Recommendation method and device for target storage positions of goods on shelf

Abstract

The invention discloses a recommendation method and device for target storage positions of goods on shelves, and relates to the technical field of smart industry. The specific implementation mode of the method comprises the steps that a shelving task is received; according to the article identifier and the to-be-shelved person identifier, matching a historical operation record of the to-be-shelved article from an article database; calculating recommendation values of historical storage positions corresponding to the historical storage position identifiers by utilizing the matched historical storage position identifiers, the historical shelf times and the historical shelf personnel identifiers, and sorting the recommendation values of the historical storage positions according to a sequence from large to small; and recommending the historical storage positions corresponding to the top N recommendation values as target storage positions to terminals corresponding to the to-be-racked personnel identifiers. According to the embodiment, the historical data can be extracted for asynchronous analysis, the nearest storage position most convenient to operate is accurately recommended to the operator, the non-standard operation rate of the operator is reduced, the accuracy of goods shelving information is improved, the storage utilization rate and the operation efficiency are improved, and the server performance is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart industrial technology, and in particular to a method and device for recommending a target storage location for items on shelves. Background Art

[0002] With the maturity of computer technology in the warehousing industry, existing warehouse management has generally adopted WMS (Warehouse Management System) to replace traditional manual management, so that various links such as warehousing, shelving, picking, outbound, transfer, inventory, upstream and downstream interactions are all electronically monitored and managed by WMS.

[0003] In the existing WMS operation, when putting items on the shelves, operators usually need to go through several stages, such as extracting items, querying storage locations through WMS, searching on-site, locating storage locations, putting items on the shelves, and uploading storage location information of items to WMS.

[0004] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0005] On the one hand, due to the non-standard operation of operators, such as placing items casually in a hurry, filling in information casually or not checking carefully resulting in errors, etc., problems such as missing picking and uneven use of storage space often occur, reducing the efficiency of warehouse operation; on the other hand, when the number of items is complicated and there are too many historical operation flows, database queries take a long time, and the server's performance and memory cannot meet the data processing needs. Summary of the invention

[0006] In view of this, an embodiment of the present invention provides a method and device for recommending target storage locations for shelving items, which can extract historical data for asynchronous analysis, accurately recommend the storage location that is closest and most convenient for operation to operators, reduce the rate of irregular operations by operators, improve the accuracy of item shelving information, promote orderly warehousing processes, improve warehousing utilization and operating efficiency, and at the same time, reduce server pressure, improve server performance and data processing speed, and ensure stable operation of WMS and improved management efficiency.

[0007] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for recommending a target storage location for a shelf item is provided, comprising:

[0008] Receive a shelf-loading task; wherein the shelf-loading task includes an item identifier of the item to be shelf-loaded and an identifier of a person to be shelf-loaded;

[0009] According to the item identification and the identification of the person to be put on the shelf, the historical operation records of the item to be put on the shelf are matched from the item database; wherein the historical operation records include the historical storage location identification corresponding to the item identification, the historical number of times the item was put on the shelf, and the historical identification of the person who put the item on the shelf in each of the previous times;

[0010] Using the matched historical storage location identifiers, the historical number of times the items were put on the shelves, and the historical identification of the person who put the items on the shelves, the recommended values ​​of the historical storage locations corresponding to the historical storage location identifiers are calculated, and the recommended values ​​of the historical storage locations are sorted in descending order;

[0011] The historical storage locations corresponding to the top N recommended values ​​are recommended as target storage locations to the terminal corresponding to the identification of the person to be put on the shelf.

[0012] Optionally, the using the matched historical storage location identifiers, the historical number of times the items were put on the shelves, and the historical identification of the person who put the items on the shelves to calculate the recommended value of the historical storage location corresponding to each of the historical storage location identifiers includes:

[0013] Constructing an initial matrix corresponding to the identification of the person to be put on the shelf through the historical storage location identification and the historical number of times the person is put on the shelf;

[0014] Calculate the average value of each element value of the initial matrix;

[0015] Determining a similarity matrix of the initial matrix according to the difference between each element value of the initial matrix and the average value;

[0016] The similarity matrix and the user evaluation matrix are used to determine the recommendation value matrix corresponding to the identification of the person to be put on the shelf, and the recommendation value of the historical storage location corresponding to each of the historical storage location identifications is obtained.

[0017] Optionally, determining the similarity matrix of the initial matrix according to the difference between each element value of the initial matrix and the average value includes:

[0018] Calculate the difference between any element value in the initial matrix and the average value respectively, and obtain a first result of the value of any element;

[0019] Determine a second result of any element value according to the sum of squares of the first results;

[0020] A similarity matrix of the initial matrix is ​​generated by using the product of the first result of the any element value and other element values ​​and the product of the second result.

[0021] Optionally, the generating a similarity matrix of the initial matrix by using the product of the first result of any element value and other element values ​​and the product of the second result includes:

[0022] The first element value of the initial matrix is ​​used as the current element value, and the following steps are performed in a loop until the similarity matrix is ​​determined:

[0023] Calculate the product of the first result of the current element value and the first results of other element values ​​to obtain a third result;

[0024] Taking the square root of the second result of the current element value as a reference square root, and calculating the product of the reference square root and other square roots of other element values ​​to obtain a fourth result;

[0025] Determining the similarity of the current element value according to a ratio of the third result to the fourth result;

[0026] In the case that the next element value of the current element value is empty, the similarities of all element values ​​in the initial matrix are combined to obtain a similarity matrix of the initial matrix.

[0027] Optionally, the using the similarity matrix and the user evaluation matrix to determine the recommendation value matrix corresponding to the identification of the person to be put on the shelf includes:

[0028] Calculating the product of the similarity matrix and the user evaluation matrix to obtain a fifth result;

[0029] The recommendation value matrix is ​​determined according to a ratio of the fifth result to the similarity matrix.

