Library shifting processing method and device

Abstract

The invention discloses a library transfer processing method and device, and relates to the technical field of intelligent supply chains and artificial intelligence. A specific embodiment of the method comprises the following steps: training a pre-established transfer classification model according to historical transfer real data, and inputting storage location data and article data of to-be-discriminated objects into the trained transfer classification model to obtain to-be-transferred objects in the to-be-discriminated objects; wherein each object comprises a storage position and an article currently stored in the storage position; determining a storage location type of a transfer target of an object type to which any one to-be-transferred object belongs from the historical transfer real data, and determining the storage location type of the transfer target meeting a preset storage location type screening condition as a target storage location type of the to-be-transferred object, and selecting a storage location of the to-be-moved object from the current storage locations included in the target storage location type. According to the embodiment, the rationality of library moving operation can be improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent supply chain and artificial intelligence technology, and in particular to a warehouse transfer processing method and device. Background Art

[0002] In modern logistics, it is necessary to change the storage location of items that have been put on the shelves in the warehouse in order to optimize the utilization status of the warehouse storage location. This operation is called warehouse transfer. Exemplarily, there are several situations for warehouse transfer: First, the quantity of a certain item is small but it occupies a larger storage location. It can be moved to other small storage locations to free up the large storage location, thereby improving the utilization rate of the storage location. Second, move items with large consumption (such as sales volume) to a storage location that is convenient for outbound delivery to improve the efficiency of outbound delivery. Third, move items with insulation requirements to storage locations with insulation conditions. Fourth, move defective products, expired products, etc. to designated isolation storage locations. At present, warehouse transfer operations are generally decided manually and rely heavily on manual experience. The rationality of warehouse transfer is insufficient and it is impossible to further improve the utilization rate of storage locations. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a warehouse transfer processing method and device, which can realize automatic warehouse transfer decision-making based on a machine learning model, thereby improving the rationality of warehouse transfer operations.

[0004] To achieve the above objective, according to one aspect of the present invention, a warehouse transfer processing method is provided.

[0005] The warehouse transfer processing method of the embodiment of the present invention includes: training a pre-established warehouse transfer classification model based on historical real warehouse transfer data, inputting the storage location data and item data of the object to be identified into the trained warehouse transfer classification model, and obtaining the proposed warehouse transfer objects among the objects to be identified; wherein each object includes a storage location and the items currently stored in the storage location; determining the transfer destination storage location type of the object type to which any proposed warehouse transfer object belongs from the historical real warehouse transfer data, determining the transfer destination storage location type that meets the preset storage location type screening conditions as the target storage location type of the proposed warehouse transfer object, and selecting the transfer destination storage location of the proposed warehouse transfer object from the current storage locations contained in the target storage location type.

[0006] Optionally, the step of inputting the storage location data and item data of the object to be identified into a trained warehouse transfer classification model to obtain the object to be identified among the objects to be identified, comprises: inputting the storage location data and item data of the object to be identified into the trained warehouse transfer classification model to obtain the calculation result output by the warehouse transfer classification model for the object to be identified; and determining the object to be identified whose calculation result indicates "needs to be transferred" as the object to be identified.

[0007] Optionally, after obtaining the objects to be moved, the objects to be moved are clustered according to their object data to obtain the object type to which each object to be moved belongs; wherein the object data of each object includes storage location data of the storage location in the object and item data of the item in the object.

[0008] Optionally, the method further includes: after obtaining the object to be transferred, clustering the storage locations and items in the object to be transferred respectively to obtain multiple storage location types and item types; the object type to which any object to be transferred belongs includes: the storage location type to which the storage location in the object to be transferred belongs and the item type to which the item in the object to be transferred belongs.

[0009] Optionally, the historical real data of warehouse transfer includes: storage location data of source storage locations of multiple objects that have been transferred, storage location data of destination storage locations, and item data of items to be transferred; and, determining the destination storage location type of any object type to which any object to be transferred belongs from the historical real data of warehouse transfer includes: determining a specific moved object that belongs to the object type of any object to be transferred from the historical real data of warehouse transfer; and determining the storage location type of the destination storage location of the specific moved object as the destination storage location type of the transfer.

