouses according to the user's warehouse selection instruction.

[0058] Once the user selects the original destination warehouse, the item selection platform will generate a transfer task. The executor of the transfer task, also known as the transfer party, will transfer the target item to the original destination warehouse based on the address of the original destination warehouse.

[0059] S240. During the process of transferring the target item to the original target warehouse, obtain preset warehousing and transportation real-time data associated with the transfer status of the target item based on a preset frequency.

[0060] S250: Input the preset real-time storage and transportation data into a pre-trained transfer warehouse allocation model, and determine the real-time allocation target warehouse of the target item based on the model output result.

[0061] S260: When the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is issued to achieve logistics scheduling of the target items during the transfer process.

[0062] In an optional embodiment, whether in the process of determining the original target warehouse or in the transshipment process, when using the preset transshipment warehouse allocation model for warehouse prediction, the current model output result can be adjusted according to the difference between the previous output results of the transshipment warehouse allocation model and the model threshold of the corresponding actual target warehouse; and then, the real-time distribution target warehouse of the target item is determined according to the adjusted current model output result, which can improve the accuracy of the output prediction value of the preset transshipment warehouse allocation model.

[0063] For example, you can refer to the calculation process corresponding to this formula: Among them, Y(i) represents the predicted value output by the preset transfer warehouse allocation model at the i-th sampling moment, A(i) represents the actual delivery result threshold, that is, the predicted value threshold corresponding to the actual target warehouse of the target item when the preset transfer warehouse allocation model is used to predict the warehouse, and α is the self-learning coefficient, which ranges from 0 to 1.

[0064] The technical solution of this embodiment is to determine the original preset warehousing and transportation real-time data corresponding to the moment when the transfer demand of the target item is obtained; input the original preset warehousing and transportation real-time data into the preset transfer warehouse allocation model, and determine the candidate target warehouse based on the model output result; determine the original target warehouse among the candidate target warehouses according to the user's warehouse selection instruction, and then obtain the preset warehousing and transportation real-time data associated with the transfer situation of the target item based on the preset frequency in the process of transferring the target item to the original target warehouse, that is, dynamically detect the data affecting the selection and switching of the item transfer warehouse and further perform data analysis, input the preset warehousing and transportation real-time data into the pre-trained transfer warehouse allocation model, and determine the real-time allocation target warehouse of the target item according to the model output result; when the real-time allocation target warehouse is different from the original target warehouse, perform a transfer warehouse switching prompt and warning to realize the logistics scheduling of the target item during the transfer process. The technical solution of the embodiment of the present invention solves the problem of being unable to respond to abnormal situations in the target warehouse in a timely manner during the item transfer process. It can obtain the storage status of the target warehouse in a timely manner and perform transfer logistics scheduling, thereby improving the accuracy of logistics scheduling, thereby avoiding the situation where large quantities of items cannot be transferred into the warehouse in a timely manner, which is conducive to alleviating the situation of warehouse queues due to warehouse overflow and achieving the rational use of warehouse resources. Moreover, in this embodiment, automatic allocation of delivery warehouses is achieved based on the transfer warehouse allocation model, and the appropriate destination warehouse is calculated based on real-time predictions. The user is recommended a suitable destination warehouse for placing orders, and orders are restricted to warehouses that are not within the safety threshold to reduce the situation of temporary switching of destination warehouses and minimize the occurrence of warehouse switching events midway.

[0065] Figure 3 This is a flowchart of a transshipment logistics scheduling method provided in an embodiment of the present invention. This embodiment shares the same inventive concept as the transshipment logistics scheduling method described in the previous embodiment and further illustrates the training process for the transshipment warehouse allocation model. This method can be executed by a transshipment logistics scheduling device, which can be implemented using software and / or hardware and integrated into a computer device with application development capabilities.

[0066] like Figure 3 As shown, the transshipment logistics scheduling method of this embodiment includes the following steps:

[0067] S310: Obtain preset warehousing and transportation data samples and build an initial online extreme learning machine.

[0068] Among them, the initial online extreme learning machine can be as follows Figure 4The network structure shown in the figure can introduce the idea of ​​sequential learning into the extreme learning machine algorithm, that is, at the beginning of model training, the output weight β0 of the single hidden layer feedforward neural network can be initialized by a small number of samples. During the online sequential learning process, the output weight β of the single hidden layer feedforward neural network learned in the initial stage is iteratively adjusted through each input sample.