[0030] Optionally, the determination of the user evaluation matrix includes:

[0031] De-duplication processing is performed on the historical times of listing of the historical listing matrix, and multiple occurrences of the times are counted;

[0032] Sorting the plurality of frequency values ​​in order from most to least to obtain a frequency sorting result;

[0033] According to the number of the frequency values, a scoring system for the frequency ranking result is constructed; wherein each frequency value corresponds to an evaluation score of the scoring system;

[0034] The user evaluation matrix of the historical shelf matrix is ​​determined by the scoring system.

[0035] Optionally, constructing a scoring system for the frequency ranking results according to the number of frequency values ​​includes:

[0036] According to the number of the secondary values, the number of grades of the first scoring system is determined, and a plurality of evaluation scores with different scores corresponding to the number of the number of grades is generated to obtain a first evaluation score sequence of the first scoring system; wherein the number of grades is a positive integer;

[0037] The plurality of evaluation scores included in the first evaluation score sequence are sequentially assigned to the respective number values ​​of the number sorting result in descending order.

[0038] Optionally, constructing a scoring system for the frequency ranking results according to the number of frequency values ​​includes:

[0039] Divide the number of the times according to the preset number of grades of the second scoring system, to obtain an average score; wherein the number of grades is a positive integer;

[0040] Constructing a level sequence that increases from 1 to the level number 2, multiplying the average value by each sequence value of the level sequence respectively, and performing rounding processing on the obtained multiplied sequence;

[0041] Determine the number of degree values ​​of each level belonging to the level sequence according to the difference between each sequence value in the rounding process sequence, generate a plurality of evaluation scores with different scores corresponding to the number of the second level, and obtain a second evaluation score sequence of the second scoring system;

[0042] The plurality of evaluation scores included in the second evaluation score sequence are sequentially assigned to the respective number values ​​of the number sorting result in descending order; wherein the number values ​​belonging to the same level have the same evaluation score.

[0043] Optionally, the constructing of an initial matrix corresponding to the identification of the person to be put on the shelf by using the historical storage location identification and the historical number of times of putting the items on the shelf includes:

[0044] The historical shelf-up matrix is ​​constructed by using the historical shelf-up personnel identification as the horizontal coordinate, the historical storage location identification as the vertical coordinate, and the historical shelf-up times as the element value;

[0045] The row vector in which the historical shelf-putting personnel identification is equal to the to-be-shelved personnel identification is used as the initial matrix corresponding to the to-be-shelved personnel identification.

[0046] According to another aspect of an embodiment of the present invention, there is provided a device for recommending a target storage location for a shelf item, comprising:

[0047] A receiving module, used for receiving a shelf-loading task; wherein the shelf-loading task includes an item identifier of the item to be shelf-loaded and an identifier of a person to be shelf-loaded;

[0048] A matching module, used to match the historical operation records of the item to be put on the shelf from the item database according to the item identification and the identification of the person to be put on the shelf; wherein the historical operation records include the historical storage location identification corresponding to the item identification, the historical number of times the item was put on the shelf, and the historical identification of the person who put the item on the shelf each time;

[0049] A data processing module, used to calculate the recommended value of the historical storage location corresponding to each of the historical storage location identifiers by using the matched historical storage location identifiers, the historical number of times the storage location has been put on the shelf, and the historical identification of the person who has put the storage location on the shelf, and sort the recommended values ​​of the historical storage location in descending order;

[0050] The recommendation module is used to recommend the historical storage locations corresponding to the top N recommended values ​​as target storage locations to the terminal corresponding to the identification of the person to be put on the shelf.

[0051] According to another aspect of an embodiment of the present invention, there is provided an electronic device for recommending a target storage location for a shelf item, comprising:

[0052] one or more processors;

[0053] a storage device for storing one or more programs,

[0054] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for recommending target storage locations for shelving items provided by the present invention.

[0055] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for recommending target storage locations for shelving items provided by the present invention is implemented.

[0056] One embodiment of the above invention has the following advantages or beneficial effects: because it adopts the technical means of matching the historical operation records of the items to be put on the shelves from the item database according to the item identification of the items to be put on the shelves and the identification of the person to be put on the shelves, including the historical storage location identification, the historical number of times of putting on the shelves, etc.; using the element value and the average value of each element in the historical number of times of putting on the shelves, the similarity between each historical storage location is calculated; then combining with the user evaluation matrix determined based on the user's historical shelving data, the recommendation value matrix corresponding to the items to be put on the shelves and the identification of the person to be put on the shelves is determined; the recommendation values ​​of each storage location are sorted, and the storage location corresponding to the top-N recommended values ​​is recommended as the target storage location to the terminal of the person who puts on the shelves, so as to overcome the technical means of overcoming the problem caused by the operator's incompetence. Standardized operations will result in problems such as missing picking and uneven utilization of storage space, which will reduce the efficiency of warehouse operation. When the number of items is complicated and there are too many historical operation flows, database queries take a long time, and the server's performance and memory cannot meet the technical needs of data processing. This will enable the extraction of historical data for asynchronous analysis, and accurately recommend the nearest and most convenient storage location to operators, reduce the rate of irregular operations by operators, improve the accuracy of item listing information, promote the orderly progress of warehouse processes, and improve warehouse utilization and operating efficiency. At the same time, it will reduce the pressure on the server, improve server performance and data processing speed, and ensure the stable operation of WMS and the improvement of management efficiency.

