CN111523918B - Commodity clustering method, device, equipment and storage medium - Google Patents

Commodity clustering method, device, equipment and storage medium Download PDF

Info

Publication number
CN111523918B
CN111523918B CN201910107025.4A CN201910107025A CN111523918B CN 111523918 B CN111523918 B CN 111523918B CN 201910107025 A CN201910107025 A CN 201910107025A CN 111523918 B CN111523918 B CN 111523918B
Authority
CN
China
Prior art keywords
commodity
commodities
inventory
network
order
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910107025.4A
Other languages
Chinese (zh)
Other versions
CN111523918A (en
Inventor
陈伟
韩昊
孙凯
王玉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jizhijia Technology Co Ltd
Original Assignee
Beijing Jizhijia Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jizhijia Technology Co Ltd filed Critical Beijing Jizhijia Technology Co Ltd
Priority to CN201910107025.4A priority Critical patent/CN111523918B/en
Priority to EP19907152.3A priority patent/EP3905154A4/en
Priority to US17/419,724 priority patent/US20220051178A1/en
Priority to PCT/CN2019/128557 priority patent/WO2020140818A1/en
Publication of CN111523918A publication Critical patent/CN111523918A/en
Application granted granted Critical
Publication of CN111523918B publication Critical patent/CN111523918B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Warehouses Or Storage Devices (AREA)

Abstract

The embodiment of the invention discloses a commodity clustering method, a commodity clustering device, commodity clustering equipment and a storage medium, wherein the commodity clustering method comprises the following steps: mapping commodities into network nodes, mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into the association weight between the two network nodes, and constructing a commodity association network between commodities; determining characteristic values of commodities corresponding to all network nodes in the commodity correlation network according to a graph embedding algorithm; and clustering the commodities according to the characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes. The technical scheme of the embodiment of the invention solves the problem that the commodities with obvious relations among the commodities can not be clustered well from the description content of the commodities, realizes the clustering of different commodities, improves the clustering effect among the commodities, and greatly improves the subsequent processing efficiency of the commodities.

Description

Commodity clustering method, device, equipment and storage medium
Technical Field
The embodiment of the invention relates to the technical field of logistics storage, in particular to a commodity clustering method, a commodity clustering device, commodity clustering equipment and a storage medium.
Background
In warehouse management, in order to increase warehouse operation efficiency and save cost, a clustering process is generally required to be performed on massive commodities, orders and storage positions according to existing information, and the key of the clustering process is that different commodities are required to be separated into different clusters according to similarity or correlation.
In the related technology, the commodity clustering mainly realizes the clustering of different commodities according to the description contents of different commodities, each commodity needs detailed text description contents when being clustered, and the commodity clustering method has a good clustering effect on commodities similar to the description contents. However, in actual use, there are many commodities, and although obvious relations between commodities are not seen from the description contents of commodities, in practical use, there are mutually auxiliary relations, such as towels and soap boxes, so that the commodities are often clustered together. It can be seen that, in the above case, the product clustering scheme in the related art cannot solve the problem of achieving good clustering for the products in which no obvious link between the products is seen from the descriptive contents of the products.
Disclosure of Invention
In view of the above problems, embodiments of the present invention provide a method, an apparatus, a device, and a storage medium for clustering commodities, so as to implement clustering of different commodities and improve a clustering effect between the commodities.
In a first aspect, an embodiment of the present invention provides a method for clustering commodities, where the method includes:
mapping commodities into network nodes, mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into the association weight between the two network nodes, and constructing a commodity association network between commodities;
determining characteristic values of commodities corresponding to all network nodes in the commodity correlation network according to a graph embedding algorithm;
and clustering the commodities according to the characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes.
In a second aspect, an embodiment of the present invention further provides a device for clustering commodities, where the device includes:
the construction module is used for mapping commodities into network nodes, mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into the association weight between the two network nodes, and constructing a commodity association network between the commodities;
the determining module is used for determining characteristic values of commodities corresponding to all network nodes in the commodity correlation network according to a graph embedding algorithm;
and the clustering module is used for clustering the commodities according to the characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes.
In a third aspect, an embodiment of the present invention further provides an apparatus, where the apparatus includes:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a method of merchandise clustering as described in any embodiment of the invention.
In a fourth aspect, there is also provided in an embodiment of the present invention a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of clustering articles according to any embodiment of the present invention.
According to the technical scheme provided by the embodiment of the invention, the commodity correlation network between commodities is constructed by mapping the commodities into the network nodes and mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into the correlation weight between the two network nodes, the characteristic values of the commodities corresponding to the network nodes in the commodity correlation network are determined according to a graph embedding algorithm, and the characteristic that obvious relations between the commodities cannot be seen from the description content of the commodities can be extracted, so that the commodities can be clustered according to the characteristic values of the commodities corresponding to the network nodes to obtain a plurality of classes of commodities, the clustering of different commodities is realized, the clustering effect between the commodities is improved, and the subsequent sorting efficiency of the commodities is greatly improved.
