Disclosure of Invention
In view of the foregoing, it is an object of the present disclosure to provide a method, an apparatus, a logistics system and a storage medium for determining a storage location of an article.
According to one aspect of the present disclosure, there is provided an article storage location determining method including: obtaining single article ordering probability information of each article to be stored; generating at least two goods shelf object placing combinations corresponding to various objects to be stored; acquiring concurrency picking probability information and shelf use probability information of shelf object placement combination based on the order probability information of the single product; and selecting one goods shelf object placing combination from the at least two goods shelf object placing combinations according to the concurrent goods picking probability information and the goods shelf use probability information, so as to determine the storage positions of the various goods.
Optionally, the selecting one of the at least two shelf article placement combinations according to the concurrent picking probability information and the shelf usage probability information includes: acquiring a picking concurrency index of a goods shelf object placing combination according to the concurrency picking probability information and the goods shelf use probability information; sorting all the goods shelf object placing combinations according to the goods picking concurrency indexes of all the goods shelf object placing combinations; and selecting one goods shelf object placing combination from the at least two goods shelf object placing combinations according to the sorting result.
Optionally, the generating at least two shelf-item placement combinations corresponding to the plurality of items to be stored includes: acquiring the information of the number of goods shelves; determining a plurality of placing shelves for placing the plurality of articles based on the bin quantity information and the category quantity of the plurality of articles; generating the at least two shelf object placing combinations for placing the plurality of objects through the plurality of placing shelves.
Optionally, the acquiring the concurrent picking probability information and the shelf usage probability information of the shelf item placement combination based on the item order probability information includes: obtaining a corresponding relation between a shelf and a set of shelf-placed articles in the shelf-placed article combination; and acquiring the concurrency picking probability of the goods shelf placing object set and the use probability of a placing shelf for placing the goods shelf placing object set according to the corresponding relation and based on the single goods ordering probability information.
Optionally, the goods shelf placing object set has the concurrency picking probability ofThe use probability of the placing shelf is +.>Wherein k is the number of article types in the article set placed on the shelf, and p i Placing a single item ordering probability of an ith item in the item set for the goods shelf; m is the number of the article types of the article set placed on the shelf and p j And placing the single article ordering probability of the j-th article in the article set for the goods shelf placed by the placing goods shelf.
Optionally, the acquiring the picking concurrency index of the goods shelf combination according to the concurrency probability information and the goods shelf use probability information includes: taking the product of the concurrency picking probability of the goods shelf placing object set and the use probability of the placing goods shelf placing object set as the use concurrency index of the goods shelf placing object set; and acquiring the picking concurrency index of the goods shelf object placing combination according to the using concurrency index of the goods shelf object placing set.
Optionally, the goods-picking concurrency index of the goods shelf object placement combination isWherein N is the goods shelf in the goods shelf combinationNumber of collections, P cl The probability of picking the first goods in the goods shelf set, P tl The probability of use of the shelf for placing the first set of shelf items.
Optionally, sorting the at least two shelf item placement combinations in order of the pick concurrency index from big to small; and selecting the goods shelf object placing combination arranged at the forefront, and determining the storage positions of the goods based on the corresponding relation between the placing shelf and the goods shelf object placing set in the goods shelf object placing combination.
Optionally, the distance between the placing shelf and the shipment of the set of shelf-placed items is set based on the usage concurrency index of the set of shelf-placed items in the selected set of shelf-placed items.
According to still another aspect of the present disclosure, there is provided an article storage position determining apparatus including: the order probability obtaining module is used for obtaining the order probability information of the single article of each article to be stored; the storage combination generating module is used for generating at least two storage rack article storage combinations corresponding to various articles to be stored; the concurrency information obtaining module is used for obtaining concurrency picking probability information and shelf use probability information of the shelf object placement combination based on the single product ordering probability information; the placing position selecting module is used for selecting one goods shelf article placing combination from the at least two goods shelf article placing combinations according to the concurrent picking probability information and the goods shelf use probability information, and determining the storage positions of the various goods.