[0010] Optionally, the historical real data of warehouse transfer includes: storage location data of source storage locations of multiple objects that have been transferred, storage location data of destination storage locations, and item data of items to be transferred; and, determining the destination storage location type of any object type to which any object to be transferred belongs from the historical real data of warehouse transfer includes: determining the storage location type in the object type to which any object to be transferred belongs as a first storage location type, and determining the item type in the object type to which any object to be transferred belongs as a first item type; determining the transferred objects corresponding to the storage locations belonging to the first storage location type in the historical real data of warehouse transfer as first-category objects, determining the transferred objects corresponding to the items belonging to the first item type in the historical real data of warehouse transfer as second-category objects, and determining the storage location type of the destination storage location of a specific transferred object that is both a first-category object and a second-category object as the destination storage location type of the transfer.

[0011] Optionally, the determination of the destination storage location type that satisfies the preset storage location type screening conditions as the target storage location type of the object to be transferred includes: determining the destination storage location type that corresponds to the most specific transferred objects as the target storage location type; or determining the destination storage location type that corresponds to the most recent specific transferred object as the target storage location type.

[0012] Optionally, the step of selecting the destination storage location for the object to be transferred from the current storage locations included in the target storage location type includes: selecting a storage location that satisfies the preset transfer rules for the object to be transferred from the current storage locations included in the target storage location type as the destination storage location for the object to be transferred.

[0013] To achieve the above objective, according to another aspect of the present invention, a warehouse transfer processing device is provided.

[0014] The warehouse transfer processing device of the embodiment of the present invention may include: a warehouse transfer classification unit, which is used to train a pre-established warehouse transfer classification model based on historical real warehouse transfer data, and input the storage location data and item data of the object to be identified into the trained warehouse transfer classification model to obtain the proposed warehouse transfer object among the objects to be identified; wherein each object includes a storage location and the items currently stored in the storage location; a warehouse transfer operation unit, which is used to determine the transfer destination storage location type of the object type to which any proposed warehouse transfer object belongs from the historical real warehouse transfer data, determine the transfer destination storage location type that meets the preset storage location type screening conditions as the target storage location type of the proposed warehouse transfer object, and select the transfer destination storage location of the proposed warehouse transfer object from the current storage locations contained in the target storage location type.

[0015] To achieve the above objective, according to another aspect of the present invention, an electronic device is provided.

[0016] An electronic device of the present invention includes: 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 warehouse transfer processing method provided by the present invention.

[0017] To achieve the above objective, according to yet another aspect of the present invention, a computer-readable storage medium is provided.

[0018] A computer-readable storage medium of the present invention stores a computer program, which, when executed by a processor, implements the warehouse transfer processing method provided by the present invention.

[0019] According to the technical solution of the present invention, the embodiments of the above invention have the following advantages or beneficial effects:

[0020] The real data of historical warehouse transfer is used in advance to train the warehouse transfer classification model based on the machine learning algorithm, and the trained warehouse transfer classification model is used to determine which of the current objects (objects are a general term for storage locations and their current stored items) in the warehouse need to be transferred, that is, to determine the objects to be transferred. Then, the object type of each object to be transferred is determined by the clustering model, and the real data of historical warehouse transfer is mined and analyzed to obtain the transfer destination storage location type of any object type to which the object to be transferred belongs. Finally, the transfer destination storage location type that meets the preset storage location type screening conditions is determined as the target storage location type of the object to be transferred, and the final transfer destination storage location of the object to be transferred is selected from the current storage locations contained in the target storage location type. Through the warehouse transfer discrimination based on the machine learning model, the clustering of objects to be transferred and the mining of the destination storage location flow, the present invention realizes the automated warehouse transfer decision-making based on big data analysis, avoids the defects of the existing technology that heavily relies on manual experience, improves the rationality of warehouse transfer, and helps to further improve the utilization rate of storage locations.

[0021] 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

[0022] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0023] Figure 1 It is a schematic diagram of the main steps of the warehouse transfer processing method in an embodiment of the present invention;

[0024] Figure 2 It is a schematic diagram of specific execution steps of the warehouse transfer processing method in an embodiment of the present invention;

[0025] Figure 3 It is a schematic diagram of components of a warehouse transfer processing device in an embodiment of the present invention;

[0026] Figure 4 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;

[0027] Figure 5 It is a schematic diagram of the structure of an electronic device used to implement the warehouse transfer processing method in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] 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.

[0029] It should be pointed out that the embodiments of the present invention and the technical features therein may be combined with each other without conflict.

[0030] Figure 1 It is a schematic diagram of the main steps of the warehouse transfer processing method according to an embodiment of the present invention.