[0057] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0059] Figure 1 is a schematic diagram of the main process of a method for recommending a target storage location for shelving items according to an embodiment of the present invention;

[0060] Figure 2 is a schematic diagram of the main process of a method for determining a recommended value of a storage position according to an embodiment of the present invention;

[0061] Figure 3 is a schematic diagram of the main process of a method for determining a similarity matrix of an initial matrix according to an embodiment of the present invention;

[0062] Figure 4 is a schematic diagram of the main process of a method for determining a user evaluation matrix according to an embodiment of the present invention;

[0063] Figure 5 is a schematic diagram of main modules of a device for recommending a target storage location for shelving items according to an embodiment of the present invention;

[0064] Figure 6 An exemplary system architecture diagram showing a main process method or a main process device of a method for recommending a target storage location for shelving items that is suitable for application in an embodiment of the present invention;

[0065] Figure 7 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0067] It should be noted that the collection, use, storage, sharing and transfer of user personal information involved in the technical solution of the present invention are in compliance with the provisions of relevant laws and regulations, and require the user to be informed and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted. (For example: After collecting user identification information, we will de-identify the data through technical means.)

[0068] WMS: Warehouse Management System is a software used to support resource and data management of the entire warehousing system, including functions such as procurement, warehousing, shelving, picking, packaging, outbound, transfer, inventory, storage location and platform management, replenishment, waybill management, reporting, query, quality inspection, etc. It can realize integrated warehousing management, effectively control and track warehousing operations in all directions, and optimize warehousing execution and production efficiency.

[0069] sku: Stock Keeping Unit, which is the basic unit for measuring inventory in and out, refers to the inventory unit used to uniquely identify an item.

[0070] ES: Elasticsearch is an open source, highly scalable distributed full-text search engine. As a distributed non-relational database, it has strong scalability and data processing capabilities and can be used for online data analysis.

[0071] Clickhouse: CK for short, is an open source column-based database management system that can be used for online analysis of data.

[0072] Hive: is a data warehouse tool that can be used for online analysis of data, including mechanisms such as data extraction, transformation, loading, storage, query and analysis.

[0073] During the process of putting goods on the shelves, one sku can correspond to multiple storage locations. Since the storage location obtained by WMS query may be far away from the operator, in the case of urgent tasks, the operator often randomly searches for nearby storage locations for merchants, resulting in the phenomenon of inconsistent locations and data errors interrupting the waybill process in the later process of waybill matching and picking. At the same time, the multiple storage locations of sku are used unevenly, affecting the operation and management efficiency of the warehouse. In addition, when putting goods on the shelves, the operator needs to upload the storage location information, which has high labor costs and cannot guarantee data accuracy; for each sku put on the shelves, the WMS query needs to match the data to determine the number of items in multiple storage locations of the sku, the required storage conditions, etc., resulting in excessive server performance and memory pressure, which is easy to crash.

[0074] Through the item shelving method of the present invention, the top-N storage locations of the items are determined by utilizing historical operation records and user evaluation matrices, and are recommended to the operator's terminal for easy shelving of the items, thereby improving the shelving efficiency and accuracy, thereby shortening the warehouse's turnover operation cycle, improving warehouse management efficiency, reducing server pressure, and ensuring the stable operation of the WMS.

[0075] Figure 1 is a schematic diagram of the main process of the method for recommending target storage locations for shelving items according to an embodiment of the present invention, such as Figure 1 As shown, the method for recommending target storage locations for shelf items of the present invention comprises the following steps:

[0076] Step S101, receiving a shelving task; wherein the shelving task includes an item identifier of the item to be shelved and an identifier of a person to be shelved.

[0077] In an embodiment of the present invention, the shelving task is generated by the WMS, and there are various scenarios for generating the shelving task, including the scenario where the goods need to be shelved for the first time entering the warehouse (also called the acceptance shelving scenario), or the scenario where the goods need to be shelved due to sorting errors, waybill cancellation, return, exchange, etc. (also called the return to shelf scenario), etc.

[0078] Furthermore, the method for recommending target storage locations for items on the shelves of the present invention can be executed by a data center such as ES, Clickhouse or Hive in the WMS. During the operation of the WMS, the data center can execute the method for recommending target storage locations for items on the shelves of the present invention asynchronously, in real time or offline to alleviate system pressure and improve system performance.

[0079] In the embodiment of the present invention, the item identifier is the SKU of the item.

[0080] Step S102, matching the historical operation records of the items to be put on the shelves from the item database according to the item identification and the identification of the person to be put on the shelves; wherein the historical operation records include the historical storage location identification corresponding to the item identification, the historical number of times the items were put on the shelves, and the historical identification of the person who put the items on the shelves each time.

[0081] In the embodiment of the present invention, the item database is located in data centers such as ES, Clickhouse, and Hive, and stores historical operation records of various items. The historical operation records include the corresponding relationship between item identification, historical task type, historical operator identification, historical storage location identification, historical task information, etc. Among them, the task type can be a shelf task, a sorting task, a warehouse transfer task, an inventory task, etc.; the operator identification is the personnel identification of the operator who performs various tasks. Depending on the task type, the operator identification can be a shelf personnel identification, a sorting personnel identification, a warehouse transfer personnel identification, an inventory personnel identification, etc.; depending on the task type, the task information can be the number of shelves, shelf time, sorting list, packing list, warehouse transfer destination identification, inventory time, etc.

[0082] Furthermore, based on the item identification and historical task type, the data center matches historical operation records whose historical task type is shelving task and corresponds to the item identification of the item to be shelved from the item database, and collects data such as historical storage location identification and historical number of shelving times included in the matched historical operation records.

[0083] Step S103, using the matched historical storage location identifiers, the historical number of times the items were put on the shelves, and the historical identification of the person who put the items on the shelves, the recommended values ​​of the historical storage locations corresponding to the historical storage location identifiers are calculated, and the recommended values ​​of the historical storage locations are sorted in descending order.

[0084] In an embodiment of the present invention, by analyzing the historical shelving records related to the items to be put on the shelves, for the items to be put on the shelves, with the goal of being most convenient for the personnel to put the items on the shelves to operate, the recommended values ​​of each historical storage location are calculated respectively, and sorted from large to small, so that the top N optimal target storage locations can be recommended to the personnel to put the items on the shelves later, so that the personnel to put the items on the shelves can choose the most convenient storage location for shelving.

