Product selection method, device, equipment and storage medium

Abstract

The present embodiment provides a product selection method, device, equipment and storage medium, which obtains multiple sets of items, obtains the current feature data of each item in the item set in the current processing cycle and the historical feature data in the historical processing cycle for each item in the item set, calculates the score value corresponding to the item set based on the current feature data and the historical feature data, determines the target item set from the multiple item sets based on the score value, and determines the first item to be transferred out from the target area based on the target item set. The present embodiment has the following beneficial effects: the target area is selected in combination with the current feature data and the historical feature data, and the first item to be transferred out from the target area is determined, which realizes the timely adjustment of the items in the target area, so that the items of the same order exist in the same area. When an order is received, only the pickers in the corresponding area need to pick the items in the area, which improves the picking efficiency.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of warehousing and logistics, and in particular to a product selection method, device, equipment and storage medium. Background Art

[0002] Currently, zone picking is commonly used to pick items from the warehouse. Zone picking refers to dividing the warehouse into multiple areas. When a user order is received, the pickers will pick independently in different areas, among which the pickers in this area are used to pick items within this area.

[0003] In the prior art, product selection is only performed once at the initial stage of warehouse planning. Usually, corresponding items are allocated to each area based on the historical sales data and experience of the items. For example, if the sales of item 1 and item 2 are respectively greater than the preset sales, item 1 and item 2 are allocated to the same area. In this way, the possibility of item 1 and item 2 appearing in the same order is greater.

[0004] However, in the process of implementing this application, the inventors found that there are at least the following problems in the prior art: as the sales situation changes dynamically, the sales volume of items will change. The use of the above solution may cause items of the same order to be distributed in different areas, reducing picking efficiency. Summary of the invention

[0005] The embodiments of the present application provide a product selection method, device, equipment and storage medium for dynamically adjusting items in a target area so that the items in the target area exist in the same order, thereby improving picking efficiency.

[0006] In a first aspect, an embodiment of the present application provides a product selection method, comprising:

[0007] Acquire multiple object sets, each object set includes at least one first object in a target area, and the target area includes multiple first objects;

[0008] For each set of items, obtaining current feature data of each item in the set of items in a current processing cycle and historical feature data in historical processing cycles;

[0009] Calculate a score value corresponding to the item set according to the current feature data and the historical feature data, where the score value is used to indicate the probability that the items in the item set exist in the same order;

[0010] Determining a target item set from the multiple item sets according to the score values, wherein the score value corresponding to the target item set is greater than a preset value;

[0011] A first object to be retrieved from the target area is determined according to the target object set.

[0012] In a specific implementation, the current processing cycle includes at least two current processing time periods, and the current feature data includes feature data corresponding to the at least two current processing time periods; the historical processing cycle includes at least two historical processing time periods, and the historical feature data includes feature data corresponding to the at least two historical processing time periods;

[0013] The calculating, according to the current feature data and the historical feature data, a score value corresponding to the item set includes:

[0014] Performing a weighted operation on the same type of data in the current feature data to obtain at least one current feature index corresponding to the item;

[0015] Performing a weighted operation on the same type of data in the historical feature data to obtain at least one historical feature indicator corresponding to the item;

[0016] According to at least one current characteristic indicator and at least one historical characteristic indicator corresponding to each item in the item set, a score value corresponding to the item set is obtained.

[0017] In a specific implementation, obtaining a score value corresponding to the item set according to at least one current feature indicator and at least one historical feature indicator corresponding to each item in the item set includes:

[0018] According to at least one current feature indicator corresponding to each item in the item set, current feature indicators of the same category are added together to obtain at least one first sum value;

[0019] According to at least one historical characteristic indicator corresponding to each item in the item set, historical characteristic indicators of the same category are added together to obtain at least one second sum value;

[0020] Performing a weighted operation on the at least one first sum value to obtain a first weighted value, and performing a weighted operation on the at least one second sum value to obtain a second weighted value;

[0021] The first weighted value and the second weighted value are added to obtain a score value corresponding to the item set.

[0022] In a specific implementation, the obtaining of multiple sets of items includes:

[0023] Acquire a second item, where the second item is an item in another area or a new item;

[0024] The plurality of sets of objects are acquired according to the plurality of first objects and the second objects in the target area.

[0025] In a specific implementation, if the target item set also includes a second item, the method further includes:

[0026] The second object is determined as the object to be transferred into the target area.

[0027] In a specific implementation, if the second item is a new item and the item set also includes the second item, obtaining current feature data of each item in the item set in a current processing cycle includes:

[0028] Acquire current feature data of the at least one first object in a current processing cycle, and current feature data of the second object in a current processing cycle;

[0029] Accordingly, the step of obtaining the second characteristic data of the items in the item set within the historical processing cycle includes:

[0030] Acquire historical feature data of the at least one first item within a historical processing cycle, and historical feature data of the second item within a historical processing cycle.

[0031] In a specific implementation, the obtaining current feature data of the second object in the current processing cycle includes:

[0032] Acquire attribute information of a plurality of first items and attribute information of the second items in the target area, wherein the attribute information includes at least one of unit price, volume, and weight;

[0033] Standardizing the attribute information of the plurality of first items and the attribute information of the second item;

[0034] Using a hierarchical clustering algorithm, according to the standardized attribute information of the plurality of first items and the standardized attribute information of the second items, the cluster distance between each two items is calculated, and the two items with the smallest cluster distance are clustered into one category, and this step is repeated until the plurality of first items and the second items are clustered into one category;

[0035] Obtaining the minimum value of the minimum clustering distance in the clustering process, and determining the item category corresponding to the minimum value;

[0036] determining the category of the second item from among the item categories;

[0037] The current feature data of the second object is obtained according to the current feature data of each first object in the category to which the second object belongs.

[0038] In a specific implementation, the acquiring of historical characteristic data of the second object in a historical processing cycle includes:

[0039] The historical feature data of the second object is acquired according to the historical feature data of each first object in the category to which the second object belongs.

[0040] In a specific implementation, the method further includes:

[0041] Abnormal attribute information from the attribute information of the plurality of first items is eliminated.