[0031] like Figure 1 As shown, the warehouse transfer processing method of the embodiment of the present invention can be executed by a server that executes warehouse management, and the specific steps are as follows:

[0032] Step S101: training a pre-established warehouse transfer classification model based on historical warehouse transfer real data, inputting the storage location data and item data of the object to be identified into the trained warehouse transfer classification model, and obtaining the proposed warehouse transfer object among the objects to be identified.

[0033] In this article, an object is a general term for a storage location and its stored items. The object that determines whether to perform the warehouse transfer is the object. Before executing this step, the server first determines the scope of the warehouse transfer operation. For example, the warehouse transfer operation can be performed for the entire warehouse, for one or more storage areas, or for the storage area and storage location of a certain owner (the owner refers to the owner of the item). It can be understood that the warehouse is composed of multiple storage areas, each storage area includes multiple storage locations, and the storage location can be used as the smallest unit for storing items.

[0034] On the other hand, the server can obtain historical data related to warehouse transfer from the database, that is, historical warehouse transfer real data. The historical warehouse transfer real data can be flexibly selected according to the actual scenario and the current data situation. Generally, the historical warehouse transfer real data may include: the storage location data of the source storage location of multiple warehouse transfer objects within a preset historical period (for example, within the past year), the storage location data of the destination storage location of the transfer, and the item data of the transferred items. These data can be either the original collected data or the statistical values ​​such as the average value, the first quantile value, the median, and the maximum value obtained by statistics of the original collected data. The above-mentioned objects that have been transferred refer to objects that have performed warehouse transfer operations. If the same storage location has performed multiple warehouse transfer operations, due to changes in the items, it can be considered that there are multiple objects that have been transferred with the same number. For example, if a storage location has performed two warehouse transfer operations, then the storage location corresponds to two objects that have been transferred, and each object that has been transferred has performed one warehouse transfer operation.

[0035] Exemplarily, the storage location data may include attribute characteristic data and operation characteristic data of the storage location. The attribute characteristic data may include one or more of: the length, width, height, load-bearing weight of the storage location, the storage area to which it belongs, whether multiple items are allowed to be mixed, the picking order (referring to the picking order between multiple storage locations storing the same items), etc. The operation characteristic data of the storage location may include one or more of the following: the usage volume of the storage location when transferring warehouses, the remaining volume of the storage location when transferring warehouses, the turnover rate (used to characterize the consumption rate of items in the storage location), the turnover cycle (used to characterize the average consumption cycle of items in the storage location), whether it is a heat-insulating storage location, the shelving operation data of the storage location in historical periods (shelving refers to entering the storage location for storage, and the shelving operation data may include the category of shelved items, the number of shelved items, the attributes of shelved items, etc.), the de-shelving operation data of the storage location in historical periods (de-shelving refers to leaving the storage location, and the de-shelving operation data may include the category of de-shelved items, the number of de-shelved items, the attributes of de-shelved items, etc.), the replenishment operation data of the storage location in historical periods (may include the category of replenishment items, the number of replenishment items, the attributes of replenishment items, etc.).

[0036] Item data may include one or more of the following: item name, item category, item quantity, item stock keeping unit SKU, item grade, shelf life, insulation requirements, heat (used to indicate the degree of acceptance of the item), consumption, etc.

[0037] In practical applications, the above historical real data of warehouse transfer can be used as positive samples for subsequent model training. In order to ensure the balance between positive and negative samples, real data of warehouse transfer that has not been made in the historical period can be selected as negative samples. The real data of warehouse transfer that has not been made can include storage location data of multiple objects that have not been moved in the historical period of a preset length (for example, in the past year) and item data of items that have been moved. It can be understood that the above historical real data of warehouse transfer preferably selects relevant data of the same warehouse transfer operation scope. For example, when performing warehouse transfer judgment on a certain storage area, it is preferred to select the historical real data of warehouse transfer in the storage area to train the model. When the data is insufficient, the historical real data of warehouse transfer in other storage areas can also be selected to train the model.

[0038] Thereafter, the server can use the collected real data of historical warehouse transfer to train the warehouse transfer classification model, and the warehouse transfer classification model can be established based on various applicable machine learning algorithms. When training input, the storage location data of the source storage location of the transferred object, the storage location data of the destination storage location of the transfer, and the item data of the transferred items can be used as training data, or only the storage location data of the source storage location of the transferred object and the item data of the transferred items can be used as training data. The training labels are "need to transfer warehouse-1" and "no need to transfer warehouse-zero". After the training is completed, the server inputs the storage location data and item data of the object to be judged (that is, the storage location within the range of the transfer operation to determine whether the transfer needs to be performed) into the trained warehouse transfer classification model, obtains the calculation result output by the warehouse transfer classification model for the object to be judged, and determines the object to be judged whose calculation result indicates "need to transfer warehouse" as the proposed transfer object.