According to still another aspect of the present disclosure, there is provided an article storage position determining apparatus including: a memory; and a processor coupled to the memory, the processor configured to perform the method as described above based on instructions stored in the memory.
According to yet another aspect of the present disclosure, there is provided a logistics system comprising: the article storage position determining apparatus as described above.
According to yet another aspect of the present disclosure, there is provided a computer-readable storage medium storing computer instructions for execution by a processor to perform the method as described above.
According to the method, the device, the logistics system and the storage medium for determining the storage positions of the articles, the loading positions of the articles in the warehouse can be determined according to the heat sales factors of the articles without dependence, the warehouses without dependence on the articles can be subjected to loading position determination, the articles are combined based on the heat sales and placed on different shelves, and the shelves for placing the articles with high heat sales can be placed at the positions close to the shipment positions, so that as many orders as possible can be met through one-time shelf transport during picking, the article delivery efficiency is improved, the working efficiency is improved, and the cost is reduced.
Detailed Description
The present disclosure now will be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments of the disclosure are shown. The following description of the technical solutions in the embodiments of the present disclosure will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, not all embodiments. Based on the embodiments in this disclosure, all other embodiments that a person of ordinary skill in the art would obtain without making any inventive effort are within the scope of protection of this disclosure. The technical solutions of the present disclosure are described in various aspects below with reference to the drawings and the embodiments.
FIG. 1 is a flow chart diagram of one embodiment of a method of determining a storage location for an item according to the present disclosure, as shown in FIG. 1:
step 101, obtaining single article ordering probability information of each article to be stored.
The articles to be stored can be various commodities, and the articles need to be stored on a goods shelf in a warehouse, and the warehouse can be an unmanned warehouse. The goods shelves can be various existing goods shelves, and the goods shelves can be transported by AGV trolleys and the like. Probability of ordering an item for a single item for that item on the day, week, month, etc., the probability of ordering an item may be obtained in a variety of ways.
Step 102, generating at least two shelf object placement combinations corresponding to various objects to be stored.
The goods shelf object placing combination is an object combination for placing objects to be stored on a goods shelf in a warehouse. For example, there are A, B, C, D items to be stored, there are E, F two shelves, and the shelf item placement combination may be placing a and B items on shelf E, and placing C and D items on shelf F; alternatively, the shelf goods placement combination may be that goods a and C are placed on shelf E, goods B and D are placed on shelf F, or the like.
And step 103, acquiring the concurrency picking probability information and the shelf use probability information of the shelf object placement combination based on the single object ordering probability information.
The concurrent picking probability information is probability information of simultaneously picking (discharging) a plurality of articles placed on the same shelf. For example, a shelf item placement combination includes placing items A and B on shelf E, and placing items C and D on shelf F; the concurrent picking probability information of the goods shelf object placement combination comprises: probability information of simultaneous picking (shipment) of the A and B items, and probability information of simultaneous picking (shipment) of the C and D items; the goods shelf use probability information of the goods shelf article placing combination comprises: usage information of the shelf E and usage information of the shelf F.
And 104, selecting one goods shelf object placing combination from at least two goods shelf object placing combinations according to the concurrent goods picking probability information and the goods shelf use probability information, and determining storage positions of various goods.
Items may be placed on shelves based on the selected shelf item placement combination, e.g., items a and B on shelf E, and items C and D on shelf F based on the selected shelf item placement combination.
FIG. 2 is a flow chart of selecting a shelf item placement combination in one embodiment of an item storage location determination method according to the present disclosure, as shown in FIG. 2:
step 201, acquiring the picking concurrency index of the goods shelf object placing combination according to the concurrency picking probability information and the goods shelf use probability information. The pick concurrency index is used to characterize the effect of simultaneously picking (shipping) items in a shelf item placement combination.
Step 202, sorting the goods shelf object placing combinations according to the goods picking concurrency index of the goods shelf object placing combinations.
Step 203, selecting one goods shelf object placing combination from at least two goods shelf object placing combinations according to the sorting result.