The foregoing summary is merely an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more fully understood, and in order that the same or additional objects, features and advantages of the present invention may be more fully understood.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1a is a schematic diagram of a system architecture of an inventory system provided in an embodiment of the invention;
FIG. 1b is a schematic view of a shelf structure provided in an embodiment of the present invention;
FIG. 1c is a schematic view of a robot according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for clustering commodities provided in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a network structure of a commodity correlation network according to an embodiment of the present invention;
FIG. 4 is a flow chart of another method of clustering commodities provided in an embodiment of the present invention;
FIG. 5 is a schematic flow chart of determining a commodity storage mode according to a commodity clustering result according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a logical partitioning of inventory container bits provided in an embodiment of the invention;
FIG. 7 is a schematic structural diagram of an apparatus for clustering commodities according to an embodiment of the present invention;
fig. 8 is a schematic structural view of an apparatus according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. In addition, it should be noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently, or at the same time. Furthermore, the order of the operations may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Fig. 1a is a schematic system configuration diagram of an inventory system according to an embodiment of the present invention. Referring to fig. 1a, an inventory system 100 may include: the robot 110, the control system 120, the inventory container area 130, and the workstation 140, the inventory container area 130 is provided with a plurality of inventory containers 131, various inventory items can be placed on the inventory containers 131, as well as shelves on which various commodities are placed as seen in supermarkets, as an alternative, the inventory containers 131 can be placed with loading devices such as bins or trays, various inventory items are accommodated in the loading devices, and the plurality of inventory containers 131 are arranged in an array form. Typically, a plurality of workstations 140 may be located on one side of the inventory receptacle region 130.
The control system 120 communicates wirelessly with the robot 110, and a worker can operate the control system 120 via the console 160, and the robot 110 can perform a task of transporting inventory containers under the control of the control system 120. Wherein the inventory receptacles may include, but are not limited to, movable inventory receptacles, and the robot 110 may be a self-driven robot. Taking the inventory container 131 as a movable inventory container, for example, the movable inventory container may be a movable rack, and the robot 110 may travel along an empty space (a part of a passage of the robot 110) in the movable rack array, move to the bottom of the movable rack, lift the movable rack by a lifting mechanism, and carry to the assigned workstation 140.
In one example, the robot 110 may have a lifting mechanism or a hooking structure, and a positioning navigation function, and the robot 110 may be able to travel to the bottom of the inventory container 131 and lift the entire inventory container 131 with the lifting mechanism or pull the entire inventory container 131 with the hooking structure, so that the entire inventory container 131 may be able to move up and down with the lifting mechanism having the lifting function or be pulled with the hooking mechanism.
In another example, the robot 110 can travel forward according to two-dimensional code information captured by a camera, and can travel under the inventory container 131 prompted by the control system 120 according to a route determined by the control system 120. Robot 110 carries inventory receptacles 131 to workstation 140, and a staff member 141 or other automated device (e.g., robotic arm) at workstation 140 performs various types of inventory operations on inventory receptacles 131, including, but not limited to: picking, stocking, restocking, etc. For example, a picking operation, a worker 141 or other automated equipment picks items from inventory receptacles 131 and places them into totes 150 for packaging.
Taking a shelf as an example, fig. 1b is a schematic structural diagram of a shelf according to an embodiment of the present invention. As shown in FIG. 1b, the shelf 131 includes a plurality of compartments on which various items 136 may be placed directly, and four floor-standing posts 1362. In particular embodiments, the items 136 may hang the items 136 from hooks or bars within or on the shelves on which the items 136 can be placed in any suitable manner on the interior or exterior surface of the shelves.
The interlayer of the goods shelf can be provided with a plurality of material boxes which can be separated from the goods shelf or can be integrated with the goods shelf, and one or a plurality of articles can be placed in the material boxes. In addition, the shelf can be a two-way opening shelf, and two articles can be placed in the depth direction of the extension layer, namely one article is placed in each opening direction, or two bins are arranged in the depth direction of the extension layer, namely one bin is arranged in each opening direction. The shelves may also be one-way open shelves (one-way open shelves are shown in fig. 1 b), where the depth direction of the barrier layer may be filled with one item, i.e. only one item is placed in the opening direction, or where the depth direction of the barrier layer is filled with one bin, i.e. only one bin is placed in the opening direction.