[0085] In the embodiment of the present invention, Figure 2 As shown, the method for determining the recommended value of the storage position of the present invention comprises the following steps:

[0086] Step S201, constructing an initial matrix corresponding to the identification of the person to be put on the shelf through the historical storage location identification and the historical number of times of putting on the shelf.

[0087] Step S2011, constructing the historical shelf matrix with the historical shelf personnel identification as the horizontal coordinate, the historical storage location identification as the vertical coordinate, and the historical shelf times as the element value.

[0088] In the embodiment of the present invention, the historical shelf personnel identification U of the item to be put on the shelf is used. i is the horizontal axis, historical storage position mark M j The vertical axis is the number of historical launches R i,jFor the element values ​​of each matrix element, a historical matrix R is constructed, where i = 1, 2, 3, ..., n, j = 1, 2, 3, ..., m.

[0089] Step S2012: taking the row vector whose historical shelf-putting personnel identification is equal to the to-be-shelved personnel identification as the initial matrix corresponding to the to-be-shelved personnel identification.

[0090] In the embodiment of the present invention, the historical shelf personnel identification whose horizontal coordinate is the same as the identification of the person to be shelf is searched in the historical shelf personnel identification matrix, and the row vector corresponding to the historical shelf personnel identification that is the same as the identification of the person to be shelf is used as the initial matrix corresponding to the identification of the person to be shelf. k , search the horizontal coordinate and U in the history matrix R k The same row vector as U k The corresponding initial matrix R k .

[0091] Furthermore, in the case where there are multiple identifications of personnel to be put on the shelf, multiple row vectors corresponding to multiple historical identifications of personnel to be put on the shelf that are the same as the multiple identifications of personnel to be put on the shelf obtained by searching are combined into an initial matrix corresponding to the multiple identifications of personnel to be put on the shelf.

[0092] Step S202, calculating the average value of each element value of the initial matrix.

[0093] In the embodiment of the present invention, the calculation and the identification of the person to be put on the shelf U k The corresponding initial matrix R k The average value a of each element in. For example, m = 12, U k The corresponding initial matrix R k =[0,2,4,9,3,1,8,10,0,6,2,3], then the average value a=4.

[0094] Furthermore, when the average value a is not an integer, the average value may be rounded up or down according to actual needs.

[0095] Furthermore, when there are multiple identifications of personnel to be put on the shelves, the average values ​​of the element values ​​of each row vector of the initial matrix are calculated respectively.

[0096] Step S203: determining a similarity matrix of the initial matrix according to the difference between each element value of the initial matrix and the average value.

[0097] In the embodiment of the present invention, the calculation formula for the similarity of each element value of the initial matrix is ​​shown in the following formula (1):

[0098]

[0099] In the embodiment of the present invention, Figure 3 As shown, the method for determining the similarity matrix of the initial matrix of the present invention comprises the following steps:

[0100] Step S301, respectively calculating the difference between any element value in the initial matrix and the average value to obtain a first result of the any element value.

[0101] In the embodiment of the present invention, R is calculated respectively. k Any element value in R k,j The difference between the average value a and R k,j The first result (R k,j -a).

[0102] Furthermore, in the case where there are multiple identifications of personnel to be put on the shelves, for each row vector of the initial matrix, the difference between any element value and the average value of the row vector is calculated to obtain a first result of any element value.

[0103] Step S302: Determine a second result of any element value according to the square sum of the first results.

[0104] In the embodiment of the present invention, R is calculated respectively. k Any element value in R k,j The first result (R k,j -a) and the sum of the squares to get R k,j The second result (R k,j -a) 2 .

[0105] Furthermore, in the case where there are multiple identifications of personnel to be put on the shelves, for each row vector of the initial matrix, the square sum of the first result of any element value is calculated to obtain the second result of any element value.

[0106] Step S303: Generate a similarity matrix of the initial matrix by using the product of the first result of any element value and other element values ​​and the product of the second result.

[0107] Step S3031: taking the first element value of the initial matrix as the current element value.

[0108] Step S3032, calculating the product of the first result of the current element value and the first results of other element values ​​to obtain a third result.

[0109] In the embodiment of the present invention, for R k The current element value in R k,l , calculate R k,l The first result (R k,l-a) and the first result of other element values The product of l≠j gives the third result

[0110] Furthermore, when there are multiple identifications of people to be put on the shelves, for each row vector of the initial matrix, the product of the first result of the current element value and the first results of other element values ​​of the row vector is calculated to obtain a third result; wherein the current element value is any element value of the row vector.

[0111] Step S3033, taking the square root of the second result of the current element value as a reference square root, and calculating the product of the reference square root and other square roots of other element values ​​to obtain a fourth result.

[0112] In the embodiment of the present invention, for R k The current element value in R k,l , R k,l The second result (R k,l -a) 2 Take the square root as the base square root The second result of other element values ​​is squared to get other square roots l≠j, find And the product of other square roots of other element values, we get the fourth result

[0113] Furthermore, in the case where there are multiple identifications of people to be put on the shelves, for each row vector of the initial matrix, the reference square root of the second result of the current element value and the other square roots of the second results of other element values ​​are calculated respectively, and the product of the reference square root and the other square roots of the row vector is determined as the fourth result.

[0114] Step S3034: Determine the similarity of the current element value according to the ratio of the third result to the fourth result.

[0115] In the embodiment of the present invention, according to the third result And the fourth result The ratio of the current element value R k,l The similarity Sim(l,j) is.

[0116] Furthermore, in the case where there are multiple identifications of personnel to be put on the shelves, for each row vector of the initial matrix, the ratio of the third result to the fourth result of each element value is calculated as the similarity of the element value.

[0117] Step S3035, determine whether the next element value of the current element value is empty, if yes, go to step S3036; if not, go to step S3037.