[0039] Taking the warehouse transfer classification model based on the random forest algorithm as an example, the information gain rate or Gini coefficient is used as the loss function to determine the various parameters in the random forest model, such as the number of decision trees in the forest, the depth of the decision tree, and the number of leaf nodes. All or part of the data in the above historical warehouse transfer real data is used as input, and whether to generate a warehouse transfer task is used as output for training. The features for each split are selected based on information gain, information gain ratio, or Gini index. After the training of a single decision tree is completed, all decision trees are combined into a random forest model, and the final classification result is determined by voting of multiple decision trees.

[0040] Taking the warehouse transfer classification model using neural network algorithm as an example, the above historical warehouse transfer real data and labels are digitized and standardized, and then input into the neural network for training. Various model parameters are constructed, including the number of neural network layers, randomly initialized weight values, learning rate, etc., and gradient descent, Adam and other algorithms are used for optimization and solution. ReLu is used as the activation function, and the cross entropy loss function is used. Finally, the model loss function is minimized, and the model parameters are continuously iterated and optimized until the set accuracy value is reached, and finally the warehouse transfer classification model is obtained.

[0041] After determining the objects to be moved, the server can obtain the object types of each object to be moved by clustering. In this article, object types refer to different types of objects formed by different characteristics of the storage locations and commodities therein. Object types can also be determined by the storage location type to which the storage location belongs and the item type to which the item belongs.

[0042] There are two ways to obtain object types through clustering: First, directly cluster the objects to be moved. Specifically, the server clusters the objects to be moved according to the object data of the objects to be moved, and obtains the object type to which each object to be moved belongs. It can be understood that the object data of each object includes the storage location data of the storage location in the object and the item data of the article in the object. Second, clustering is performed from two aspects, storage location and article. Specifically, the server clusters the storage locations and articles in the objects to be moved respectively, and obtains multiple storage location types and multiple article types. The object type to which any object to be moved includes: the storage location type to which the storage location in the object to be moved belongs and the article type to which the article in the object to be moved belongs. Exemplarily, the algorithm for performing the above clustering may be K-means, DBSCAN, etc.

[0043] Step S102: Determine the destination storage location type of any object type to which the object to be transferred belongs from the historical real data of warehouse transfer, determine the destination storage location type that meets the preset storage location type screening conditions as the target storage location type of the object to be transferred, and select the destination storage location of the object to be transferred from the current storage locations included in the target storage location type.

[0044] In this step, the server first needs to determine the storage location type of the object type to which any object to be transferred belongs from the historical real data of transfer, that is, for any object to be transferred, first determine the storage location type of the object type to which it belongs that is suitable for the transfer. The reason for doing so is that it is difficult to provide data guidance and prompts for the transfer purpose of specific storage locations and specific objects in the historical real data of transfer (the amount of matching data is extremely small), but through big data mining and analysis, relevant data for a certain object type can be provided. For example, data guidance for the transfer purpose of a specific object a cannot be given in the historical real data of transfer, because there may not be any historical data matching a in the historical real data of transfer, but data guidance for the object type A to which a belongs can be given, because there may be many historical data matching object type A in the historical real data of transfer.

[0045] In actual applications, the server has two methods to determine the type of the destination storage location for the object type to which any object to be transferred belongs. First, the server performs big data mining from the overall perspective of the object. Specifically, the server determines from the historical real data of transfers a specific moved object that belongs to the object type of any of the above objects to be transferred, that is, the specific moved object belongs to the same object type as any of the above objects to be transferred. Thereafter, the server determines the storage location type to which the destination storage location for the specific moved object belongs as the destination storage location type. It can be understood that the above storage location types determined are generally multiple, representing the types of real destination storage locations for the same object type in historical periods, and these types of storage locations may be the destination storage locations for the objects to be transferred to be processed.

[0046] For example, the object to be moved is a, and its object type is A. The server first queries the moved objects of object type A from the historical real data of the move (the query can be limited to the scope of the move operation). These moved objects are specific moved objects. Thereafter, the storage location types of the transfer destination storage locations of these specific moved objects are counted. If the counted storage location types are x, y, and z, then x, y, and z are the transfer destination storage location types of a and A.