Fig. 1c is a schematic structural diagram of a robot according to an embodiment of the present invention. As shown in fig. 1c, in one example, the self-driven robot 110 may include a drive mechanism 1101 by which the self-driven robot 110 is movable within the workspace, and the self-driven robot 110 may further include a lift mechanism 1102 for transporting the racks, and the self-driven robot 110 may move under the target racks 131, lift the target racks 131 with the lift mechanism 1102, and transport to the assigned workstations 140. The lifting mechanism 1102 lifts the entire target shelf 131 from the ground when lifted so that the self-driving robot 110 conveys the target shelf 131, and the lifting mechanism 1102 lowers the target shelf 131 onto the ground. The target recognition module 1103 on the self-driven robot 110 can efficiently recognize the target shelf 131 when the self-driven robot 110 lifts the target shelf 131.
In addition, if based on two-dimensional code navigation, the self-driven robot 110 also includes a navigation recognition component (not shown in FIG. 1 c) for recognizing two-dimensional code markings on the paved surface. The self-driven robot 110 may adopt other navigation modes besides two-dimensional code navigation, such as inertial navigation, SLAM navigation, etc., and may also combine two or more navigation modes simultaneously, such as two-dimensional code navigation and inertial navigation, SLAM navigation and two-dimensional code navigation, etc. Of course, the self-driven robot 110 further comprises a control module (not shown in fig. 1 c) for controlling the entire self-driven robot 110 to perform functions of movement, navigation, etc. In one example, the self-driven robot 110 includes at least two upward and downward cameras, which can travel forward according to two-dimensional code information (other ground identification may be possible) captured by the downward cameras, and can travel to below the target shelf 131 prompted by the control system 120 according to the route determined by the control system 120.
As shown in fig. 1b, a two-dimensional code 1361 is arranged at the center of the bottom of the target shelf 131, and when the self-driven robot 110 runs below the target shelf 131, the two-dimensional code 1361 is accurately shot by an upward camera, so that the self-driven robot 10 is ensured to be positioned right below the target shelf 131, and the self-driven robot 110 can stably lift and transport the target shelf 131.
The control system 120 is a software system running on a server and having data storage and information processing capabilities, and can be connected with a robot, a hardware input system and other software systems by wireless or wire. The control system 120 may include one or more servers, which may be a centralized control architecture or a distributed computing architecture. The server has a processor 1201 and a memory 1202, and may have an order pool 1203 in the memory 1202.
In the inventory system shown in fig. 1, as the warehouse area increases, the distance of movement of the robot in the warehouse increases, and the picking efficiency decreases; warehouse commodity warehouse entry and warehouse exit are real-time dynamic processes, and the position of a goods shelf in a warehouse needs to be adjusted in real time; when an order is selected, the order is required to be subjected to wave combination, so that the efficiency of ex-warehouse can be effectively improved; in the warehouse-crossing sorting scheme, sorting time and station recommendation of sorting are required to be carried out on commodities in warehouse-crossing operation according to the relevance of the commodities, so that warehouse-crossing sorting efficiency can be improved. The various operations in the warehouse, especially for the goods picking operation, are realized by means of the clustering result of the goods. Therefore, there is a need to improve the clustering method of commodities and determine the clustering result of commodities.
The method, the device, the equipment and the storage medium for commodity clustering provided by the embodiment of the invention are described in detail below.
Fig. 2 is a flow chart of a method for clustering commodities provided in the embodiment of the present invention, and the embodiment of the present invention may be applied to a scenario in which commodities are clustered according to relevance of the commodities, especially in a warehouse management center, in order to increase operation efficiency of a warehouse, a situation in which a clustering process is required for a large number of commodities. The method can be implemented by a commodity clustering device, the device can be implemented in a software and/or hardware mode, the device can be integrated on any device with a network communication function, the device can be a terminal device or a server, the terminal device can be a mobile phone, a tablet computer, a computer and the like, and the server can be a background server for data processing or other servers. As shown in fig. 2, the method for clustering commodities in an embodiment of the present invention may include:
s201, mapping commodities into network nodes, mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into association weights between the two network nodes, and constructing a commodity association network between commodities.
In this embodiment, the types of commodities are relatively wide, and the commodities may be tangible commodities, such as clothing, food, etc.; and may be an intangible commodity such as a financial product. In addition, the commodity can have a certain association attribute, the association attribute can be the inherent attribute of the commodity, the commodity is different from the property of other commodities in different fields, and the association between the commodities can also be defined by the behavior of a user. For example, in practical applications, the association attribute between commodities may be a co-occurrence attribute where commodities co-occur with each other, that is, an attribute where two commodities co-occur in the same order. Based on the co-occurrence of the two commodities, a correlation network between the commodities can be constructed. Wherein, the association relation among the commodities included in the commodity association network can be reflected from the commodity association network.