[0118] Step S3036, combining the similarities of all element values ​​in the initial matrix to obtain a similarity matrix of the initial matrix.

[0119] In the embodiment of the present invention, when the next element value of the current element value is empty, it indicates that the similarity processing of the initial matrix is ​​completed, and the similarities of all element values ​​in the initial matrix are combined into the initial matrix R k The similarity matrix S k =[S k,1 ,S k,2 ,S k,3 ,…,S k,m ].

[0120] Furthermore, in the case where there are multiple identifications of personnel to be put on the shelves, the similarity matrix S of the initial matrix is ​​obtained based on the similarity of each element value of the initial matrix.

[0121] Step S3037, taking the next element value as the current element value, and going to step S3032.

[0122] In the embodiment of the present invention, if the next element value of the current element value is not empty, the next element value of the current element value is used as the current element value, and the process goes to step S3032 to continue. For example, the current element value is the first element value of the initial matrix, and the next element value of the current element value is the second element value of the initial matrix.

[0123] In an embodiment of the present invention, according to the method for determining the similarity matrix of the initial matrix of the present invention, the difference between the element value of the initial matrix and the element average value is used to calculate the similarity between different element values ​​of the initial matrix, so that the preferences of the shelving personnel can be obtained, and more suitable shelving storage locations can be recommended to the shelving personnel, thereby improving the accuracy of the shelving information uploaded by the shelving personnel and improving the efficiency of warehouse management.

[0124] Step S204, using the similarity matrix and the user evaluation matrix, determine the recommendation value matrix corresponding to the to-be-shelved personnel identifier, and obtain the recommendation value of the historical storage location corresponding to each of the historical storage location identifiers.

[0125] Step S2041, calculating the product of the similarity matrix and the user evaluation matrix to obtain a fifth result.

[0126] In this embodiment of the present invention, the similarity matrix S is calculated k And the user evaluation matrix E k The fifth result S is obtained. k ·E k . User evaluation matrix E k Use historical shelf personnel identification k is the horizontal axis, historical storage position mark Mj The vertical axis is E, the historical evaluation score is k,j is the element value of each matrix element.

[0127] Furthermore, in the case where there are multiple identifications of people to be put on the shelf, the product of the similarity matrix S and the user evaluation matrix E is calculated to obtain a fifth result S·E. The user evaluation matrix E is based on the historical identifications of people to be put on the shelf U i is the horizontal axis, historical storage position mark M j The vertical axis is E, the historical evaluation score is i,j is the element value of each matrix element.

[0128] In the embodiment of the present invention, Figure 4 As shown, the method for determining the user evaluation matrix of the present invention comprises the following steps:

[0129] Step S401, performing deduplication processing on the historical times of listing of the historical listing matrix, and counting multiple times of occurrence.

[0130] In an embodiment of the present invention, for example, multiple number values ​​that appear after the historical rack matrix deduplication processing include: 11, 3, 1, 59, 21, 19, 10, 30, 15, 32, 9, 28, and 5.

[0131] Step S402, sorting the plurality of frequency values ​​in order from most to least to obtain a frequency sorting result.

[0132] In an embodiment of the present invention, for example, a plurality of frequency values ​​are sorted in order from most to least to obtain a frequency sorting result: 59, 32, 30, 28, 21, 19, 15, 11, 10, 9, 5, 3, 1.

[0133] Step S403, constructing a scoring system for the frequency ranking result according to the number of the frequency values; wherein each frequency value corresponds to an evaluation score of the scoring system.

[0134] In the embodiment of the present invention, according to the number of the number of times, the number of grades of the first scoring system is determined, and a plurality of evaluation scores with different scores corresponding to the number of the number of grades is generated to obtain a first evaluation score sequence of the first scoring system; wherein the number of grades is a positive integer;

[0135] The plurality of evaluation scores included in the first evaluation score sequence are sequentially assigned to the respective number values ​​of the number sorting result in descending order.

[0136] For example, the number of frequency values ​​is 13, and the number of levels of the first scoring system is also 13, that is, the first scoring system is a 13-point system. 13 evaluation scores with different scores are generated to obtain a first evaluation score sequence [1-13] of the first scoring system. The 13 evaluation scores included in the first evaluation score sequence [1-13] are sequentially assigned to the respective frequency values ​​59, 32, 30, 28, 21, 19, 15, 11, 10, 9, 5, 3, 1 of the frequency sorting result in the order of 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1 from high to low.

[0137] In the embodiment of the present invention, alternatively, the number of the time values ​​is evenly divided according to the preset number of levels two of the second scoring system to obtain an average value; wherein the number of levels two is a positive integer;

[0138] Constructing a level sequence that increases from 1 to the level number 2, multiplying the average value by each sequence value of the level sequence respectively, and performing rounding processing on the obtained multiplied sequence;

[0139] Determine the number of degree values ​​of each level belonging to the level sequence according to the difference between each sequence value in the rounding process sequence;

[0140] generating a plurality of evaluation scores with different scores corresponding to the number of the second level, and obtaining a second evaluation score sequence of the second scoring system;

[0141] The plurality of evaluation scores included in the second evaluation score sequence are sequentially assigned to the respective number values ​​of the number sorting result in descending order; wherein the number values ​​belonging to the same level have the same evaluation score.