[0069] In this embodiment, a linear extreme learning machine model is used as the target transfer warehouse allocation model.

[0070] The preset warehousing and transportation data samples include the inventory of a certain commodity in warehouses across the country, the queue situation of warehouses across the country that can store a certain commodity, the transfer vehicles in transit to a certain warehouse, the delivery area of ​​the transfer vehicles, the delivery range, and other factors that affect warehouse selection. i Represents time.

[0071] S320: Performing model training on the initial online extreme learning machine based on the preset warehousing and transportation data samples, and parsing the preset training objective function of the initial online extreme learning machine based on the sparrow search algorithm to train and obtain a target transshipment warehouse allocation model.

[0072] In the initial training phase, there are N0 arbitrary training samples (X i ,t i ), where X i =[x i1 ,x i2 ,…,x in ] T ∈R n Among them, X i Represents t i The network structure of the online extreme learning machine can be expressed as the following formula:

[0073] Among them, w i =[w i1 ,w i2 ,…,w in ] T is the input weight connecting the i-th hidden node and the input, b i is the bias of the hidden node, both are generated randomly. i =[β i1 ,β i2 ,…,β im ] T is the input weight connecting the i-th hidden node and the output node.

[0074] When β=[β1,β2,…,β n ] Tis the target matrix of the training data, i = 1, 2, ..., n, and the output matrix of the hidden layer is as follows:

[0075]

[0076] The matrix relationship is H0β=T0, where In order to make the learning goal of the single hidden layer feedforward neural network to minimize the output error value, the objective function is min||H0β-T0||

[0077] After calculating the hidden layer output, it is necessary to calculate the output layer weight β. According to the generalized inverse method, the minimum β0=H that meets the conditions is obtained. + T0.H + is the generalized inverse matrix of H0. + =(H0 T H0) -1 H0 T , let the intermediate matrix H + =(H0 T H0) -1 H0 T In the online learning phase, calculate the hidden layer output H after the K+1th learning k+1 , then P k+1 and the output weight β k+1 as follows:

[0078]

[0079] Considering that the model convergence speed of the online extreme learning machine is slow during the training process, the improved sparrow search algorithm can be used to optimize the online extreme learning machine model to speed up the model convergence speed and ensure the stability of the prediction results.

[0080] Furthermore, the sparrow population in the sparrow search algorithm is represented as follows:

[0081] Where n is the number of sparrows in the population and d represents the dimension of the optimization variable.

[0082] The fitness value of the sparrow is:

[0083] Where f represents the fitness value. During each iteration, the position updates of the discoverer and joiner are described as follows:

[0084]

[0085] Among them, t is the current iteration number, itermax is the maximum iteration number, X i,jIt represents the position of the i-th sparrow in the j-th dimension. α ∈ (0, 1], L is a 1×d identity matrix. Q is a random number from a normal distribution. R2 and ST represent the warning value and the safety value respectively. R2 ∈ [0, 1], ST ∈ [0.5, 1]. When R2 < ST, it means the foraging environment is safe and there are no predators; when R2 ≥ ST, it means the population has detected a predator and will fly to a safe area to forage. If the joiner fails to successfully snatch the discoverer's food, then the position of the joiner is updated.

[0086] Among them, the improvement of the sparrow search algorithm is due to the fact that during the operation of the sparrow search algorithm, the performance data matrix of the sparrow population may be irreversible, making it impossible to continue the operation smoothly and affecting the iterative process of model training. In this implementation, if during the operation of the sparrow search algorithm, the performance data matrix of the sparrow population is irreversible, then a set of random data is generated to replace the repeated row data or column data in the performance data matrix of the sparrow population until the performance data matrix of the sparrow population can continue to perform inverse operations. The improved sparrow search algorithm uses the prediction deviation as the objective function, that is, a decision-making module is added to the sparrow search algorithm to improve the optimization algorithm. When the matrix is irreversible, a new set of data is randomly generated to replace the original matrix until the matrix is reversible, and then the weights and biases of the line extreme learning machine are optimized.