[0042] In a specific implementation, the score value corresponding to the target item set is the maximum value among the score values ​​corresponding to the multiple item sets.

[0043] In a second aspect, an embodiment of the present application provides a product selection device, including:

[0044] An acquisition module, configured to acquire a plurality of object sets, each of which includes at least one first object in a target area, and the target area includes a plurality of first objects;

[0045] For each set of items, obtaining current feature data of each item in the set of items in a current processing cycle and historical feature data in historical processing cycles;

[0046] a processing module, configured to calculate a score value corresponding to the item set according to the current feature data and the historical feature data, wherein the score value is used to indicate a probability that items in the item set exist in the same order;

[0047] Determining a target item set from the multiple item sets according to the score values, wherein the score value corresponding to the target item set is greater than a preset value;

[0048] A first object to be retrieved from the target area is determined according to the target object set.

[0049] In a specific implementation, the current processing cycle includes at least two current processing time periods, and the current feature data includes feature data corresponding to the at least two current processing time periods; the historical processing cycle includes at least two historical processing time periods, and the historical feature data includes feature data corresponding to the at least two historical processing time periods;

[0050] The processing module is specifically used for:

[0051] Performing a weighted operation on the same type of data in the current feature data to obtain at least one current feature index corresponding to the item;

[0052] Performing a weighted operation on the same type of data in the historical feature data to obtain at least one historical feature indicator corresponding to the item;

[0053] According to at least one current characteristic indicator and at least one historical characteristic indicator corresponding to each item in the item set, a score value corresponding to the item set is obtained.

[0054] In a specific implementation, the processing module is specifically used to:

[0055] According to at least one current feature indicator corresponding to each item in the item set, current feature indicators of the same category are added together to obtain at least one first sum value;

[0056] According to at least one historical characteristic indicator corresponding to each item in the item set, historical characteristic indicators of the same category are added together to obtain at least one second sum value;

[0057] Performing a weighted operation on the at least one first sum value to obtain a first weighted value, and performing a weighted operation on the at least one second sum value to obtain a second weighted value;

[0058] The first weighted value and the second weighted value are added to obtain a score value corresponding to the item set.

[0059] In a specific implementation, the acquisition module is specifically used to:

[0060] Acquire a second item, where the second item is an item in another area or a new item;

[0061] The plurality of sets of objects are acquired according to the plurality of first objects and the second objects in the target area.

[0062] In a specific implementation, if the target item set also includes a second item, the processing module is further configured to:

[0063] The second object is determined as the object to be transferred into the target area.

[0064] In a specific implementation, if the second item is a new item and the item set also includes the second item, the acquisition module is specifically configured to:

[0065] Acquire current feature data of the at least one first object in a current processing cycle, and current feature data of the second object in a current processing cycle;

[0066] Acquire historical feature data of the at least one first item within a historical processing cycle, and historical feature data of the second item within a historical processing cycle.

[0067] In a specific implementation, the acquisition module is specifically used to:

[0068] Acquire attribute information of a plurality of first items and attribute information of the second items in the target area, wherein the attribute information includes at least one of unit price, volume, and weight;

[0069] Standardizing the attribute information of the plurality of first items and the attribute information of the second item;

[0070] Using a hierarchical clustering algorithm, according to the standardized attribute information of the plurality of first items and the standardized attribute information of the second items, the cluster distance between each two items is calculated, and the two items with the smallest cluster distance are clustered into one category, and this step is repeated until the plurality of first items and the second items are clustered into one category;

[0071] Obtaining the minimum value of the minimum clustering distance in the clustering process, and determining the item category corresponding to the minimum value;

[0072] determining the category of the second item from among the item categories;

[0073] The current feature data of the second object is obtained according to the current feature data of each first object in the category where the second object belongs.

[0074] In a specific implementation, the acquisition module is further used to:

[0075] The historical feature data of the second object is acquired according to the historical feature data of each first object in the category to which the second object belongs.

[0076] In a specific implementation, the processing module is further used for:

[0077] Abnormal attribute information from the attribute information of the plurality of first items is eliminated.

[0078] In a specific implementation, the score value corresponding to the target item set is the maximum value among the score values ​​corresponding to the multiple item sets.

[0079] In a third aspect, an embodiment of the present application provides a terminal device, including:

[0080] Processor, memory, and interfaces for communicating with other electronic devices;

[0081] The memory stores computer-executable instructions;

[0082] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the product selection method as described in the first aspect.

[0083] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the product selection method described in the first aspect.

[0084] The embodiments of the present application provide a product selection method, apparatus, device and storage medium, which obtain multiple item sets, each item set includes at least one first item in a target area, and the target area includes multiple first items. For each item set, current feature data of each item in the item set in a current processing cycle and historical feature data in a historical processing cycle are obtained, the current feature data and the historical feature data respectively include at least one of an average picking time, an average order quantity, and an average number of items in an order. Based on the current feature data and the historical feature data, a score value corresponding to the item set is calculated, and the score value is used to indicate the probability that the items in the item set exist in the same order. Based on the score value, a target item set is determined from the multiple item sets, wherein the score value corresponding to the target item set is greater than a preset value, and based on the target item set, a first item to be called out from the target area is determined. This embodiment has the following beneficial effects: it selects items for the target area in combination with current feature data and historical feature data, determines the first item to be transferred out from the target area, and realizes timely adjustment of the items in the target area, so that items of the same order exist in the same area. When an order is received, only the pickers in the corresponding area need to pick items in the area, avoiding other pickers from picking items in other areas, thereby improving picking efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 A schematic diagram of an application scenario of the product selection method provided in an embodiment of the present application;

[0086] Figure 2 Schematic diagram of the process of the product selection method provided in the embodiment of the present application Figure 1 ;

[0087] Figure 3 Schematic diagram of the target area product selection process provided in the embodiment of the present application Figure 1 ;

[0088] Figure 4 Schematic diagram of the product selection process provided in the embodiment of this application Figure 2 ;

[0089] Figure 5 Schematic diagram of the target area product selection process provided in the embodiment of the present application Figure 2 ;

[0090] Figure 6 Schematic diagram of the process of the product selection method provided in the embodiment of the present application Figure 3 ;

[0091] Figure 7 A schematic diagram of the structure of a product selection device provided in an embodiment of the present application;

[0092] Figure 8 A schematic diagram of the hardware structure of a terminal device provided in an embodiment of the present application.