[0047] Second, the server conducts big data mining from the two perspectives of storage location and items. Specifically, the server determines the storage location type in the object type to which any of the above proposed objects to be transferred belongs as the first storage location type, and determines the item type in the object type to which any of the above proposed objects to be transferred belongs as the first item type; and determines the transferred objects corresponding to the storage locations belonging to the first storage location type in the historical real data of transfer as the first type of objects, and determines the transferred objects corresponding to the items belonging to the first item type in the historical real data of transfer as the second type of objects. It can be understood that the first type of objects are objects with the same storage location type (relative to any of the above proposed objects to be transferred), the second type of objects are objects with the same item type (relative to any of the above proposed objects to be transferred), and the intersection of the first type of objects and the second type of objects is an object with the same object type (relative to any of the above proposed objects to be transferred). Finally, the server determines the storage location type to which the transfer destination storage location of a specific transferred object that is both a first type object and a second type object belongs as the transfer destination storage location type.

[0048] Continuing with the above example, the storage location type in A is A1 and the item type is A2. The server first queries the moved objects with storage location type A1 from the historical real data of warehouse transfer (the query can be limited to the scope of warehouse transfer operations). These moved objects are first-category objects. The server also queries the moved objects with item type A2 from the historical real data of warehouse transfer (the query can be limited to the scope of warehouse transfer operations). These moved objects are second-category objects. Then, it determines which objects are both first-category objects and second-category objects. These objects are specific moved objects. Finally, the server counts the storage location types of the transfer destination storage locations of these specific moved objects, that is, the transfer destination storage location types.

[0049] After that, the server determines the transfer destination storage location type that meets the preset storage location type screening conditions as the target storage location type of the object to be transferred. The above storage location type screening conditions can be formulated according to actual needs. For example, the server can determine the transfer destination storage location type corresponding to the most specific transferred objects as the target storage location type, or can determine the transfer destination storage location type corresponding to the most recent specific transferred object as the target storage location type, and "most recent" means that the time interval between a certain historical moment or historical period and the current moment is the shortest.

[0050] Finally, the server can select the destination storage location of the object to be transferred from the current storage locations included in the target storage location type, thereby realizing the final transfer operation of the object to be transferred. In specific applications, the server can select a storage location that meets the transfer rules from each current storage location included in the target storage location type as the destination storage location of the object to be transferred. The above transfer rules can be pre-configured for each object to be transferred, such as limiting the load-bearing weight, usage volume, insulation conditions, etc. of the destination storage location. Only storage locations that meet the above transfer rules can be used as the destination storage locations. After determining the destination storage location, the server can generate a transfer operation sheet and complete the transfer operation based on the transfer operation sheet.

[0051] Figure 2 is a schematic diagram of specific execution steps of the warehouse transfer processing method in an embodiment of the present invention, see Figure 2 In step S201, the server obtains historical warehouse transfer real data from the database; in step S202, the server uses historical warehouse transfer real data to train the warehouse transfer classification model; in step S203, the server identifies the objects to be transferred based on the warehouse transfer classification model; in step S204, the server clusters the objects to be transferred to obtain the object type; in step S205, the server obtains the specific transferred objects of each object to be transferred by mining the historical warehouse transfer real data; in step S206, the server determines the storage location type of the transfer destination storage location of the specific transferred object as the transfer destination storage location type; in step S207, the server filters the target storage location type from the transfer destination storage location type; in step S208, the server selects the storage location that meets the transfer rules from the current storage location included in the target storage location type as the transfer destination storage location; in step S209, the server generates a transfer operation sheet and performs the transfer operation to the transfer destination storage location.

[0052] In the technical solution of the embodiment of the present invention, the real data of historical warehouse transfer is used to train the warehouse transfer classification model based on the machine learning algorithm in advance, and the trained warehouse transfer classification model is used to determine which of the current objects in the warehouse need to be transferred, that is, to determine the objects to be transferred. Then, the object type of each object to be transferred is determined by the clustering model, and the real data of historical warehouse transfer is mined and analyzed to obtain the transfer destination storage location type of any object type to which the object to be transferred belongs. Finally, the transfer destination storage location type that meets the preset storage location type screening conditions is determined as the target storage location type of the object to be transferred, and the final transfer destination storage location of the object to be transferred is selected from the current storage location included in the target storage location type. Through warehouse transfer discrimination based on machine learning models, clustering of objects to be transferred, and destination storage location flow mining, the present invention realizes automated warehouse transfer decision-making based on big data analysis, avoids the defects of the existing technology that heavily relies on manual experience, improves the rationality of warehouse transfer, and helps to further improve storage location utilization.