[0087] Finally, the target transfer warehouse allocation model is trained and can be used in the item selection platform to generate transfer tasks and dynamically analyze the operation of each transfer warehouse, which helps to analyze and determine the target transfer warehouse in real time.

[0088] S330. In the case of obtaining the transfer requirement of the target item, determine the original preset warehousing and transportation real-time data corresponding to the moment when the transfer requirement is obtained.

[0089] S340. Input the original preset warehousing and transportation real-time data into the target transfer warehouse allocation model, and determine the candidate target warehouses based on the model output results.

[0090] S350. According to the user's warehouse selection instruction, determine the original target warehouse among the candidate target warehouses.

[0091] S360. During the process of transferring the target item to the original target warehouse, obtain the preset warehousing and transportation real-time data associated with the transfer situation of the target item based on a preset frequency.

[0092] S370. Input the preset warehousing and transportation real-time data into the target transfer warehouse allocation model, and determine the real-time allocation target warehouse of the target item according to the model output results.

[0093] S380: When the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is issued to achieve logistics scheduling of the target items during the transfer process.

[0094] S390. Synchronize the logistics scheduling information of the target item during the transfer process to the target transfer task carrier.

[0095] The technical solution of this embodiment is to obtain preset warehousing and transportation data samples and construct an initial online extreme learning machine; perform model training on the initial online extreme learning machine based on the preset warehousing and transportation data samples, and analyze the preset training objective function of the initial online extreme learning machine based on the sparrow search algorithm to train a target transfer warehouse allocation model; when the transfer demand of the target item is obtained, determine the original preset warehousing and transportation real-time data corresponding to the moment when the transfer demand is obtained; input the original preset warehousing and transportation real-time data into the target transfer warehouse allocation model, and determine the candidate target warehouse based on the model output result; according to the user's warehouse selection Instructions, determine the original target warehouse among the candidate target warehouses; in the process of transferring the target item to the original target warehouse, obtain the preset warehousing and transportation real-time data associated with the transfer status of the target item based on a preset frequency; input the preset warehousing and transportation real-time data into the target transfer warehouse allocation model, and determine the real-time allocation target warehouse of the target item according to the model output result; if the real-time allocation target warehouse is different from the original target warehouse, perform a transfer warehouse switching prompt and warning to realize the logistics scheduling of the target item during the transfer process; synchronize the logistics scheduling information of the target item during the transfer process to the target transfer task carrier. The technical solution of the embodiment of the present invention solves the problem of not being able to respond to abnormal situations in the target warehouse in a timely manner during the transshipment of items. It adopts an algorithm that can accelerate the convergence of the model and trains a target transshipment warehouse allocation model. It can calculate the appropriate destination warehouse in real time based on the model, recommend the appropriate destination warehouse to the user for placing orders, and restrict orders to warehouses that are not within the safety threshold to reduce the situation of temporary switching of destination warehouses and avoid cutting warehouses midway; it can also obtain the storage status of the target warehouse in a timely manner and perform transshipment logistics scheduling, improve the accuracy of logistics scheduling, and avoid the situation where large quantities of items cannot be transshipped into the warehouse in time, which is conducive to alleviating the queues in warehouses that are overwhelmed and realizing the rational use of warehouse resources.

[0096] Figure 5A structural schematic diagram of a transshipment logistics scheduling device provided in an embodiment of the present invention. This embodiment can be applied to transshipment logistics scheduling scenarios, especially when target warehouse switching is required during the transshipment of goods. The transshipment logistics scheduling device can be implemented by software and / or hardware and integrated into a computer terminal device with application development capabilities.

[0097] like Figure 5 As shown, the transshipment logistics scheduling device includes: a transshipment dynamic data acquisition module 410, a target warehouse real-time analysis module 420 and a target warehouse switching early warning module 430.

[0098] Among them, the transfer dynamic data acquisition module 410 is used to obtain the preset warehousing and transportation real-time data associated with the transfer status of the target item based on a preset frequency during the process of transferring the target item to the original target warehouse; the target warehouse real-time analysis module 420 is used to input the preset warehousing and transportation real-time data into a pre-trained transfer warehouse allocation model, and determine the real-time allocation target warehouse of the target item based on the model output result; the target warehouse switching warning module 430 is used to issue a transfer warehouse switching prompt warning when the real-time allocation target warehouse is different from the original target warehouse, so as to realize the logistics scheduling of the target item during the transfer process.