[0093] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0094] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0095] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0096] Figure 1 A schematic diagram of an application scenario of the product selection method provided in the embodiment of the present application, such as Figure 1 As shown, a warehouse is usually equipped with multiple areas, for example, area 1, area 2, area 3, and area 4. Each area stores corresponding items. When a user order is received, the pickers in different areas will pick items independently. The pickers in this area are only responsible for picking items in this area. The regional picking method avoids the pickers running around the warehouse to pick items in the order. By having the pickers in different areas pick items independently in their own areas, the picking efficiency is improved to a certain extent.

[0097] At present, product selection is only carried out once at the initial stage of warehouse planning. Items are usually allocated to various areas of the warehouse based on data such as the historical sales volume of the items. That is to say, the categories of items stored in various areas of the warehouse are basically fixed. However, in the process of implementing this application, the inventors found that there are at least the following problems in the prior art: with the dynamic changes in sales, the sales volume of items will change. The use of the above solution may cause items of the same order to be allocated to different areas, reducing the picking efficiency.

[0098] In response to the above problems, an embodiment of the present application provides a product selection method. By combining the current feature data and historical feature data of the items, items that may appear in the same order are transferred to the target area, and items that are unlikely to appear in the same order are transferred out of the target area, thereby achieving timely adjustment of items in the target area, so that items of the same order exist in the same area. When an order is received, only the pickers in the corresponding area need to pick items in the local area, avoiding other pickers from picking items in other areas, thereby improving picking efficiency.

[0099] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0100] Figure 2 Schematic diagram of the process of the product selection method provided in the embodiment of the present application Figure 1 The execution subject of this embodiment may be a terminal device, such as a mobile phone, a laptop computer, a tablet computer, etc. Figure 2 As shown, the product selection method provided in this embodiment may include:

[0101] S101. Acquire multiple object sets, each object set including at least one first object in a target area.

[0102] There are multiple areas in the warehouse, each area corresponds to a picker, and in actual application, the target area is any area in the warehouse for storing items, and the target area includes multiple first items, for example, different types of items of different brands.

[0103] Specifically, multiple first items in the target area are randomly combined to obtain multiple item sets. For example, the target area includes n first items, and the n first items are randomly combined to obtain A collection of items.

[0104] S102: For each item set, obtain current feature data of each item in the item set in a current processing cycle and historical feature data in historical processing cycles.

[0105] Among them, the current feature data can be the operating data of the past x days, and the historical feature data can be the operating data of y days before the warehouse was established. That is to say, the current feature data can better reflect the recent operating conditions of the item, and the historical feature data can better reflect the historical operating conditions of the item.

[0106] The current feature data and the historical feature data may respectively include at least one of an average picking time, an average order quantity, and an average number of items in an order.

[0107] It should be noted that the average picking time is used to evaluate the speed of item picking. The faster the items are picked, the higher the picking efficiency. The average order volume is used to measure the popularity of items. If the sales volume of an item is relatively low, and it occupies inventory space in the warehouse, resulting in a waste of space, such items should be placed in the slow-moving items area. The average number of orders refers to the number of items in an order. If the average number of orders for an item is high, the more items are picked each time, and the higher the picking efficiency. Selecting such items will help improve picking efficiency.

[0108] From this we can see that the average picking time is a negative parameter for picking efficiency, while the average order quantity and the average number of orders are positive parameters for picking efficiency.

[0109] S103. Calculate a score value corresponding to the item set based on the current feature data and the historical feature data. The score value is used to indicate the probability that the items in the item set exist in the same order.

[0110] In a specific implementation, the current processing cycle includes at least two current processing time periods, and the current feature data includes feature data corresponding to the at least two current processing time periods respectively; the historical processing cycle includes at least two historical processing time periods, and the historical feature data includes feature data corresponding to the at least two historical processing time periods respectively.

[0111] Among them, at least two current processing time periods can be the past 7 days, the past 30 days, the past 90 days, etc., each current processing time period corresponds to a characteristic data, and each characteristic data includes at least one of the average picking time, the average order quantity, and the average number of orders; at least two historical processing time periods can be the 7 days before the establishment of the warehouse, the previous 30 days, the previous 90 days, etc., each historical processing time period corresponds to a characteristic data, and each characteristic data includes at least one of the average picking time, the average order quantity, and the average number of orders.

[0112] Accordingly, S103 specifically includes:

[0113] A1: Perform a weighted operation on the same type of data in the current feature data to obtain at least one current feature index corresponding to the item.

[0114] For each set of items, the current feature data of each item includes feature data corresponding to at least two current processing time periods, and each feature data includes at least one of average picking time, average order quantity, and average number of items in an order.

[0115] Among them, the average picking time is a type of data, the average order volume is a type of data, and the average number of orders is a type of data. Since the average picking time is a negative parameter, and the average order volume and the average number of orders are positive parameters, the reciprocal of the average picking time can be taken and converted into a positive parameter. After conversion into a positive parameter, it is also a type of data. Then, a weighted operation is performed based on the same type of data in the current feature data to obtain at least one current feature index corresponding to the item. Among them, each type of data corresponds to a current feature index, that is, when each feature data includes the average picking time, the average order volume, and the average number of orders, the three current feature indicators corresponding to the item can be obtained.

[0116] Exemplarily, Table 1 is a schematic table of current feature data of each item. As shown in Table 1, at least two current processing periods include the past 7 days, the past 30 days, and the past 90 days. Each current processing period corresponds to a feature data, and each feature data includes the average picking time (1 / X), the average order quantity (Y), and the average number of orders (Z). In Table 1, the average picking time (1 / X) has been converted into a positive parameter X.

[0117]

[0118] Table 1

[0119] in, represents the value of X of item i in the past m days, represents the value of Y of item i in the past m days, It represents the value of Z of item i in the past m days. The value of i ranges from 1 to j, and m is 7, 30, and 90 respectively.