[0053] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of the present invention are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security and national security.

[0054] For the above-mentioned method embodiments, for the convenience of description, they are expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, and some steps can actually be performed in other orders or simultaneously. In addition, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily necessary to implement the present invention.

[0055] In order to better implement the above-mentioned solution of the embodiment of the present invention, relevant devices for implementing the above-mentioned solution are also provided below.

[0056] See also Figure 3 As shown, the warehouse transfer processing device 300 provided in the embodiment of the present invention may include: a warehouse transfer classification unit 301 and a warehouse transfer operation unit 302.

[0057] Among them, the warehouse transfer classification unit 301 can be used to train a pre-established warehouse transfer classification model based on historical real warehouse transfer data, and input the storage location data and item data of the object to be identified into the trained warehouse transfer classification model to obtain the proposed warehouse transfer object among the objects to be identified; wherein, each object includes a storage location and the items currently stored in the storage location; the warehouse transfer operation unit 302 can be used to determine the transfer destination storage location type of any object type to which the proposed warehouse transfer object belongs from the historical real warehouse transfer data, determine the transfer destination storage location type that meets the preset storage location type screening conditions as the target storage location type of the proposed warehouse transfer object, and select the transfer destination storage location of the proposed warehouse transfer object from the current storage locations contained in the target storage location type.

[0058] In the implementation of the present invention, the warehouse transfer classification unit 301 can be further used to: input the storage location data and item data of the object to be identified into the trained warehouse transfer classification model to obtain the calculation result output by the warehouse transfer classification model for the object to be identified; and determine the object to be identified whose calculation result indicates "needs to be transferred" as the proposed warehouse transfer object.

[0059] In actual applications, the device 300 may further include a clustering unit, which is used to: after obtaining the objects to be moved, cluster the objects to be moved according to the object data of the objects to be moved, so as to obtain the object type to which each object to be moved belongs; wherein the object data of each object includes the storage location data of the storage location in the object and the item data of the item in the object.

[0060] In practical applications, the clustering unit can be further used to: after obtaining the object to be transferred, cluster the storage locations and items in the object to be transferred respectively to obtain multiple storage location types and item types; the object type to which any object to be transferred belongs includes: the storage location type to which the storage location in the object to be transferred belongs and the item type to which the item in the object to be transferred belongs.

[0061] Preferably, the historical real data of warehouse transfer includes: storage location data of source storage locations of multiple transferred objects, storage location data of transfer destination storage locations, and item data of transferred items; and the warehouse transfer operation unit 302 can be further used to: determine a specific transferred object belonging to the object type to which any object to be transferred belongs from the historical real data of warehouse transfer; and determine the storage location type to which the transfer destination storage location of the specific transferred object belongs as the transfer destination storage location type.

[0062] As a preferred scheme, the warehouse transfer operation unit 302 can be further used to: determine the storage location type in the object type to which any of the objects to be transferred belongs as the first storage location type, and determine the item type in the object type to which any of the objects to be transferred belongs as the first item type; determine the moved objects corresponding to the storage locations belonging to the first storage location type in the historical warehouse transfer real data as first-category objects, determine the moved objects corresponding to the items belonging to the first item type in the historical warehouse transfer real data as second-category objects, and determine the storage location type of the transfer destination storage location of a specific moved object that is both a first-category object and a second-category object as the transfer destination storage location type.

[0063] In one embodiment, the warehouse transfer operation unit 302 can be further used to: determine the destination storage location type corresponding to the most specific transferred objects as the target storage location type; or determine the destination storage location type corresponding to the most recent specific transferred object as the target storage location type.

[0064] In addition, in an embodiment of the present invention, the warehouse transfer operation unit 302 can be further used to: select a storage location that meets the preset warehouse transfer rules for the object to be transferred from each current storage location included in the target storage location type as the transfer destination storage location of the object to be transferred.

[0065] According to the technical solution of the embodiment of the present invention, the real data of historical warehouse transfer is used in advance to train the warehouse transfer classification model based on the machine learning algorithm, and the trained warehouse transfer classification model is used to determine which of the current objects in the warehouse need to be transferred, that is, to determine the objects to be transferred. Then, the object type of each object to be transferred is determined by the clustering model, and the real data of historical warehouse transfer is mined and analyzed to obtain the transfer destination storage location type of any object type to which the object to be transferred belongs. Finally, the transfer destination storage location type that meets the preset storage location type screening conditions is determined as the target storage location type of the object to be transferred, and the final transfer destination storage location of the object to be transferred is selected from the current storage location included in the target storage location type. Through the warehouse transfer judgment based on the machine learning model, the clustering of the objects to be transferred and the mining of the destination storage location flow, the present invention realizes the automated warehouse transfer decision-making based on big data analysis, avoids the defects of the existing technology that heavily relies on manual experience, improves the rationality of warehouse transfer, and helps to further improve the storage location utilization rate.