There are various ways to generate a shelf item placement combination corresponding to the various items to be stored. For example, the number of goods shelves is obtained, one goods shelf can hold one kind of article, and a plurality of placing shelves for placing a plurality of kinds of articles are determined based on the number of goods shelves and the kinds of the plurality of kinds of articles. At least two goods shelf object placing combinations for placing various objects through a plurality of goods shelf are generated, and all possible goods shelf object placing combinations can be generated by adopting the existing various methods.
There may be multiple sorting methods for sorting the placement combinations of the shelf items according to the order picking concurrency index. For example, the at least two goods shelf object placing combinations are ordered according to the order of the goods picking concurrency index from big to small, the goods shelf object placing combination arranged at the front is selected, and determining storage positions of the articles based on the corresponding relation between the shelf and the shelf storage article set in the shelf article storage combination.
FIG. 3 is a schematic diagram of obtaining a pick concurrency index in one embodiment of an item storage location determination method according to the present disclosure, as shown in FIG. 3:
step 301, obtaining a corresponding relationship between a shelf and a set of shelf-placed items in the shelf-placed item combination.
Step 302, obtaining the concurrency picking probability of the goods shelf placing object set and the use probability of the placing shelf for placing the goods shelf placing object set according to the corresponding relation and based on the single-product ordering probability information.
The concurrent picking probability of the goods set placed on the goods shelf can beThe use probability of the shelf can be +.>Wherein k is the number of article types in the article set placed on the shelf, and p i Placing a single item ordering probability of an ith item in the item set for the shelf; m is the number of article types of a goods shelf placing article set placed on a placing shelf, p j And placing the single article ordering probability of the j-th article in the article set for the goods shelf placed on the goods shelf.
For example, the number of the goods shelves in the warehouse is two, and the number of the types of the articles to be stored is six, namely, the number of the various articles to be stored is six. The delivery place of the warehouse is a workstation, and the workstation is one. The probability of ordering the daily unit for six items to be stored is shown in table 1 below:
article numbering
|
Probability of daily ordering
|
Sku1
|
0.9
|
Sku2
|
0.9
|
Sku3
|
0.5
|
Sku4
|
0.5
|
Sku5
|
0.1
|
Sku6
|
0.1 |
TABLE 1 probability Table for ordering daily articles
Six articles to be stored are 6 commodities in total, namely, sku1, sku2, sku3, … … and sku6, wherein P (sku 1) is the single-article ordering probability of sku1 (probability of picking and delivering), P (sku 2) is the single-article ordering probability … … P (sku 6) of sku2 and is the single-article ordering probability of sku 6; if only two kinds of goods can be placed on one goods shelf, there areAnd placing the article set on the goods shelf. For example, three shelf item placement combinations are generated:
goods shelf article placing and combining: three shelf-holding item sets, sku1 and sku2, sku3 and sku4, sku5 and sku6, are placed on three shelves 1, 2, 3, respectively. The probability of the occurrence of the goods collection and the picking of goods placed on the goods shelf is as follows:
after the shelf 1 is taken out of the warehouse and used by the workstation, the probability of concurrent picking of the shelf placing object sets sku1 and sku2 is as follows: p1 concurrency=p (sku 1 n sku 2) =p (sku 1) ×p (sku 2) =0.81;
after the shelf 2 is taken out of the warehouse and used by the workstation, the probability of concurrent picking of the shelf placing article sets sku3 and sku4 is as follows: p2 concurrency=p (sku3 n sku 4) =p (sku 3) P (sku 4) =0.25;
after shelf 3 is taken out of the warehouse and used by the workstation, the shelf puts the concurrent pick probabilities of item sets sku5 and sku 6: p3 concurrency=p (sku 5 n sku 6) =p (sku 5) P (sku 6) =0.01.