[0142] For example, the preset second scoring system is a 10-point system, and the second level of the 10-point system is 10. The number of the number of times 13 is evenly divided according to the second level 10, and the average value is 1.3. Construct a level sequence [1-10] that increases from 1 to the second level, and multiply the average value 1.3 with each sequence value of the level sequence [1-10] respectively, and the multiplication sequence is [1.3, 2.6, 3.9, 5.2, 6.5, 7.8, 9.1, 10.4, 11.7, 13]. The rounding process is rounding, and the obtained multiplication sequence is rounded to obtain the rounding process sequence [1, 3, 4, 5, 7, 8, 9, 10, 12, 13]. According to the difference between adjacent sequence values ​​in the rounding process sequence, the number of times values ​​belonging to each level is determined to be [1, 2, 1, 1, 2, 1, 1, 1, 2, 1], that is, the level sequence [1-10] corresponds to the rounding process sequence [1, 3, 4, 5, 7, 8, 9, 10, 12, 13], the number of times values ​​of level 1 is 1, the number of times values ​​of level 2 is the difference between 3 and 1, that is, 2, the number of times values ​​of level 3 is the difference between 4 and 3, that is, 1, .... Ten evaluation scores with different scores corresponding to the number of levels equal to 10 are generated to obtain the second evaluation score sequence [1-10]. The 10 evaluation scores included in the second evaluation score sequence [1-10] are assigned to each number value of the frequency sorting result in the order of 10, 9, 8, 7, 6, 5, 4, 3, 2, 1 from high to low. Since the number values ​​belonging to the same level have the same evaluation score, the evaluation scores of the number values ​​of the frequency sorting results 59, 32, 30, 28, 21, 19, 15, 11, 10, 9, 5, 3, 1 are 10, 9, 9, 8, 7, 6, 6, 5, 4, 3, 2, 2, 1 respectively.

[0143] Step S404, determining the user evaluation matrix of the historical shelf matrix through the scoring system.

[0144] In an embodiment of the present invention, for the first scoring system and / or the second scoring system, the user evaluation matrix corresponding to the historical shelf matrix is ​​determined according to the evaluation scores corresponding to each number value in step S403, that is, the evaluation scores of each number value in step S403 are respectively assigned to the corresponding historical shelf times in the historical shelf matrix to obtain the user evaluation matrix.

[0145] Furthermore, before the method for recommending target storage locations for shelving items of the present invention is executed, the historical shelving matrix is ​​used to determine the initial user evaluation matrix. Each time the shelving personnel updates the operation record, the method for recommending target storage locations for shelving items of the present invention can update the historical shelving matrix using the updated historical operation record, and then use the updated historical shelving matrix to update the user evaluation matrix, so that the recommendation value matrix is ​​kept at the latest value.

[0146] It should be noted that the above example is an example case where there is one identification of the person to be listed. In the case where there are multiple identifications of the person to be listed, the dimension of the user evaluation matrix matches the multiple identifications of the person to be listed.

[0147] In an embodiment of the present invention, according to the method for determining the user evaluation matrix of the present invention, a scoring system for the number of times the number of times the products are put on the shelves in history is constructed to determine the user evaluation matrix. Subsequently, the recommended value of the storage location can be calculated based on the user evaluation matrix, thereby improving the accuracy of the recommendation and the management efficiency of the warehouse.

[0148] Step S2042: determining the recommendation value matrix according to the ratio of the fifth result to the similarity matrix.

[0149] In the embodiment of the present invention, the third result S is calculated k ·E k With the similarity matrix S k The ratio of , and the recommended value matrix corresponding to the identification of the person to be put on the shelf is obtained, as shown in the following formula (2):

[0150]

[0151] It should be noted that T k The example of is an example case when the identification of the person to be put on the shelf is one. In the case where there are multiple identifications of the person to be put on the shelf, the dimension of T matches the multiple identifications of the person to be put on the shelf.

[0152] Step S104: recommending the historical storage locations corresponding to the top N recommended values ​​as target storage locations to the terminal corresponding to the identifier of the person to be put on the shelf.

[0153] In the embodiment of the present invention, after selecting the first N historical storage locations sorted in descending order according to the recommended values, the first N historical storage location identifiers are pushed as target storage location identifiers to the terminal corresponding to the identification of the person to be put on the shelf, so that the person who puts the item on the shelf at the terminal can select any storage location from them. Wherein, N is a positive integer greater than or equal to 1.

[0154] Furthermore, the operation records of the items to be shelved uploaded by the terminal of the shelving personnel are received, and the operation records of the items to be shelved uploaded by the terminal are stored in the item database. The operation records stored in the item database are the historical operation records when the method for recommending the target storage location for shelving items of the present invention is executed next time. The target storage location for the shelving task is recommended based on the updated historical operation records, so that the recommended target storage location is the optimal value.

[0155] In the embodiment of the present invention, the target storage location recommendation method for shelving items of the present invention is compared with the traditional method by means of log embedding. It can be found that the target storage location recommendation method for shelving items of the present invention has high recommendation accuracy and selection rate of shelving personnel, which improves warehouse utilization and management efficiency without interfering with WMS.

[0156] In an embodiment of the present invention, a shelving task is received; wherein the shelving task includes an item identifier of the item to be shelved and an identifier of a person to be shelved; according to the item identifier and the identifier of the person to be shelved, a historical operation record of the item to be shelved is matched from an item database; wherein the historical operation record includes a historical storage location identifier, a historical number of shelving operations, and a historical shelving personnel identifier corresponding to the item identifier; using the matched historical storage location identifier, the historical number of shelving operations, and the historical shelving personnel identifier, a recommended value of the historical storage location corresponding to each of the historical storage location identifiers is calculated, and the recommended value of the historical storage location corresponding to the historical storage location identifier is calculated according to the historical storage location identifier. The recommended values ​​of the historical storage locations are sorted in descending order; the historical storage locations corresponding to the top N recommended values ​​are recommended as target storage locations to the terminal corresponding to the identification of the person to be put on the shelf, etc., which can extract historical data for asynchronous analysis, accurately recommend the nearest and most convenient storage location to the operator, reduce the irregular operation rate of the operator, improve the accuracy of the item shelving information, promote the orderly progress of the warehousing process, improve the warehousing utilization rate and operating efficiency, and at the same time, reduce the pressure on the server, improve the server performance and data processing speed, and ensure the stable operation of the WMS and the improvement of management efficiency.