[0120] Then the at least one current feature index corresponding to item i includes three current feature indexes, namely X i , Y i , Z i , calculated as follows:

[0121]

[0122]

[0123]

[0124] in, It represents the reciprocal of the average picking time of item i in the past 7 days. It represents the reciprocal of the average picking time of item i in the past 30 days. It represents the reciprocal of the average picking time of item i in the past 90 days; represents the average order volume of item i in the past 7 days, represents the average order volume of item i in the past 30 days, represents the average order volume of item i in the past 90 days; Indicates the average number of orders for item i in the past 7 days, Indicates the average number of orders for item i in the past 30 days, Represents the average number of orders for item i in the past 90 days.

[0125] α, α(1-α), α(1-α) 2 are weight coefficients respectively, 0≤α≤1, α is a sliding parameter, and the value of α can be determined according to actual conditions, which is not limited in this embodiment.

[0126] As can be seen from formulas (1)-(3), the larger the weight coefficient corresponding to the recent feature data, the smaller the weight coefficient corresponding to the long-term feature data.

[0127] A2: Perform a weighted operation on the same type of data in the historical feature data to obtain at least one historical feature indicator corresponding to the item.

[0128] For each set of items, the historical feature data of each item includes feature data corresponding to at least two historical processing time periods, and each feature data includes at least one of average picking time, average order quantity, and average number of items in an order.

[0129] The calculation method of at least one historical characteristic index of each item is similar to the calculation method of at least one current characteristic index of the item in step A1, which will not be repeated here. For example, the at least one historical characteristic index corresponding to item i includes three historical characteristic indexes, namely X'1, Y'1, and Z'1, and the calculation method is as follows:

[0130]

[0131]

[0132]

[0133] in, It represents the reciprocal of the average picking time of item i in the 7 days before the warehouse was established. It represents the reciprocal of the average picking time of item i in the 30 days before the warehouse was established. It represents the reciprocal of the average picking time of item i in the 90 days before the warehouse was established;

[0134] represents the average order quantity of item i in the 7 days before the warehouse was established, represents the average order quantity of item i in the 30 days before the warehouse was established, represents the average order quantity of item i in the 90 days before the warehouse was established; It represents the average number of orders for item i in the 7 days before the warehouse was established. It represents the average number of orders for item i in the 30 days before the warehouse was established. It represents the average number of orders for item i in the 90 days before the warehouse was established.

[0135] ω、ω(1-ω),ω(1-ω) 2 are weight coefficients respectively, 0≤ω≤1, ω is a sliding parameter, and the value of ω can be determined according to actual conditions, which is not limited in this embodiment.

[0136] A3: Obtain a score value corresponding to the item set according to at least one current feature indicator and at least one historical feature indicator corresponding to each item in the item set.

[0137] The score value is used to indicate the probability that the items in the item set exist in the same order. The larger the score value is, the greater the probability that the items in the item set exist in the same order is.

[0138] Through steps A1-A2, at least one current characteristic index and at least one historical characteristic index corresponding to each item in each item set are obtained, and then the score value corresponding to the item set can be obtained according to the at least one current characteristic index and at least one historical characteristic index corresponding to each item. The specific implementation method is as follows: Figure 4 The examples are described below.

[0139] S104: Determine a target item set from multiple item sets according to the score values.

[0140] Through steps S101-S103, the score value corresponding to each item set is obtained, and then the target item set is determined from the multiple item sets according to the score value, wherein the score value corresponding to the target item set is greater than the preset value. The preset value can be determined according to actual conditions, and this embodiment does not limit this.

[0141] Optionally, the score value corresponding to the target item set is the maximum value among the score values ​​corresponding to the multiple item sets. In this way, the probability that the items in the target item set appear in the same order is the highest, thereby improving the picking efficiency.

[0142] S105: Determine the first object to be retrieved from the target area according to the target object set.

[0143] Among them, the target area includes multiple first items, and the items in the target item set are the first items in the target area. Then, the items in the target area except the target item set are determined as the first items to be called out, thereby realizing the selection of items in the target area.

[0144] Figure 3 Schematic diagram of the target area product selection process provided in the embodiment of the present application Figure 1 ,like Figure 3 As shown, the original target area includes multiple first items (recorded as A set + B set), and the target item set includes some types of first items (A set), so B set is determined as the first item to be called out. After the items are selected, only A set is stored in the current target area.

[0145] The product selection method provided in this embodiment obtains multiple item sets, each item set includes at least one first item in the target area, and the target area includes multiple first items. For each item set, the current feature data of each item in the item set in the current processing cycle and the historical feature data in the historical processing cycle are obtained. According to the current feature data and the historical feature data, the score value corresponding to the item set is calculated, and the score value is used to represent the probability that the items in the item set exist in the same order. According to the score value, the target item set is determined from the multiple item sets, wherein the score value corresponding to the target item set is greater than a preset value, and according to the target item set, the first item to be transferred out from the target area is determined. This embodiment has the following beneficial effects: the target area is selected in combination with the current feature data and the historical feature data, and the first item to be transferred out from the target area is determined, so that the items in the target area are adjusted in time, so that the items of the same order exist in the same area. When an order is received, only the pickers in the corresponding area need to pick the items in the area, so as to avoid other pickers from picking items in other areas, thereby improving the picking efficiency.

[0146] Based on the above embodiments, Figure 4 Schematic diagram of the product selection process provided in the embodiment of this application Figure 2 ,like Figure 4 As shown, step S103 specifically includes:

[0147] S201. According to at least one current feature indicator corresponding to each item in the item set, current feature indicators of the same category are added together to obtain at least one first sum value.

[0148] For example, at least one current feature index corresponding to item i in the item set is denoted as X i , Y i , Z i , then add the current feature indicators of the same class to obtain at least one first added value, which are:

[0149] Among them, U represents the item set.

[0150] If at least one current feature index corresponding to item i in the item set includes X i , then add the current feature indices of the same class to get a first added value, that is,

[0151] S202. According to at least one historical characteristic indicator corresponding to each item in the item set, historical characteristic indicators of the same category are added together to obtain at least one second sum value.