In this embodiment, if two commodities are co-present in the same historical order, it is indicated that the two commodities have co-present association attributes; if the two commodities are not commonly present in the same historical order, the fact that the two commodities do not have the commonly-present association attribute is indicated. In addition, considering that the frequency of two commodities appearing together in the same historical order may be one or more times, different frequencies may reflect the degree of association between the two commodities.
In this embodiment, fig. 3 is a network structure diagram of a commodity correlation network according to the present invention. Referring to fig. 3, in constructing a commodity correlation network between commodities, the commodities may be mapped into network nodes, each of which may represent one dimension. If any two commodities co-appear in the same historical order, adding an edge between network nodes corresponding to the two commodities so as to correlate the two commodities; if the two commodities are not co-present in the same historical order, no edge is added between the network nodes corresponding to the two commodities, namely, the two commodities are not associated.
In this embodiment, referring to fig. 3, considering that the frequency of co-occurrence of two commodities in the same historical order may be one or multiple times, when the commodity correlation network is constructed, the frequency of co-occurrence of commodities corresponding to any two network nodes in the historical order may also be referred to simultaneously. Optionally, the frequency of the co-occurrence of the commodities corresponding to any two network nodes in the historical order may be mapped to an association weight between the two network nodes. The frequency of the co-occurrence of commodities corresponding to the two network nodes in the historical order is in direct proportion to the weight of the added edge between the network nodes corresponding to the two commodities. The more times two commodities are commonly present in one historical order, the greater the weight of the edge between the network nodes corresponding to the two commodities in the built commodity correlation network; the fewer the number of times two items co-occur in a historical order, the less the weight of the edge between the corresponding network nodes of the two items in the item association network. By adopting the mode, the commodity correlation network which is more fit with the actual condition can be constructed according to the actual commodity and commodity correlation condition, so that the actual correlation degree among all commodities can be reflected through the commodity correlation network.
S202, determining characteristic values of commodities corresponding to all network nodes in a commodity correlation network according to a graph embedding algorithm.
In this embodiment, after the commodity correlation network is constructed, each commodity in the commodity correlation network may be used as an object to be evaluated. Aiming at each commodity contained in the commodity correlation network, the commodity correlation network can be processed through a graph embedding algorithm, and characteristic values of the commodities corresponding to the network nodes are extracted from the commodity correlation network. The feature value of the commodity corresponding to the network node may be a feature vector for representing an association relationship between the commodity and other commodities in the commodity association network. Optionally, after the commodity correlation network is constructed, a graph embedding algorithm may be used to process each network node included in the commodity correlation network, and the correlation information of each network node and other network nodes is extracted from the commodity correlation network and is used as a characteristic value of the commodity corresponding to each network node.
In this embodiment, the graph embedding algorithm may include: depth walk algorithms, large-scale information network embedding algorithms, etc. Determining characteristic values of the commodities corresponding to each network node in the commodity correlation network according to the graph embedding algorithm may include: and calculating characteristic values of the commodities corresponding to each network node in the commodity correlation network by adopting a deep walk algorithm or a large-scale information network embedding algorithm.
In an alternative manner of this embodiment, the calculation of the feature value of the commodity corresponding to each network node in the commodity correlation network by using the deep walk algorithm may include the following steps S2021a to S2021b:
s2021a, uniformly and randomly sampling a network node from a commodity association network as a starting point of the random walk when carrying out random walk each time, uniformly and randomly sampling an adjacent point with association weight for the last accessed node in the walk process until the walk reaches a preset maximum length to finish the random walk, and finally obtaining a plurality of node sequences.
S2021b, training the plurality of node sequences through machine learning to obtain characteristic value vectors of commodities corresponding to each network node.
In the embodiment, implicit characterization information of each network node in the commodity correlation network can be learned through a deep walk algorithm. The implicit characterization information can be understood as implicit association information between commodities corresponding to each network node reflected in the commodity association network.
In this embodiment, a random walk generator may be used to uniformly select at least one network node from the commodity correlation network, and a deep walk algorithm may be used to perform a random walk process on each selected network node. Optionally, when each random walk is performed, a random walk generator may be used to uniformly and randomly sample a network node from the commodity association network as a starting point of the random walk, and each walk uniformly and randomly samples an adjacent point with an association weight for the network node accessed last until reaching the maximum length, so as to obtain a walked network node combination of the random walk as a node sequence of the random walk. In the manner, a plurality of network nodes can be uniformly sampled from the commodity correlation network by using a random walk generator as the starting point of each random walk, and a plurality of node sequences can be finally obtained through a plurality of random walk processes.