The probability of use of the three shelves 1, 2, 3 by the workstation is as follows:
the probability of use that the shelf 1 is used in operation is: p1 is used=p (sku 1 u-sku 2) =1- ((1-P (sku 1)) (1-P (sku 2))) =0.99;
the probability of use that the shelf 2 is used in operation is: p2 is used=p (sku3 u sku 4) =0.75;
the probability of use that the shelf 2 is used in operation is: p3 is used=p (sku 5 u-sku 6) =0.19.
Step 303, taking the product of the concurrency picking probability of the goods shelf placing object set and the use probability of the placing goods shelf placing the goods shelf placing object set as the use concurrency index of the goods shelf placing object set.
Step 304, acquiring the picking concurrency index of the goods shelf object placing combination according to the using concurrency index of the goods shelf object placing set.
The goods-picking concurrency index of the goods shelf object placing combination can beWherein N is the number of goods shelf placing article sets in the goods shelf article placing combination, and P cl Probability of picking concurrently for the first set of shelf items in the shelf item placement combination, P tl The probability of use of the shelf for placing the first set of shelf items.
For example, three sets of shelf items in a shelf item placement group are sku1 and sku2, sku3 and sku4, sku5 and sku6.
The usage concurrency index for the set of shelf-items sku1 and sku2 is: p1 use concurrency = P1 use P1 concurrency = 0.99 x 0.81 = 0.80;
the usage concurrency index for the set of shelf-items sku3 and sku4 is: p2 use concurrency = P2 use P2 concurrency = 0.75 x 0.25 = 0.19;
the usage concurrency index for the set of shelf-items sku5 and sku6 is: p3 use concurrency = P3 use P3 concurrency = 0.19 x 0.01 = 0.02.
Then the shelf item placement combines a pick concurrency index (characterizing concurrency effects) e1=0.80+0.19+0.02=1.01.
The three shelf placement item sets of the shelf placement combination two are sku1 and sku5, sku2 and sku6, sku3 and sku4. The method is as follows:
the usage concurrency index for the set of shelf-items sku1 and sku5 is: p1 uses concurrency = 0.91 x 0.09 = 0.08;
the usage concurrency index for the set of shelf-items sku2 and sku6 is: p2 use concurrency = 0.75 x 0.25 = 0.19;
the usage concurrency index for the set of shelf-items sku3 and sku4 is: p3 uses concurrency = 0.91 x 0.09 = 0.08;
then the pick concurrency index e2=0.35 for shelf item placement combination two.
The three shelf placement item sets of shelf item placement combination three are sku1 and sku3, sku4 and sku5, sku2 and sku6. The method is as follows:
the usage concurrency index for the set of shelf-placed items sku1 and sku3 is: p1 use concurrency=0.95×0.45=0.43;
the usage concurrency index for the set of shelf-items sku4 and sku5 is: p2 using concurrency = 0.55 x 0.05 = 0.03;
the usage concurrency index for the set of shelf-items sku2 and sku6 is: p3 using concurrency = 0.91 x 0.45 = 0.41;
then the pick concurrency index e3=0.87 for shelf item placement combination three.
In the storage position determination, one shelf arrives at the workstation (the shelf can be moved) 1 time to satisfy as many orders as possible, and the overall delivery efficiency is considered to be high. From the above, if E1> E3> E2, the first set of shelf items is selected, and the storage position of the items is determined based on the correspondence between the shelf and the set of shelf items in the first set of shelf items, that is, three sets of shelf items, sku1 and sku2, sku3 and sku4, sku5 and sku6, of the first set of shelf items are respectively placed in the three shelves.
In one embodiment, the distance between the placement shelf where the set of shelf items is placed and the shipment is set based on the usage concurrency index of the set of shelf items in the selected set of shelf items.
For example, the selected shelf object placement combinations are one of shelf object placement combinations, and the usage concurrency index of the shelf object placement sets sku1 and sku2 is: p1 use concurrency = 0.80; the usage concurrency index for the set of shelf-items sku3 and sku4 is: p2 use concurrency = 0.19; the usage concurrency index for the set of shelf-items sku5 and sku6 is: p3 use concurrency = 0.02.