[0152] Similarly, if at least one historical feature indicator corresponding to item i in the item set includes X i ', Y i ', Z i ', then add the current feature indicators of the same class to obtain at least one second added value, which are:

[0153] Among them, U represents the item set.

[0154] S203: Perform a weighted operation on at least one first sum value to obtain a first weighted value, and perform a weighted operation on at least one second sum value to obtain a second weighted value.

[0155] For example, at least one first added value is When , the first weighted value f(score) is calculated as follows:

[0156]

[0157] Among them, β, γ, and δ are weight coefficients respectively, and β, γ, and δ are all greater than or equal to 0 and less than or equal to 1. The values ​​of β, γ, and δ can be determined according to actual conditions, and this embodiment does not impose any limitation on this.

[0158] Similarly, a weighted operation is performed on at least one second sum value to obtain a second weighted value, which is recorded as f'(score). For example, at least one second added value is: The calculation method is as follows:

[0159]

[0160] S204: Add the first weighted value and the second weighted value to obtain a score value corresponding to the item set.

[0161] The score value f(newscore) corresponding to the item set is calculated as follows:

[0162] f(newscore)=f(score)+f'(score) Formula (9)

[0163] Through steps S201-S204, the score value corresponding to each item set can be obtained.

[0164] The product selection method provided in this embodiment includes: according to at least one current feature index corresponding to each item in the item set, adding the current feature indexes of the same category to obtain at least one first sum value, according to at least one historical feature index corresponding to each item in the item set, adding the historical feature indexes of the same category to obtain at least one second sum value, performing a weighted operation on at least one first sum value to obtain a first weighted value, and performing a weighted operation on at least one second sum value to obtain a second weighted value, adding the first weighted value and the second weighted value to obtain a score value corresponding to the item set. This embodiment has the following beneficial effects: the score value corresponding to each item set is obtained by combining the current feature index and the historical feature index, so that the calculation method of the score value corresponding to each item set is more reasonable, so that the first item to be transferred out from the target area can be determined more accurately, so that the items in the target area may exist in the same order, which helps to improve the picking efficiency.

[0165] Based on the above embodiment, it should be noted that, during the item sales process, a second item can be added according to demand, and the second item can be an item or items in other areas. Then, obtaining multiple item sets includes:

[0166] Acquire a second item, where the second item is an item in another area or a new item;

[0167] According to the plurality of first objects and second objects in the target area, a plurality of object sets are obtained.

[0168] The other areas may be any area in the warehouse except the target area. New products refer to newly launched items, which have no current feature data in the current processing cycle and no historical sales data in the historical processing cycle.

[0169] Specifically, if the second object and the multiple first objects in the target area are of different categories, then the multiple first objects and the second objects in the target area are combined to obtain multiple object sets, each of which includes at least one first object.

[0170] If the second item is an item in other areas, the current feature data of the second item in the current processing cycle and the historical sales data in the historical processing cycle can be directly obtained. The specific method is similar to step S102 and will not be repeated here.

[0171] If the second new product is a new product and the item set includes the second item, current feature data of each item in the item set during the current processing cycle is obtained, including: obtaining current feature data of at least one first item during the current processing cycle, and current feature data of the second item during the current processing cycle.

[0172] Correspondingly, obtaining the second characteristic data of the items in the item set within the historical processing cycle includes: obtaining at least one historical characteristic data of the first item within the historical processing cycle, and the historical characteristic data of the second item within the historical processing cycle.

[0173] Since the second item is a new product, it does not have current feature data and historical feature data. Therefore, it is necessary to estimate the current feature data of the second item in the current processing cycle and the historical sales data in the historical processing cycle. For the specific process, please refer to Figure 6 Example.

[0174] Of course, this embodiment only takes one type of second object as an example. In actual applications, the types of second objects that can be moved into the target area include but are not limited to one type.

[0175] It should be noted that when the target item set also includes a second item, it also includes:

[0176] The second object is determined as the object to be transferred into the target area.

[0177] exist Figure 3 On the basis of Figure 5 Schematic diagram of the target area product selection process provided in the embodiment of the present application Figure 2 ,like Figure 5 As shown, the target area includes multiple first items (recorded as set A + set B), and the target item set includes some types of first items (set A), so set B is determined as the first items to be transferred out. Since the target item set also includes second items (set C), set D is the items to be transferred into the target area after selection. That is to say, after implementing this selection plan, set A and set C are stored in the target area.

[0178] In this embodiment, by combining the current feature data and historical feature data of the items for item selection, the items in the target area are adjusted so that the items in the target area are more likely to exist in the same order, which helps to improve picking efficiency.

[0179] Figure 6 Schematic diagram of the process of the product selection method provided in the embodiment of the present application Figure 3 ,like Figure 6 As shown, obtaining the current characteristic data of the second object in the current processing cycle specifically includes:

[0180] S301, acquiring attribute information of a plurality of first objects and attribute information of a plurality of second objects in a target area.

[0181] S302: Standardize the attribute information of the first items and the attribute information of the second items.

[0182] The attribute information includes at least one of unit price, volume, and weight. The volume is the volume of a single item, and the weight is the weight of a single item. Since the second item does not have current feature data and historical feature data when it is a new item, the current feature data of the second item is estimated based on the attribute information of multiple first items and the attribute information of the second items in the target area.

[0183] First, attribute information of a plurality of first objects and attribute information of a second object in a target area is obtained, and then the attribute information of the plurality of first objects and the attribute information of the second object are standardized to eliminate the influence of data dimension.

[0184] In a specific embodiment, the method further comprises:

[0185] Abnormal attribute information from the attribute information of the multiple first items is eliminated.

[0186] Among them, in the case of system abnormality or data statistical abnormality, there may be abnormal attribute information, for example, the unit price is significantly higher than the usual unit price of this type of item, or the volume is significantly larger than the usual volume of this type of item. In this case, the attribute information of the first item is eliminated, and then the attribute information of the second item and the attribute information of the first item after elimination are standardized, thereby improving the accuracy of the current feature data of the second item in the current processing cycle.