[0066] Figure 4 An exemplary system architecture 400 is shown to which the warehouse transfer processing method or the warehouse transfer processing device according to the embodiment of the present invention can be applied.

[0067] like Figure 4 As shown, the system architecture 400 may include terminal devices 401, 402, 403, a network 404 and a server 405 (this architecture is only an example, and the components included in the specific architecture may be adjusted according to the specific application). The network 404 is used to provide a medium for a communication link between the terminal devices 401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0068] Users can use terminal devices 401, 402, 403 to interact with server 405 through network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, 403, such as warehouse transfer operation applications (only as an example).

[0069] The terminal devices 401 , 402 , and 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0070] The server 405 may be a server that provides various services, such as a warehouse management server (for example only) that provides support for warehouse transfer operation applications operated by users using the terminal devices 401, 402, and 403. The warehouse management server may process the received warehouse transfer decision request, etc., and feed back the processing result (for example, the transfer destination storage location identifier of the object to be transferred - for example only) to the terminal devices 401, 402, and 403.

[0071] It should be noted that the warehouse transfer processing method provided in the embodiment of the present invention is generally executed by the server 405 , and accordingly, the warehouse transfer processing device is generally set in the server 405 .

[0072] It should be understood that Figure 4 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.

[0073] The present invention also provides an electronic device. The electronic device of an embodiment of the present invention includes: 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 warehouse transfer processing method provided by the present invention.

[0074] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 of an electronic device suitable for implementing an embodiment of the present invention. Figure 5 The electronic 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.

[0075] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0076] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0077] In particular, according to the embodiments disclosed in the present invention, the process described in the main step diagram above can be implemented as a computer software program. For example, the embodiments of the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the main step diagram. In the above embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit 501, the above functions defined in the system of the present invention are executed.

[0078] It should be noted that the computer-readable medium shown in 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 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 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. Computer readable signal media may also be any computer readable medium other than computer readable storage media, 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.

[0079] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product 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.

[0080] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes a warehouse transfer classification unit and a warehouse transfer operation unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the warehouse transfer classification unit may also be described as "a unit that provides a warehouse transfer object to a warehouse transfer operation unit".

[0081] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the device, the steps executed by the device include: training a pre-established warehouse transfer classification model according to historical warehouse transfer real data, inputting the storage location data and item data of the object to be identified into the trained warehouse transfer classification model, and obtaining the proposed warehouse transfer object among the objects to be identified; wherein each object includes a storage location and the items currently stored in the storage location; determining the warehouse transfer destination storage location type of the object type to which any proposed warehouse transfer object belongs from the historical warehouse transfer real data, determining the warehouse transfer destination storage location type that meets the preset storage location type screening condition as the target storage location type of the proposed warehouse transfer object, and selecting the warehouse transfer destination storage location of the proposed warehouse transfer object from the current storage locations included in the target storage location type.

[0082] In the technical solution of the embodiment of the present invention, the real data of historical warehouse transfer is used to train the warehouse transfer classification model based on the machine learning algorithm in advance, and the trained warehouse transfer classification model is used to determine which of the current objects in the warehouse need to be transferred, that is, to determine the objects to be transferred. Then, the object type of each object to be transferred is determined by the clustering model, and the real data of historical warehouse transfer is mined and analyzed to obtain the transfer destination storage location type of any object type to which the object to be transferred belongs. Finally, the transfer destination storage location type that meets the preset storage location type screening conditions is determined as the target storage location type of the object to be transferred, and the final transfer destination storage location of the object to be transferred is selected from the current storage location included in the target storage location type. Through warehouse transfer discrimination based on machine learning models, clustering of objects to be transferred, and destination storage location flow mining, the present invention realizes automated warehouse transfer decision-making based on big data analysis, avoids the defects of the existing technology that heavily relies on manual experience, improves the rationality of warehouse transfer, and helps to further improve storage location utilization.