The distance between the placing shelf 1 and the shipment place (workstation) of the placing shelf placing article sets sku1 and sku2 can be set to be shortest, and the distance between the placing shelf 3 and the shipment place of the placing shelf placing article sets sku5 and sku6 can be set to be longest, so that the shelf placing the shelf article placing combination using the concurrency index high is set at a place close to the shipment place (workstation).
FIG. 4 is a schematic diagram of obtaining order probability information for a single item in one embodiment of a method of determining a storage location for an item according to the present disclosure, as shown in FIG. 4:
step 401, obtaining shopping data and purchase influence factor information; wherein the shopping data includes the number, kind, etc. of the purchased items; the purchase influencing factor information includes: season, holiday, weather, user age characteristics, user occupation, region, etc.
Step 402, obtaining a single item ordering probability of each item according to shopping data.
Various methods may be used to calculate the order probability for a single item. For example, the total number of items purchased on a certain day is obtained, the total number of items a purchased on the same day is obtained, and the quotient of the total number of items a purchased and the total number of items purchased is taken as the probability of ordering a single item on a certain day.
And step 403, training by using the single product order probability and the purchase influence factor information as training data and utilizing the training data to obtain an order probability model.
Step 404, inputting the purchase influencing factor information into the order probability model to obtain the order probability information of the single article corresponding to each article to be stored.
For example, an order probability model is established, and the order probability model may be a neural network model, and the neural network model may be various, for example CNN, RNN, RNTN, GAN. The method comprises the steps of obtaining single product ordering probability and purchase influence factor information as training data, generating historical influence factor vectors by using the purchase influence factor information such as seasons, holidays, weather, user ages, user professions, regions and the like, using the historical influence factor vectors and single product ordering probability (the historical ordering probability in days, weeks, months and the like) as training data, and training by using a machine learning algorithm to obtain an ordering probability model. The current influencing factor vector is input into a trained order probability model for outputting the order probability of the single product.
In one embodiment, the present disclosure provides an article storage location determining device 50 comprising: the system comprises an order probability obtaining module 51, a placement combination generating module 52, a concurrent information obtaining module 53 and a placement position selecting module 54.
Order probability obtaining module 51 obtains individual order probability information for each item to be stored. The placement composition generation module 52 generates at least two shelf item placement compositions corresponding to the plurality of items to be stored. The concurrency information obtaining module 53 obtains concurrency pick probability information and shelf use probability information of the shelf item placement combination based on the individual item order probability information. The placement location selection module 54 selects one shelf item placement combination from the at least two shelf item placement combinations based on the concurrent pick probability information and the shelf use probability information for determining a storage location of the plurality of items.
As shown in fig. 6, the placement position selection module 54 includes: the concurrent effect obtaining unit 541, the placement combination selecting unit 542, and the shelf position setting unit 543. The concurrency effect obtaining unit 541 obtains a picking concurrency index of the shelf item placement combination according to the concurrency picking probability information and the shelf use probability information. The placement combination selecting unit 542 sorts the placement combinations of the shelf items according to the order picking concurrency index of the placement combinations of the shelf items, and selects one placement combination of the shelf items from at least two placement combinations of the shelf items according to the sorting result.
The placement composition generation module 52 obtains the bin number information of the racks, and determines a plurality of placement racks for placing the plurality of items based on the bin number information and the sort number of the plurality of items. The placement composition generation module 52 generates at least two shelf item placement compositions for placing a plurality of items through a plurality of placement shelves.
In one embodiment, the concurrency information obtaining module 53 obtains a correspondence of a put shelf in the shelf item put combination to a set of shelf put items. The concurrency information obtaining module 53 obtains the concurrency picking probability of the goods shelf placing object set and the use probability of the placing shelf for placing the goods shelf placing object set according to the corresponding relation and based on the single-product ordering probability information.
The concurrent picking probability of the goods set placed on the goods shelf isThe probability of use of the shelf is thatWherein k is the number of article types in the article set placed on the shelf, and p i Placing a single item ordering probability of an ith item in the item set for the shelf; m is the number of article types of a goods shelf placing article set placed on a placing shelf, p j And placing the single article ordering probability of the j-th article in the article set for the goods shelf placed on the goods shelf.