[0099] The technical solution of this embodiment is to obtain preset storage and transportation real-time data related to the transfer status of the target items based on a preset frequency during the process of transferring the target items to the original target warehouse, that is, dynamically detect the data that affects the selection and switching of the transfer warehouse for the items and further perform data analysis, input the preset storage and transportation real-time data into a pre-trained transfer warehouse allocation model, and determine the real-time allocation target warehouse for the target items based on the output results of the model; when the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is performed to achieve logistics scheduling of the target items during the transfer process. The technical solution of the embodiment of the present invention solves the problem of not being able to respond to abnormal situations of the target warehouse in a timely manner during the transfer of items. It can obtain the storage status of the target warehouse in a timely manner and perform transfer logistics scheduling, thereby improving the accuracy of logistics scheduling to avoid the situation where large quantities of items cannot be transferred into the warehouse in time, which is conducive to alleviating the queue situation of warehouse overflow and achieving rational use of warehouse resources.

[0100] In an optional embodiment, the target warehouse switching warning module 430 may also be used to:

[0101] Determining a real-time storage safety analysis value of the original target warehouse based on the preset real-time storage and transportation data;

[0102] When the real-time warehouse safety analysis value is greater than a preset warehouse safety threshold, the target transfer warehouse of the target item is switched from the original target warehouse to the real-time allocation target warehouse.

[0103] In an optional embodiment, the transshipment logistics scheduling device further includes an original target warehouse determination module, specifically configured to:

[0104] When the transshipment demand of the target item is obtained, determining the original preset warehousing and transportation real-time data corresponding to the moment when the transshipment demand is obtained;

[0105] Inputting the original preset warehousing and transportation real-time data into the transshipment warehouse allocation model, and determining candidate target warehouses based on the model output results;

[0106] According to the user's warehouse selection instruction, the original target warehouse is determined from the candidate target warehouses.

[0107] In an optional embodiment, the target warehouse switching warning module 430 may also be used to:

[0108] The logistics scheduling information of the target item during the transfer process is synchronized to the target transfer task carrier.

[0109] In an optional embodiment, the transshipment logistics scheduling device further includes a model training module for training the transshipment warehouse allocation model. The training process includes:

[0110] During the training of the transfer warehouse allocation model, a preset training objective function of the transfer warehouse allocation model is parsed based on a sparrow search algorithm;

[0111] Among them, the transfer warehouse allocation model is an online extreme learning machine.

[0112] In an optional embodiment, the model training module may also be used to:

[0113] During the operation of the sparrow search algorithm, if the sparrow population performance data matrix becomes irreversible, a set of random data is generated to replace the repeated row data or column data in the sparrow population performance data matrix until the sparrow population performance data matrix can continue to be inverted.

[0114] In an optional embodiment, the target warehouse real-time analysis module 420 may also be used to:

[0115] Adjust the current model output result according to the difference between the previous output results of the transfer warehouse allocation model and the model threshold of the corresponding actual target warehouse;

[0116] The real-time distribution target warehouse of the target item is determined according to the adjusted output result of the current sub-model.

[0117] The transfer logistics scheduling device provided in the embodiment of the present invention can execute the transfer logistics scheduling method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0118] Figure 6 A schematic structural diagram of a computer device provided in an embodiment of the present invention. Figure 6 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 6 The computer device 12 shown is only an example and should not limit the functionality and scope of use of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities, such as an intelligent controller, a server, a mobile phone, or other terminal devices.

[0119] like Figure 6 As shown, computer device 12 is implemented as a general-purpose computing device. Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 that connects various system components (including system memory 28 and processing unit 16).

[0120] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0121] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0122] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 6 Not shown, often called a "hard drive"). Although Figure 6Not shown, a magnetic disk drive for reading and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0123] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0124] The computer device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, a pointing device, a display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0125] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the transshipment logistics scheduling method provided in the embodiment of the present invention, which includes:

[0126] During the process of transferring the target item to the original target warehouse, obtaining preset warehousing and transportation real-time data associated with the transfer status of the target item based on a preset frequency;

[0127] Inputting the preset real-time storage and transportation data into a pre-trained transit warehouse allocation model, and determining the real-time allocation target warehouse of the target item based on the model output result;

[0128] In the case that the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is performed to achieve logistics scheduling of the target items during the transfer process.