In this embodiment, after obtaining a plurality of network node sequences, the obtained plurality of node sequences may be trained by a preset machine learning model, so as to map each network node in the node sequence obtained by random walk into a continuous vector space, thereby obtaining a feature value corresponding to each network node in the commodity correlation network. The depth walk algorithm can obtain a plurality of node sequences from the commodity correlation network in a random walk mode, and then the correlation feature vectors existing among all network nodes are learned from the node sequences through training the node sequences, so that feature values of commodities corresponding to all network nodes included in the commodity correlation network can be obtained.
Illustratively, referring to fig. 3, the commodity correlation network may include a plurality of network nodes and correlation weights between the respective network nodes. The commodity correlation network can be represented by a commodity correlation graph G= (V, E), in the commodity correlation network G= (V, E), wherein V represents the commodity type in the commodity correlation network, E represents the connection of the points in V, and different networks are named by adopting different symbols VAnd the node uses a storage structure of the two-dimensional array to represent whether a connecting edge exists between two network nodes, wherein the existence of the connecting edge is 1, and otherwise, the existence of the connecting edge is 0. The specific process is as follows: in each random walk process, a network node V can be randomly and uniformly selected from a commodity correlation network G= (V, E) by adopting a deep random walk algorithm i And select the network node v i And carrying out random walk as a starting point of the current random walk, so that a walked network node combination of the current random walk can be obtained and used as a node sequence of the current random walk. By uniformly sampling a plurality of network nodes from the commodity correlation network as the starting points of each random walk respectively, a plurality of node sequences can be finally obtained through a plurality of random walk processes. After constructing and generating a plurality of node sequences with fixed length, training the constructed and generated node sequences by adopting a Skip-gram model, learning and training from intermediate network nodes to obtain low-dimensional feature vectors corresponding to all network nodes, and taking the low-dimensional feature vectors corresponding to all network nodes as feature values of commodities corresponding to all network nodes included in a commodity correlation network. For example, the plurality of node sequences acquired by random walk may specifically be: 1-4-13-1-11-5-7- …, 33-34-10-3-20-25 …, 28-24-30-27-9-21- …, and further training the node sequence to obtain a low-dimensional feature vector corresponding to each network node in the commodity correlation network, so as to obtain the feature value of the commodity corresponding to each network node. Referring to fig. 3, the characteristic values of the commodity corresponding to the network node 1 may be: 0.016579, -0.0336, 0.3452167, 0.04698 …; the characteristic value of the commodity corresponding to the network node 2 may be: 0.00703, 0.26589, -0.351422, 0.043923 ….
In this embodiment, by adopting the above technical solution, when extracting the feature value of the commodity corresponding to each network node from the commodity correlation network, the characteristics of the self-adaptability of the deep walk algorithm (after newly adding the network node, without relearning), the rationality (the probability of classifying the network nodes with similar feature vectors into the same class is large), the low latitude (the feature vectors with low dimensionality can be generated to accelerate the classification efficiency of the commodity), and the continuity (the order expression can be performed in the continuous space, and the classification effect is increased) are fully utilized, so that the feature value of the commodity corresponding to each network node can be better extracted from the commodity correlation network.
Although the correlation information among the network nodes can be extracted from the commodity correlation network as far as possible through the depth migration algorithm to obtain the characteristic value of the commodity corresponding to each network node, the depth migration algorithm only considers the first-order proximity of the commodity, and the information of the deeper hidden multi-order proximity in the commodity correlation network cannot be effectively obtained. In view of the above, the embodiment of the invention can extract the information of deeper hidden multi-order proximity from the commodity correlation network by adopting a large-scale information network embedding algorithm.
In an alternative manner of this embodiment, calculating the feature value of the commodity corresponding to each network node in the commodity correlation network by using the large-scale information network embedding algorithm may include the following steps S2022a to S2022c:
s2022a, determining first-order similarity among all network nodes in the commodity correlation network, and optimizing the first-order similarity among all network nodes to obtain a first characteristic value vector of the commodity corresponding to each network node.
S2022b, determining the second-order similarity among the network nodes in the commodity correlation network, and optimizing the second-order similarity among the network nodes to obtain a second characteristic value vector of the commodity corresponding to each network node.
S2022c, splicing the first eigenvalue vector and the second eigenvalue vector to obtain eigenvalue vectors of commodities corresponding to each network node.
In this embodiment, the first-order similarity and the second-order similarity may be introduced at the same time, and the combination of the first-order similarity and the second-order similarity is used to extract the hidden multi-order proximity information from the commodity correlation network, so as to extract the characteristic value of the commodity corresponding to each network node from the commodity correlation network.