The concurrency effect obtaining unit 541 uses, as the concurrency index of use of the set of shelf items, a product of the concurrency pick probability of the set of shelf items and the use probability of the shelf for placing the set of shelf items. The concurrency effect obtaining unit 541 obtains a picking concurrency index of the shelf item placement combination according to the use concurrency index of the shelf item placement set.
The goods-picking concurrency index of the goods shelf object placing combination isWherein N is the number of goods shelf placing article sets in the goods shelf article placing combination, and P cl Probability of picking concurrently for the first set of shelf items in the shelf item placement combination, P tl The probability of use of the shelf for placing the first set of shelf items.
The placement combination selection unit 542 follows the order picking concurrency index is from big to small at least two shelf item placement combinations are ordered in the order of (1). The placement combination selection unit 542 selects the shelf item placement combination that is placed at the forefront, and determines the storage positions of the plurality of items based on the correspondence between the placement shelves and the set of shelf placement items in the shelf item placement combination.
The shelf position setting unit 543 sets a distance between a placing shelf where the set of shelf items is placed and a shipment place based on a use concurrency index of the set of shelf items in the selected set of shelf items.
In one embodiment, order probability obtaining module 51 obtains shopping data and purchase influencing factor information; wherein the shopping data includes the number, kind, etc. of the purchased items. Order probability obtaining module 51 obtains a single item order probability for each item from the shopping data. Order probability obtaining module 51 uses the individual order probability and the purchase influence factor information as training data, and trains the individual order probability and the purchase influence factor information by using the training data to obtain an order probability model. Order probability obtaining module 51 inputs the current purchase influence factor information into order probability model to obtain individual order probability information corresponding to each item to be stored.
Fig. 7 is a block diagram of another embodiment of an item storage position determining system according to the present disclosure. As shown in fig. 7, the apparatus may include a memory 71, a processor 72, a communication interface 73, and a bus 74. The memory 71 is for storing instructions, and the processor 72 is coupled to the memory 71, the processor 72 being configured to perform the article storage location determining method described above based on the instructions stored by the memory 71.
The memory 71 may be a high-speed RAM memory, a nonvolatile memory (non-volatile memory), or the like, and the memory 71 may be a memory array. The memory 71 may also be partitioned and the blocks may be combined into virtual volumes according to certain rules. The processor 72 may be a central processing unit CPU, or an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the article storage location determination methods of the present disclosure.
In one embodiment, the present disclosure provides a logistics system comprising an item storage location determining apparatus as in any one of the embodiments above.
In one embodiment, the present disclosure provides a computer readable storage medium storing computer instructions that when executed by a processor implement the article storage location determination method of any of the embodiments above.
The method, the device, the logistics system and the storage medium for determining the storage position of the goods in the embodiment acquire the concurrent picking probability information and the goods shelf use probability information of the goods shelf object placing combination based on the single-object ordering probability information of the goods, select the goods shelf object placing combination according to the concurrent picking probability information and the goods shelf use probability information and determine the storage position; the method has the advantages that the loading position of the articles in the warehouse can be determined according to the heat sales factors of the articles without dependence on the relevance of the articles, the warehouse without relevance of the articles can be subjected to loading position determination, the articles are combined based on the heat sales and placed on different shelves, and the shelves for placing the articles with high heat sales can be placed at the position close to the shipment position, so that as many orders as possible can be met through one-time shelf transport during picking, the article shipment efficiency is improved, the working efficiency is improved, the cost is reduced, and the use sensitivity of users is improved.
The methods and systems of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, firmware. The above-described sequence of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the sequence specifically described above unless specifically stated otherwise. Furthermore, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
The description of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the disclosure in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments were chosen and described in order to best explain the principles of the disclosure and the practical application, and to enable others of ordinary skill in the art to understand the disclosure for various embodiments with various modifications as are suited to the particular use contemplated.