[0083] The above specific implementations do not constitute a limitation on the protection scope 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 modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A warehouse transfer processing method, characterized in that: include: A pre-established warehouse transfer classification model is trained based on historical warehouse transfer real data, and the storage location data and item data of the object to be identified are input into the trained warehouse transfer classification model to obtain the proposed warehouse transfer object among the objects to be identified; wherein each object includes a storage location and items currently stored in the storage location; Determine the destination storage location type of any object type to which the object to be transferred belongs from the historical real data of warehouse transfer, determine the destination storage location type that meets the preset storage location type screening conditions as the target storage location type of the object to be transferred, and select the destination storage location of the object to be transferred from the current storage locations contained in the target storage location type.

2. The method according to claim 1, characterized in that The step of inputting the storage location data and item data of the object to be identified into the trained warehouse transfer classification model to obtain the proposed warehouse transfer object among the object to be identified includes: Inputting the storage location data and item data of the object to be identified into the trained warehouse transfer classification model to obtain the calculation result output by the warehouse transfer classification model for the object to be identified; The object to be identified for which the calculation result indicates "needs to be moved" is determined as the object to be moved.

3. The method according to claim 1, characterized in that The method further comprises: After obtaining the objects to be moved, clustering is performed on the objects to be moved according to their object data to obtain the object type to which each object to be moved belongs; wherein the object data of each object includes storage location data of the storage location in the object and item data of the item in the object.

4. The method according to claim 1, characterized in that: The method further comprises: After obtaining the object to be transferred, the storage locations and items in the object to be transferred are clustered respectively to obtain multiple storage location types and item types; the object type to which any object to be transferred belongs includes: the storage location type to which the storage location in the object to be transferred belongs and the item type to which the item in the object to be transferred belongs.

5. The method according to claim 3, characterized in that: The historical warehouse transfer real data includes: storage location data of source storage locations of multiple warehouse transferred objects, storage location data of transfer destination storage locations, and item data of transferred items; and determining the transfer destination storage location type of the object type to which any object to be transferred belongs from the historical warehouse transfer real data includes: Determine, from the historical warehouse transfer real data, a specific warehouse-transferred object belonging to the object type to which any warehouse-transferred object belongs; The storage location type to which the transfer destination storage location of the specific transferred object belongs is determined as the transfer destination storage location type.

6. The method according to claim 4, characterized in that The historical warehouse transfer real data includes: storage location data of source storage locations of multiple warehouse transferred objects, storage location data of transfer destination storage locations, and item data of transferred items; and determining the transfer destination storage location type of the object type to which any object to be transferred belongs from the historical warehouse transfer real data includes: Determine the storage location type in the object type to which any object to be transferred belongs as the first storage location type, and determine the item type in the object type to which any object to be transferred belongs as the first item type; The moved objects corresponding to the storage locations belonging to the first storage location type in the historical real data of warehouse transfer are determined as first-category objects, the moved objects corresponding to the items belonging to the first item type in the historical real data of warehouse transfer are determined as second-category objects, and the storage location type of the transfer destination storage location of a specific moved object that is both a first-category object and a second-category object is determined as the transfer destination storage location type.

7. The method according to claim 5 or 6, characterized in that: The step of determining the target storage location type that meets the preset storage location type screening condition as the target storage location type of the object to be transferred includes: Determine the transfer destination storage location type corresponding to the largest number of specific transferred objects as the target storage location type; or, The destination storage location type corresponding to the most recent specific transferred object is determined as the target storage location type.

8. The method according to claim 1, characterized in that: The step of selecting the target storage location for the object to be transferred from the current storage locations included in the target storage location type includes: A storage location that satisfies the preset transfer rule for the proposed transfer object is selected from each current storage location included in the target storage location type as the transfer destination storage location of the proposed transfer object.

9. A warehouse transfer processing device, characterized in that: include: The warehouse transfer classification unit is used to train a pre-established warehouse transfer classification model based on historical warehouse transfer real data, input the storage location data and item data of the object to be identified into the trained warehouse transfer classification model, and obtain the proposed warehouse transfer object among the objects to be identified; wherein each object includes a storage location and the items currently stored in the storage location; The warehouse transfer operation unit is used to determine the destination storage location type of any object type to which the object to be transferred belongs from the historical real data of warehouse transfer, determine the destination storage location type that meets the preset storage location type screening conditions as the target storage location type of the object to be transferred, and select the destination storage location of the object to be transferred from the current storage locations included in the target storage location type.

10. 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 8.

11. A computer-readable storage 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 8 is implemented.

Images