In this embodiment, the first-order similarity in the commodity correlation network may refer to a local pairwise similarity between two network nodes, and the weight of the edge connected between the two network nodes may be used to represent the first-order similarity between the two network nodes . If there is no edge between two network nodes, the first-order similarity between two network nodes is 0. The second-order similarity in the commodity correlation network may refer to the similarity of neighbor network structures in the commodity correlation network, for example, p is used in the commodity correlation network u Representing first-order similarity between network node u and other adjacent network nodes, using p v Representing first-order similarity between the network node v and other adjacent network nodes, and the second-order similarity between the corresponding network node v and the network node u is p u And p v Similarity between them. If no other network node is connected to network node u and network node v, the second order similarity between network node v and network node u is 0.
In this embodiment, in order to ensure accuracy of the obtained first-order similarity, after determining the first-order similarity between the network nodes in the commodity correlation network, the first-order similarity between the network nodes may be optimized, so as to obtain a first eigenvalue vector of the commodity corresponding to each network node; in addition, the second-order similarity between the network nodes in the commodity correlation network can be determined according to the first-order similarity between the network nodes, and the second-order similarity between the network nodes is optimized, so that the second characteristic value vector of the commodity corresponding to the network nodes can be obtained.
In this embodiment, after the first eigenvalue vector and the second eigenvalue vector of the commodity corresponding to each network node are obtained, the first eigenvalue vector and the second eigenvalue vector may be subjected to splicing processing, so as to obtain a third eigenvalue vector corresponding to each network node, and the third eigenvalue vector is used as the eigenvalue vector of the commodity corresponding to each network node. Further, it is considered that the first eigenvalue vector and the second eigenvalue vector do not necessarily both satisfy the condition of minimum similarity. In other words, even if the first-order similarity represented by the first eigenvalue vector alone satisfies the minimum similarity condition and the second-order similarity represented by the second eigenvalue vector alone satisfies the minimum similarity condition, it does not represent that the similarity represented by the third eigenvalue vector after concatenation satisfies the minimum similarity condition. For this purpose, a weight ratio may be set for the first eigenvalue vector and the second eigenvalue vector, respectively, by which the third eigenvalue vector after splicing is balanced. For example, taking the first eigenvalue vector as a, the second eigenvalue vector as B as an example, and the third eigenvalue vector after splicing is c= [ a; b, normalizing the first eigenvalue vector a to set a weight beta, normalizing the second eigenvalue vector B to set a weight gamma, and obtaining a third eigenvalue vector C' = [ beta ] a after weight balance; and gamma is equal to B, and the third eigenvalue vector C' after weight balance is taken as the eigenvalue vector of the commodity corresponding to each network node, thus obtaining the eigenvalue of the commodity corresponding to each network node.
In this embodiment, in order to better perform the stitching process on the first eigenvalue vector and the second eigenvalue vector, the normalization process may be performed on the first eigenvalue vector and the second eigenvalue vector, and the first eigenvalue vector and the second eigenvalue vector after the normalization process may be stitched, so as to obtain a third eigenvalue vector after the stitching process. Optionally, when the first eigenvalue vector and the second eigenvalue vector after the unification processing are spliced, the weight proportion of the first eigenvalue vector and the second eigenvalue vector can be balanced so as to obtain accurate eigenvalue vectors of commodities corresponding to each network node.
In this embodiment, the commodity correlation network may be represented by a commodity correlation graph g= (V, E), where V represents the commodity category in the commodity correlation network, E represents the connection of points in V, and each pair of pairs is an ordered pair e= (u, V) and has a weight w greater than zero uv Indicating how many orders in all orders contain both u, v products. A large-scale network algorithm can be used to map each network node v in the commodity correlation diagram to a low-dimensional space R d In (1) learning a function f G :V→R d Where d < |V| and thus in space R d The first order similarity and the second order similarity are reserved. The following description is made for an exemplary description of the first-order similarity optimization process and the second-order similarity optimization process.
(1) The case of performing optimization processing on the first-order similarity:
specifically, two network nodes V are defined for each edge (i, j) in the commodity correlation graph g= (V, E) i ，v j The connection probability between the network nodes can be specifically:
wherein u is i Is v i Is distributed in V x V space defined by commodity correlation diagram g= (V, E), empirical distributionWherein (1)>
To preserve the first order similarity, the following objective function may be reduced:where d is the distance between the two distributions.
By reducing the KL divergence of the two probability distributions, replacing the distance function with the KL divergence and removing the constants, one can obtain:find +.>Each point in d-dimensional space can be represented and a first eigenvalue vector can be derived.