[0187] For example, the type of the first item in the target area is n, and the attribute information of the first item includes a unit price a i , volume b i , weight c i , i starts from 1 and goes up to n, the attribute information of the second item includes unit price a, b, c, then the attribute information of multiple first items is standardized to obtain the standardized unit price a' of the first item i , the standardized volume b' i , standardized weight c' i , the process of standardization is shown in formula (10)-formula (12):

[0188]

[0189]

[0190]

[0191] in, Indicates u a is the average of the unit prices of n first and second items;

[0192] represents the standard deviation of the unit prices of n first and second items;

[0193] It is expressed as the average of the volumes of n first items and second items;

[0194] represents the standard deviation of the volumes of n first and second items;

[0195] represents the average weight of n first items and second items; Represents the standard deviation of the weights of n first items and second items.

[0196] Similarly, the attribute information of the second item may be standardized to obtain the standardized unit price a', standardized volume b', and standardized weight c' of the second item:

[0197]

[0198]

[0199]

[0200] S303, using a hierarchical clustering algorithm, according to the standardized attribute information of the first items and the standardized attribute information of the second items, calculate the clustering distance between every two items, and cluster the two items with the smallest clustering distance into one category, repeating this step until the multiple first items and second items are clustered into one category.

[0201] Among them, the hierarchical clustering algorithm is used to calculate the similarity between two types of data points, combine the two most similar data points among all data points, and iterate this process repeatedly. Usually, the Euclidean distance is used to calculate the distance between data points of different categories. The smaller the distance, the higher the similarity.

[0202] For example, data point 1 is represented by x1, y1, z1, and data point 2 is represented by x2, y2, z2. The cluster distance d(1,2) between data point 1 and data point 2 can be calculated using the following formula:

[0203]

[0204] In this embodiment, the standardized unit price a' of the first item can be obtained through steps S201-S202.i , the standardized volume b' i , standardized weight c' i , and the standardized unit price a', standardized volume b', and standardized weight c' of the second item, and then refer to the calculation method of formula (16) to obtain the clustering distance between each two items, and then cluster the two items with the smallest clustering distance into one category. Then, repeat this step until multiple first items and second items are clustered into one category.

[0205] For example, Table 2 is a schematic table of clustering distances. The types of the first items are n=5, represented by A, B, C, D, and E respectively, and the second item is represented by F. As shown in Table 2, the clustering distance between A and A is 0, and the minimum clustering distance between A and B, and between B and A is 1.00, so A and B are clustered into one category to obtain a combined item (A, B).

[0206] A B C D E F A 0 1.00 22.60 63.90 65.10 17.70 B 1.00 0 21.60 42.30 43.50 3.90 C 22.60 21.60 0 41.30 42.50 4.90 D 63.90 42.30 41.30 0 1.20 46.20 E 65.10 43.50 42.50 1.20 0 47.40 F 17.70 3.9 4.90 46.20 47.40 0

[0207] Table 2

[0208] Then, the clustering distance between each two items in the combined items (A, B), C, D, E, and F is calculated. Table 3 is a schematic diagram of the clustering distance. As shown in Table 3, the clustering distance between (A, B) and F is the smallest, so (A, B) and F are aggregated into one category to obtain the combined item (A, B, F).

[0209] (A, B) C D E F (A, B) 0.00 55.65 42.40 77.10 13.50 C 55.65 0.00 90.35 83.73 49.03 D 42.40 90.35 0.00 55.50 60.59 E 77.10 83.73 55.50 0.00 46.10 F 13.50 49.03 60.59 46.10 0.00

[0210] Table 3

[0211] Among them, if the standardized attribute information of the first item A is a'1, b'1, c'1, the standardized attribute information of the first item B is a'2, b'2, c'2, and the standardized attribute information of the second item F is a', b', c', then the calculation method of the cluster distance between the combined items (A, B) and F can be:

[0212]

[0213] Next, repeat this step until the plurality of first objects (A, B, C, D, E) and second objects (F) are grouped into one category.

[0214] S304: Obtain the minimum value of the minimum clustering distance in the clustering process, and determine the item category corresponding to the minimum value.

[0215] In the clustering process of step S3021, each clustering corresponds to a minimum clustering distance, then the minimum value of the minimum clustering distance in the above clustering process is obtained, and the item category corresponding to the minimum value is determined, that is, the items are divided into multiple item categories according to the minimum value. For example, in the above clustering process, the clustering distance between the item combination (A, B, D) and F is the minimum value of the minimum clustering distance, and the item category corresponding to the minimum value includes 2 categories, namely, the item combination (A, B, D, F) and (C, E). Table 4 is a schematic diagram of the clustering distance. Figure 3 ,As shown in Table 4, the clustering distance between the item combination (A, B, D) and F is the smallest, so (A, B, D) and F are aggregated into one category to obtain the combination item (A, B, D, F).

[0216] (A, B, D) (C, E) F (A, B, D) 0.00 55.65 0.50 (C, E) 55.65 0.00 25.20 F 0.50 25.20 0.00

[0217] Table 4

[0218] S305: Determine the category of the second item from the item categories.

[0219] S306. Obtain current feature data of the second object according to the current feature data of each first object in the category to which the second object belongs.

[0220] Referring to the above example, the category of the second item F includes three first items (A, B, D), then the average value of the current feature data of the three first items (A, B, D) can be used as the current feature data of the second item F.

[0221] For example, the current feature data of A includes the average picking time in the past 7 days. Average order volume And the average number of orders B's current feature data includes the average picking time in the past 7 days Average order volume And the average number of orders D's current feature data includes the average picking time in the past 7 days Average order volume And the average number of orders The current feature data of the second item F includes the average picking time in the past 7 days. Average order volume Average number of orders

[0222] Of course, the quantile or median of the current feature data of each first item in the category to which the second item belongs may also be used as the current feature data of the second item, and this embodiment does not impose any limitation on this.

[0223] Accordingly, historical feature data of the second item in the historical processing cycle is obtained, including:

[0224] The historical feature data of the second object is obtained according to the historical feature data of each first object in the category where the second object belongs.