[0157] Figure 5 is a schematic diagram of main modules of a device for recommending target storage locations for items on shelves according to an embodiment of the present invention, such as Figure 5 As shown, the device 500 for recommending target storage locations for shelf items of the present invention comprises:

[0158] The receiving module 501 is used to receive a shelving task; wherein the shelving task includes an item identifier of the item to be shelved and an identifier of a person to be shelved.

[0159] The matching module 502 is used to match the historical operation records of the items to be put on the shelves from the item database according to the item identification and the identification of the person to put the items on the shelves; wherein the historical operation records include the historical storage location identification corresponding to the item identification, the historical number of times the items were put on the shelves, and the historical identification of the person who put the items on the shelves each time.

[0160] The data processing module 503 is used to calculate the recommended value of the historical storage location corresponding to each historical storage location identifier by using the matched historical storage location identifier, the historical number of times the items were put on the shelves, and the historical identification of the person who put the items on the shelves, and sort the recommended values ​​of the historical storage locations in descending order.

[0161] The recommendation module 504 is used to recommend the historical storage locations corresponding to the top N recommendation values ​​as target storage locations to the terminal corresponding to the identification of the person to be put on the shelf.

[0162] In the embodiment of the present invention, through modules such as the receiving module, the matching module, the data processing module and the recommendation module, historical data can be extracted for asynchronous analysis, and the storage location that is closest and most convenient for operation can be accurately recommended to the operator, thereby reducing the operator's irregular operation rate, improving the accuracy of item shelving information, promoting the orderly progress of the warehousing process, improving warehousing utilization and operating efficiency, and at the same time, reducing the pressure on the server, improving server performance and data processing speed, and ensuring the stable operation of the WMS and improving management efficiency.

[0163] Figure 6 An exemplary system architecture diagram of a method for recommending a target storage location for a shelf item or a device for recommending a target storage location for a shelf item suitable for application in an embodiment of the present invention is shown. Figure 6 As shown, an exemplary system architecture of a method for recommending a target storage location for a shelf item or a device for recommending a target storage location for a shelf item according to an embodiment of the present invention includes:

[0164] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0165] The user can use the terminal devices 601, 602, 603 to interact with the server 605 through the network 604 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 601, 602, 603, such as WMS applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0166] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0167] The server 605 may be a server that provides various services, such as a background management server that provides support for WMS websites browsed by users using the terminal devices 601, 602, and 603. The background management server may analyze and process the received data such as the shelf tasks, and feed back the processing results (such as the target storage location identifier) ​​to the terminal devices 601, 602, and 603.

[0168] It should be noted that the method for recommending a target storage location for shelving items provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the device for recommending a target storage location for shelving items is generally disposed in the server 605 .

[0169] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0170] Figure 7 is a schematic diagram of a computer system of a terminal device or server suitable for implementing an embodiment of the present invention, such as Figure 7 As shown, the computer system 700 of the terminal device or server of the embodiment of the present invention includes:

[0171] A central processing unit (CPU) 701 can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage portion 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the system 700 are also stored in the RAM 703. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0172] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0173] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0174] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0175] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0176] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be arranged in a processor, for example, they may be described as: a processor including a receiving module, a matching module, a data processing module and a recommendation module. The names of these modules do not constitute limitations on the modules themselves in certain cases. For example, the data processing module may also be described as "a module for calculating the recommended value of the historical storage location corresponding to each of the historical storage location identifiers using the matched historical storage location identifiers, the historical number of shelves and the historical shelf personnel identifiers".

[0177] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: receiving a shelving task; wherein the shelving task includes an item identifier of the item to be shelved and an identifier of a person to be shelved; according to the item identifier and the identifier of the person to be shelved, matching the historical operation record of the item to be shelved from the item database; wherein the historical operation record includes a historical storage location identifier, a historical number of shelving times, and a historical shelving person identifier corresponding to the item identifier; using the matched historical storage location identifier, the historical number of shelving times, and the historical shelving person identifier, calculating the recommended value of the historical storage location corresponding to each of the historical storage location identifiers, and sorting the recommended values ​​of the historical storage locations in descending order; recommending the historical storage locations corresponding to the top N recommended values ​​as target storage locations to the terminal corresponding to the identifier of the person to be shelved.

[0178] According to the technical solution of the embodiment of the present invention, in the context of WMS operation, the data center is used to extract historical operation records, calculate the recommended value of each storage location, and push the target storage location identifier to the operator, so that the operator can choose the best one for shelving. Therefore, the target storage location recommendation method of the present invention is more in line with the actual situation of the operator, which can avoid the operator's irregular operation to a large extent and improve the accuracy of the shelving information; using the data center for calculation, on the one hand, the data analysis and processing speed is fast, the recommendation efficiency is high and accurate, and on the other hand, it reduces the system memory consumption and computing pressure, optimizes the system performance, promotes the orderly progress of the warehousing process, improves the warehousing utilization rate and operating efficiency, and at the same time, reduces the pressure on the server, improves the server performance and data processing speed, and ensures the stable operation of WMS and the improvement of management efficiency.

[0179] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for recommending target storage locations for items on shelves, characterized in that: include: Receive a shelf-loading task; wherein the shelf-loading task includes an item identifier of the item to be shelf-loaded and an identifier of a person to be shelf-loaded; According to the item identification and the identification of the person to be put on the shelf, the historical operation records of the item to be put on the shelf are matched from the item database; wherein the historical operation records include the historical storage location identification corresponding to the item identification, the historical number of times the item was put on the shelf, and the historical identification of the person who put the item on the shelf in each of the previous times; Using the matched historical storage location identifiers, the historical number of times the items were put on the shelves, and the historical identification of the person who put the items on the shelves, the recommended values ​​of the historical storage locations corresponding to the historical storage location identifiers are calculated, and the recommended values ​​of the historical storage locations are sorted in descending order; The historical storage locations corresponding to the top N recommended values ​​are recommended as target storage locations to the terminal corresponding to the identification of the person to be put on the shelf.