(2) And (3) the condition of optimizing the second-order similarity:
specifically, given a hypothetical directed commodity correlation graph g= (V, E), assuming that any network node shares multiple connections with other network nodes, each network node has two cases: network node itself and external nodes of other network nodes, at which time two vectors are introduced V respectively representing network nodes i And v as external node i For each directed edge (i, j) first define an environment v j Generating a network node v i Probability of (2):
where V is the number of network nodes or environments. For each network node v i P is as above 2 (v j ,v i ) A distribution of environmental conditions is determined.
To preserve second order similarity, the conditional distribution should be determined from the low-dimensional representation to approximate the empirical distributionThe simplest approach is to reduce the following objective function:
where d (·, ·) represents the distance between two distributions, and λ is introduced due to the different importance of the network nodes in the commodity correlation graph g= (V, E) i To represent the importance that the network node i can measure by the degree or algorithm.
Empirical distributionWherein w is ij Representing the weight of edge (i, j), d i Is the degree of departure of node i, to simplify the calculation, KL divergence is introduced as a distance function, lambda is taken as i Set to the degree d i And removing the constant to obtain the following objective function:
through learningAnd->To reduce the objective function of the above formula, the d-dimensional vector can be used>Representing each node v i Thus, a second eigenvalue vector can be obtained.
After the optimization processing of the first-order similarity and the second-order similarity, a first eigenvalue vector and a second eigenvalue vector can be obtained, and the eigenvalue vector of the commodity corresponding to each network node can be obtained by performing splicing processing on the first eigenvalue vector and the second eigenvalue vector.
In the present embodiment, the objective function O is trained in combination of the first-order similarity and the second-order similarity 1 And an objective function O 2 In consideration of calculating the conditional probability p 2 When all nodes need to be accumulated, the cost is very high, so that 'negative sampling' is introduced, a plurality of negative edges are sampled according to the noise distribution of edges (i, j) among the nodes, and the following functions are specified for the edges among the nodes:
where σ (x) =1/(1+exp (-x)), the first term is to construct the observation edge, the second term constructs the negative edge drawn by the noise distribution, and K is the negative edge number. Order theWherein d is v Is the degree of egress of node v. In addition, to optimize the above equation, an asynchronous random gradient Algorithm (ASGD) may be employed for optimization.
And S203, clustering the commodities according to characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes.
In this embodiment, after the characteristic values of the commodities corresponding to the network nodes in the commodity correlation network, the commodities corresponding to the network nodes included in the commodity correlation network may be clustered according to the characteristic values of the commodities corresponding to the network nodes by a preset clustering algorithm. According to the clustering result of the commodities corresponding to each network node, the commodities corresponding to each network node included in the commodity correlation network can be distributed to different commodity classes, so that a plurality of commodity classes can be obtained. The preset clustering algorithm can be used for carrying out clustering analysis on commodities corresponding to all network nodes included in the commodity correlation network. Alternatively, the preset clustering algorithm may include, but is not limited to, K-means clustering (K-means), spectral clustering, and the like.
In this embodiment, clustering in this embodiment may be understood as dividing a set of commodities including a plurality of commodities into different classes or clusters according to a certain specific standard, so that the similarity of the commodities in the same class or cluster is as large as possible, and the variability of the commodities in different classes or clusters is also as large as possible.
In an optional manner of this embodiment, after determining the feature value of the commodity corresponding to each network node in the commodity correlation network according to the graph embedding algorithm, the method may further include:
and taking the characteristic value as a dimension, and performing dimension reduction processing on the characteristic value of the commodity corresponding to each network node in the commodity correlation network.
In this embodiment, after determining the feature value of the commodity corresponding to each network node in the commodity correlation network according to the graph embedding algorithm, the dimension of the feature value of the commodity corresponding to each network node may be still relatively high, and invalid data may exist in the feature value of the commodity corresponding to each network node. If the feature value dimension of the commodity corresponding to the network node is higher or invalid data exists, the complexity of data processing is increased when clustering is performed according to the feature value of the commodity corresponding to each network node, so that the clustering efficiency of the commodity is affected. Therefore, a preset dimension reduction algorithm can be adopted to take the characteristic value of the commodity corresponding to each network node as a dimension, and dimension reduction can be carried out on the characteristic value of the commodity corresponding to each network node in the commodity correlation network. The preset dimension reduction algorithm can comprise Principal Component Analysis (PCA), equidistant mapping (Isomap), laplace feature mapping (LE), local Linear Embedding (LLE), t-distributed random neighborhood embedding (t-SNE) and other algorithms.
According to the technical scheme, the commodity is mapped into the network nodes, the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order is mapped into the association weight between the two network nodes, the commodity association network between the commodities is constructed, the characteristic value of the commodity corresponding to each network node in the commodity association network is determined according to the graph embedding algorithm, the characteristic that obvious association between the commodities cannot be seen from the description content of the commodity can be extracted, and therefore clustering can be carried out on each commodity according to the characteristic value of the commodity corresponding to each network node, so that a plurality of commodity categories are obtained, different commodities are clustered, the clustering effect between the commodities is improved, and the subsequent commodity sorting efficiency is greatly improved.