[0225] The average value of the historical feature data of each first object in the category to which the second object belongs can be determined as the process of obtaining the current feature data of the second object. The specific process is similar to the process of obtaining the current feature data of the second object and will not be repeated here.

[0226] The product selection method provided in this embodiment includes: obtaining attribute information of multiple first items and attribute information of second items in the target area, the attribute information including at least one of unit price, volume, and weight, standardizing the attribute information of the multiple first items and the attribute information of the second items, using a hierarchical clustering algorithm, calculating the clustering distance between every two items based on the standardized attribute information of the multiple first items and the standardized attribute information of the second items, and clustering the two items with the smallest clustering distance into one category, repeating this step until the multiple first items and the second items are clustered into one category, obtaining the minimum value of the smallest clustering distance in the clustering process, determining the item category corresponding to the minimum value, determining the category of the second item from the item category, and obtaining the current feature data of the second item based on the current feature data of each first item in the category of the second item. This embodiment has the following beneficial effects: the second items are clustered according to the attribute information, and then the current feature data of each first item in the category of the second item is used to obtain the current feature data of the second item. This method makes the calculation of the current feature data of the second item more reasonable, improves the accuracy of the current feature data of the second item, and further makes the score value corresponding to each item set more accurate, which helps to select the target item set, thereby improving the picking efficiency.

[0227] Figure 7 This is a schematic diagram of the structure of a product selection device provided in an embodiment of the present application. The product selection device is integrated in a terminal device and can be implemented by hardware and / or software. Figure 7 As shown, the product selection device 400 includes:

[0228] An acquisition module 401 is used to acquire multiple item sets, each item set includes at least one first item in a target area, and the target area includes multiple first items;

[0229] For each set of items, obtaining current feature data of each item in the set of items in a current processing cycle and historical feature data in a historical processing cycle, wherein the current feature data and the historical feature data respectively include at least one of an average picking time, an average order quantity, and an average number of items in an order;

[0230] A processing module 402 is used to calculate a score value corresponding to the item set according to the current feature data and the historical feature data, wherein the score value is used to indicate the probability that the items in the item set exist in the same order;

[0231] Determining a target item set from the multiple item sets according to the score values, wherein the score value corresponding to the target item set is greater than a preset value;

[0232] A first object to be retrieved from the target area is determined according to the target object set.

[0233] In a specific implementation, the current processing cycle includes at least two current processing time periods, and the current feature data includes feature data corresponding to the at least two current processing time periods; the historical processing cycle includes at least two historical processing time periods, and the historical feature data includes feature data corresponding to the at least two historical processing time periods;

[0234] The processing module 402 is specifically used for:

[0235] Performing a weighted operation on the same type of data in the current feature data to obtain at least one current feature index corresponding to the item;

[0236] Performing a weighted operation on the same type of data in the historical feature data to obtain at least one historical feature indicator corresponding to the item;

[0237] According to at least one current characteristic indicator and at least one historical characteristic indicator corresponding to each item in the item set, a score value corresponding to the item set is obtained.

[0238] In a specific implementation, the processing module 402 is specifically used to:

[0239] According to at least one current feature indicator corresponding to each item in the item set, current feature indicators of the same category are added together to obtain at least one first sum value;

[0240] According to at least one historical characteristic indicator corresponding to each item in the item set, historical characteristic indicators of the same category are added together to obtain at least one second sum value;

[0241] Performing a weighted operation on the at least one first sum value to obtain a first weighted value, and performing a weighted operation on the at least one second sum value to obtain a second weighted value;

[0242] The first weighted value and the second weighted value are added to obtain a score value corresponding to the item set.

[0243] In a specific implementation, the acquisition module 401 is specifically used to:

[0244] Acquire a second item, where the second item is an item in another area or a new item;

[0245] The plurality of sets of objects are acquired according to the plurality of first objects and the second objects in the target area.

[0246] In a specific implementation, if the target item set also includes a second item, the processing module is further configured to:

[0247] The second object is determined as the object to be transferred into the target area.

[0248] In a specific implementation, if the second item is a new item and the item set also includes the second item, the acquisition module 401 is specifically configured to:

[0249] Acquire current feature data of the at least one first object in a current processing cycle, and current feature data of the second object in a current processing cycle;

[0250] Acquire historical feature data of the at least one first item within a historical processing cycle, and historical feature data of the second item within a historical processing cycle.

[0251] In a specific implementation, the acquisition module 401 is specifically used to:

[0252] Acquire attribute information of a plurality of first items and attribute information of the second items in the target area, wherein the attribute information includes at least one of unit price, volume, and weight;

[0253] Standardizing the attribute information of the plurality of first items and the attribute information of the second item;

[0254] Using a hierarchical clustering algorithm, according to the standardized attribute information of the plurality of first items and the standardized attribute information of the second items, the cluster distance between each two items is calculated, and the two items with the smallest cluster distance are clustered into one category, and this step is repeated until the plurality of first items and the second items are clustered into one category;

[0255] Obtaining the minimum value of the minimum clustering distance in the clustering process, and determining the item category corresponding to the minimum value;

[0256] determining the category of the second item from among the item categories;

[0257] The current feature data of the second object is obtained according to the current feature data of each first object in the category where the second object belongs.

[0258] In a specific implementation, the acquisition module 401 is further used to:

[0259] The historical feature data of the second object is acquired according to the historical feature data of each first object in the category to which the second object belongs.

[0260] In a specific implementation, the processing module 402 is further used to:

[0261] Abnormal attribute information from the attribute information of the plurality of first items is eliminated.

[0262] In a specific implementation, the score value corresponding to the target item set is the maximum value among the score values ​​corresponding to the multiple item sets.

[0263] The product selection device of this embodiment can be used to execute the technical solutions executed by the terminal equipment in the above-mentioned method embodiments. Its implementation principles and technical effects are similar and will not be repeated here.

[0264] Figure 8 A schematic diagram of the hardware structure of the terminal device provided in the embodiment of the present application is shown in FIG. Figure 8 As shown, the terminal device 500 of this embodiment includes:

[0265] Processor 501, interface 502 for communicating with other electronic devices, and memory 503;

[0266] The memory 503 stores computer-executable instructions;

[0267] The processor 501 executes the computer-executable instructions stored in the memory, so that the processor executes the product selection method provided by any of the aforementioned embodiments.