2. The method according to claim 1, characterized in that The method of calculating the recommended value of the historical storage location corresponding to each of the historical storage location identifiers by using the matched historical storage location identifiers, the historical number of times the items are put on the shelves, and the historical identification of the person who put the items on the shelves, comprises: Constructing an initial matrix corresponding to the identification of the person to be put on the shelf through the historical storage location identification and the historical number of times the person is put on the shelf; Calculate the average value of each element value of the initial matrix; Determining a similarity matrix of the initial matrix according to the difference between each element value of the initial matrix and the average value; The similarity matrix and the user evaluation matrix are used to determine the recommendation value matrix corresponding to the identification of the person to be put on the shelf, and the recommendation value of the historical storage location corresponding to each of the historical storage location identifications is obtained.

3. The method according to claim 2, characterized in that Determining the similarity matrix of the initial matrix according to the difference between each element value of the initial matrix and the average value includes: Calculate the difference between any element value in the initial matrix and the average value respectively, and obtain a first result of the value of any element; Determine a second result of any element value according to the sum of squares of the first results; A similarity matrix of the initial matrix is ​​generated by using the product of the first result of the any element value and other element values ​​and the product of the second result.

4. The method according to claim 3, characterized in that The step of generating a similarity matrix of the initial matrix by using the product of the first result of the any element value and the other element values ​​and the product of the second result includes: The first element value of the initial matrix is ​​used as the current element value, and the following steps are performed in a loop until the similarity matrix is ​​determined: Calculate the product of the first result of the current element value and the first results of other element values ​​to obtain a third result; Taking the square root of the second result of the current element value as a reference square root, and calculating the product of the reference square root and other square roots of other element values ​​to obtain a fourth result; Determining the similarity of the current element value according to a ratio of the third result to the fourth result; In the case that the next element value of the current element value is empty, the similarities of all element values ​​in the initial matrix are combined to obtain a similarity matrix of the initial matrix.

5. The method according to claim 4, characterized in that The method of using the similarity matrix and the user evaluation matrix to determine the recommendation value matrix corresponding to the identification of the person to be put on the shelf comprises: Calculating the product of the similarity matrix and the user evaluation matrix to obtain a fifth result; The recommendation value matrix is ​​determined according to a ratio of the fifth result to the similarity matrix.

6. The method according to claim 1, characterized in that The determination of the user evaluation matrix includes: De-duplication processing is performed on the historical times of listing of the historical listing matrix, and multiple occurrences of the times are counted; Sorting the plurality of frequency values ​​in order from most to least to obtain a frequency sorting result; According to the number of the frequency values, a scoring system for the frequency ranking result is constructed; wherein each frequency value corresponds to an evaluation score of the scoring system; The user evaluation matrix of the historical shelf matrix is ​​determined by the scoring system.

7. The method according to claim 6, characterized in that The step of constructing a scoring system for the frequency ranking results according to the number of the frequency values ​​includes: According to the number of the secondary values, the number of grades of the first scoring system is determined, and a plurality of evaluation scores with different scores corresponding to the number of the number of grades is generated to obtain a first evaluation score sequence of the first scoring system; wherein the number of grades is a positive integer; The plurality of evaluation scores included in the first evaluation score sequence are sequentially assigned to the respective number values ​​of the number sorting result in descending order.

8. The method according to claim 6, characterized in that The step of constructing a scoring system for the frequency ranking results according to the number of the frequency values ​​includes: Divide the number of the times according to the preset number of grades of the second scoring system, to obtain an average score; wherein the number of grades is a positive integer; Constructing a level sequence that increases from 1 to the level number 2, multiplying the average value by each sequence value of the level sequence respectively, and performing rounding processing on the obtained multiplied sequence; Determine the number of times of each level belonging to the level sequence according to the difference between each sequence value in the rounding process sequence, generate a plurality of evaluation scores with different scores corresponding to the number of the second level, and obtain a second evaluation score sequence of the second scoring system; The plurality of evaluation scores included in the second evaluation score sequence are sequentially assigned to the respective number values ​​of the number sorting result in descending order; wherein the number values ​​belonging to the same level have the same evaluation score.

9. The method according to claim 2, characterized in that: The constructing of an initial matrix corresponding to the identification of the person to be put on the shelf by using the historical storage location identification and the historical number of times the items are put on the shelf comprises: The historical shelf-up matrix is ​​constructed by using the historical shelf-up personnel identification as the horizontal coordinate, the historical storage location identification as the vertical coordinate, and the historical shelf-up times as the element value; The row vector in which the historical shelf-putting personnel identification is equal to the to-be-shelved personnel identification is used as the initial matrix corresponding to the to-be-shelved personnel identification.

10. A device for recommending target storage locations for items on shelves, characterized in that: include: A receiving module, used for receiving a shelf-loading task; wherein the shelf-loading task includes an item identifier of the item to be shelf-loaded and an identifier of a person to be shelf-loaded; A matching module, used for matching the historical operation records of the item to be put on the shelf from the item database according to the item identification and the identification of the person to be put on the shelf; wherein the historical operation records include the historical storage location identification corresponding to the item identification, the historical number of times the item was put on the shelf, and the historical identification of the person who put the item on the shelf each time; A data processing module, used to calculate the recommended value of the historical storage location corresponding to each of the historical storage location identifiers by using the matched historical storage location identifiers, the historical number of times the storage location has been put on the shelf, and the historical identification of the person who has put the storage location on the shelf, and sort the recommended values ​​of the historical storage location in descending order; The recommendation module is used to recommend the historical storage locations corresponding to the top N recommended values ​​as target storage locations to the terminal corresponding to the identification of the person to be put on the shelf.

11. An electronic device for recommending a target storage location for a shelf item, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 9.

12. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images