[0129] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for transshipment logistics scheduling provided in any embodiment of the present invention is implemented. The method includes:

[0130] During the process of transferring the target item to the original target warehouse, obtaining preset warehousing and transportation real-time data associated with the transfer status of the target item based on a preset frequency;

[0131] Inputting the preset real-time storage and transportation data into a pre-trained transit warehouse allocation model, and determining the real-time allocation target warehouse of the target item based on the model output result;

[0132] In the case that the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is performed to achieve logistics scheduling of the target items during the transfer process.

[0133] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: 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 this document, a computer-readable storage medium can 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.

[0134] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0135] Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0136] The computer program code for performing the operations of the present invention can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0137] Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computing device. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computer device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

[0138] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A transshipment logistics scheduling method, characterized in that: include: During the process of transferring the target item to the original target warehouse, obtaining preset warehousing and transportation real-time data associated with the transfer status of the target item based on a preset frequency; Inputting the preset real-time storage and transportation data into a pre-trained transit warehouse allocation model, and determining the real-time allocation target warehouse of the target item based on the model output result; In the case that the real-time allocation target warehouse is different from the original target warehouse, a transfer warehouse switching prompt warning is performed to achieve logistics scheduling of the target items during the transfer process.

2. The method according to claim 1, characterized in that Also includes: Determining a real-time storage safety analysis value of the original target warehouse based on the preset real-time storage and transportation data; When the real-time warehouse safety analysis value is greater than a preset warehouse safety threshold, the target transfer warehouse of the target item is switched from the original target warehouse to the real-time allocation target warehouse.

3. The method according to claim 1, characterized in that The process of determining the original target warehouse includes: When the transshipment demand of the target item is obtained, determining the original preset warehousing and transportation real-time data corresponding to the moment when the transshipment demand is obtained; Inputting the original preset warehousing and transportation real-time data into the transshipment warehouse allocation model, and determining candidate target warehouses based on the model output results; According to the user's warehouse selection instruction, the original target warehouse is determined from the candidate target warehouses.

4. The method according to claim 1, wherein The method further comprises: The logistics scheduling information of the target item during the transfer process is synchronized to the target transfer task carrier.

5. The method according to any one of claims 1 to 4, characterized in that: The transshipment warehouse allocation model is a pre-trained online extreme learning machine; During the training of the transfer warehouse allocation model, a preset training objective function of the transfer warehouse allocation model is analyzed based on a sparrow search algorithm.

6. The method according to claim 5, characterized in that The process of analyzing the preset training objective function of the transshipment warehouse allocation model based on the sparrow search algorithm includes: During the operation of the sparrow search algorithm, if the sparrow population performance data matrix becomes irreversible, a set of random data is generated to replace the repeated row data or column data in the sparrow population performance data matrix until the sparrow population performance data matrix can continue to be inverted.

7. The method according to any one of claims 1 to 4, characterized in that: The step of determining the target warehouse for real-time allocation of the target item according to the model output result includes: Adjust the current model output result according to the difference between the previous output results of the transfer warehouse allocation model and the model threshold of the corresponding actual target warehouse; The real-time distribution target warehouse of the target item is determined according to the adjusted output result of the current sub-model.

8. A transshipment logistics dispatching device, characterized in that: include: A transshipment dynamic data acquisition module is used to acquire preset warehousing and transportation real-time data associated with the transshipment status of the target item based on a preset frequency during the process of transshipping the target item to the original target warehouse; A target warehouse real-time analysis module is used to input the preset warehousing and transportation real-time data into a pre-trained transit warehouse allocation model, and determine the real-time allocation target warehouse of the target item based on the model output result; The target warehouse switching warning module is used to issue a transfer warehouse switching warning when the real-time assigned target warehouse is different from the original target warehouse, so as to realize the logistics scheduling of the target items during the transfer process.

9. A computer device, characterized in that: The computer device comprises: one or more processors; a memory 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 transit logistics scheduling method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the transshipment logistics scheduling method as described in any one of claims 1 to 7 is implemented.

Images