[0268] The communication interface may be an input / output (I / O) interface.

[0269] Optionally, the terminal device further includes a bus 504 for connecting the memory 503 and the processor 501 .

[0270] An embodiment of the present invention further provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the product selection method as described above is implemented.

[0271] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0272] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0273] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each module may exist physically separately, or two or more modules may be integrated into one unit. The above-mentioned module-composed unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0274] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present application.

[0275] It should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0276] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0277] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0278] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0279] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0280] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0281] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A product selection method, characterized in that: include: Acquire multiple item sets, each item set includes at least one first item in a target area, and the target area includes multiple first items; wherein the multiple item sets are obtained by randomly combining all the first items in the target area; For each set of items, obtain current feature data of each item in the set of items in a current processing cycle and historical feature data in a historical processing cycle; wherein the current feature data and historical feature data respectively include at least one of an average picking time, an average order quantity, and an average number of items in an order; wherein the current feature data is recent historical operation data, and the historical feature data is historical operation data before the warehouse is established; Calculate a score value corresponding to the item set according to the current feature data and the historical feature data, where the score value is used to indicate the probability that the items in the item set exist in the same order; Determining a target item set from the multiple item sets according to the score values, wherein the score value corresponding to the target item set is greater than a preset value; A first object to be retrieved from the target area is determined according to the target object set.

2. The method according to claim 1, characterized in that The current processing cycle includes at least two current processing periods, and the current feature data includes feature data corresponding to the at least two current processing periods respectively; the historical processing cycle includes at least two historical processing periods, and the historical feature data includes feature data corresponding to the at least two historical processing periods respectively; The calculating, according to the current feature data and the historical feature data, a score value corresponding to the item set includes: Performing a weighted operation on the same type of data in the current feature data to obtain at least one current feature index corresponding to the item; Performing a weighted operation on the same type of data in the historical feature data to obtain at least one historical feature indicator corresponding to the item; According to at least one current characteristic indicator and at least one historical characteristic indicator corresponding to each item in the item set, a score value corresponding to the item set is obtained.

3. The method according to claim 2, characterized in that The obtaining, according to at least one current characteristic indicator and at least one historical characteristic indicator corresponding to each item in the item set, a score value corresponding to the item set includes: According to at least one current feature indicator corresponding to each item in the item set, current feature indicators of the same category are added together to obtain at least one first sum value; According to at least one historical characteristic indicator corresponding to each item in the item set, historical characteristic indicators of the same category are added together to obtain at least one second sum value; Performing a weighted operation on the at least one first sum value to obtain a first weighted value, and performing a weighted operation on the at least one second sum value to obtain a second weighted value; The first weighted value and the second weighted value are added to obtain a score value corresponding to the item set.

4. The method according to claim 1, characterized in that: The obtaining of multiple item sets includes: Acquire a second item, where the second item is an item in another area or a new item; The plurality of sets of objects are acquired according to the plurality of first objects and the second objects in the target area.

5. The method according to claim 4, characterized in that If the target item set also includes a second item, the method further includes: The second object is determined as the object to be transferred into the target area.

6. The method according to claim 4, characterized in that If the second item is a new item, and the item set also includes the second item, the step of obtaining current feature data of each item in the item set in the current processing cycle includes: Acquire current feature data of the at least one first object in a current processing cycle, and current feature data of the second object in a current processing cycle; Accordingly, the step of obtaining the second characteristic data of the items in the item set within the historical processing cycle includes: Acquire historical feature data of the at least one first item within a historical processing cycle, and historical feature data of the second item within a historical processing cycle.

7. The method according to claim 6, characterized in that The obtaining of current characteristic data of the second object in the current processing cycle includes: Acquire attribute information of a plurality of first items and attribute information of the second items in the target area, wherein the attribute information includes at least one of unit price, volume, and weight; Standardizing the attribute information of the plurality of first items and the attribute information of the second item; Using a hierarchical clustering algorithm, according to the standardized attribute information of the plurality of first items and the standardized attribute information of the second items, the cluster distance between each two items is calculated, and the two items with the smallest cluster distance are clustered into one category, and this step is repeated until the plurality of first items and the second items are clustered into one category; Obtaining the minimum value of the minimum clustering distance in the clustering process, and determining the item category corresponding to the minimum value; determining the category of the second item from among the item categories; The current feature data of the second object is obtained according to the current feature data of each first object in the category to which the second object belongs.

8. The method according to claim 7, characterized in that The acquiring of historical characteristic data of the second object in a historical processing cycle includes: The historical feature data of the second object is acquired according to the historical feature data of each first object in the category to which the second object belongs.

9. The method according to claim 7, characterized in that: The method further comprises: Abnormal attribute information from the attribute information of the plurality of first items is eliminated.

10. The method according to any one of claims 1 to 9, characterized in that: The score value corresponding to the target item set is the maximum value among the score values ​​corresponding to the multiple item sets.

11. A product selection device, characterized in that: include: an acquisition module, configured to acquire a plurality of item sets, each item set including at least one first item in a target area, and the target area including a plurality of first items; wherein the plurality of item sets are obtained by randomly combining all the first items in the target area; For each set of items, obtain current feature data of each item in the set of items in a current processing cycle and historical feature data in a historical processing cycle; wherein the current feature data and the historical feature data respectively include at least one of an average picking time, an average order quantity, and an average number of items in an order; wherein the current feature data is recent historical operation data, and the historical feature data is historical operation data before the warehouse is established; a processing module, configured to calculate a score value corresponding to the item set according to the current feature data and the historical feature data, wherein the score value is used to indicate a probability that items in the item set exist in the same order; Determining a target item set from the multiple item sets according to the score values, wherein the score value corresponding to the target item set is greater than a preset value; A first object to be retrieved from the target area is determined according to the target object set.

12. A terminal device, characterized in that: include: Processor, memory, and interfaces for communicating with other electronic devices; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the product selection method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the product selection method as described in any one of claims 1 to 10.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the product selection method according to any one of claims 1 to 10 is implemented.

Images