FIG. 4 is a flow chart of another method for clustering commodities provided in an embodiment of the present invention, which is optimized based on the above embodiment, and which may be combined with each of the alternatives in one or more embodiments. As shown in fig. 4, the method for clustering commodities in an embodiment of the present invention may include:
S401, mapping commodities into network nodes, mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into association weights between the two network nodes, and constructing a commodity association network between commodities.
S402, determining characteristic values of commodities corresponding to all network nodes in the commodity correlation network according to a graph embedding algorithm.
S403, clustering the commodities according to characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes.
S404, determining a commodity storage mode, an order wave-grouping mode, a goods shelf adjustment mode and/or a warehouse-crossing sorting mode in a warehouse according to the acquired multiple commodity types.
In this embodiment, each commodity may be correspondingly provided with a unique SKU, and SKUs of commodities belonging to a commodity class may be located in the same SKU cluster. SKU (Stock Keeping Unit, stock unit) is a unit of stock in and out metering and may be in units of pieces, boxes, trays, etc. The SKUs involved in the embodiments of the present application may be referred to as simply the unified numbering of inventory items, where each inventory corresponds to a unique SKU number. SKUs may be understood as the uniform number or unique identification number of an item of inventory, through which the identity of each item may be identified.
According to the technical scheme provided by the embodiment of the invention, the problem that the commodities with obvious relations among the commodities cannot be clustered well is solved, the clustering of different commodities is realized, and the clustering effect among the commodities is improved, so that the instruction of a commodity storage mode, an order group wave mode, a goods shelf adjustment mode and/or a warehouse-crossing sorting mode in a warehouse can be realized according to the clustering result.
The following describes the operation steps of determining a commodity storage mode, an order wave-grouping mode, a shelf adjustment mode and/or a warehouse-crossing sorting mode in a warehouse according to a plurality of acquired commodity types.
In an application scenario scheme of the present embodiment, a detailed scheme for determining a commodity storage mode according to a commodity clustering result is provided in the present embodiment. Fig. 5 is a schematic flow chart of determining a commodity storage mode according to a commodity clustering result in the embodiment of the present invention. The present embodiment is optimized on the basis of the above embodiment. As shown in fig. 5, the step of determining a commodity storage mode according to a commodity clustering result provided in the embodiment of the present invention may include:
s501, dividing an inventory system of a warehouse into a plurality of logic partitions according to a plurality of acquired commodity types; any one stock container and any one station in the stock system has its associated logical partition.
In this embodiment, compared with the conventional scheme of performing order processing based on physical partition, the technical scheme of this embodiment processes orders based on logical partition. In other words, with the solution of the present embodiment, when processing an order, the order is not processed according to the physical partition, but is processed according to the logical partition. Wherein, the logical partition management does not traditionally perform partition management on the inventory system according to the actual position, but performs partition management on the inventory system from a logical point of view.
In this embodiment, a fixed inventory container location is provided in the inventory system, and inventory containers may be placed at corresponding inventory container locations. Each inventory container location may correspond to only one inventory container at any one time, and each inventory container may only be placed on the corresponding inventory container location. Of course, the correspondence between the inventory container position and the inventory container can be adaptively adjusted according to the position adjustment of the inventory container in the inventory system.
In this embodiment, a plurality of logical partitions may be included in the inventory system, each logical partition in the inventory system may be associated with at least one workstation in the inventory system (in one alternative, one logical partition is associated with one workstation in the inventory system) and a plurality of inventory containers and a plurality of inventory container bits, the sum of all the inventory containers associated with all the logical partitions being at least a portion or even all of all the inventory containers in the inventory system, and the sum of all the inventory container bits associated with all the logical partitions being at least a portion or even all of all the inventory container bits in the inventory system. The inventory receptacles may include shelves or other forms of receptacles on which trays, bins, etc. may be placed for carrying items.
In an alternative manner of this embodiment, the inventory system of the warehouse is divided into a plurality of logical partitions according to the acquired plurality of categories of goods, and the following steps S501a to S501d may be included:
s501a, determining a plurality of logical partitions according to the acquired plurality of commodity classes.
In this embodiment, each commodity class corresponds to one logical partition, or each logical partition may correspond to a plurality of commodity classes. Preferably, each commodity class corresponds to a logical partition. After the acquired multiple commodity classes, the division number in the process of logically dividing the inventory system can be determined according to the acquired multiple commodity classes so as to ensure that each commodity class corresponds to at least one logical division.
S501b, dividing the inventory container in the inventory system into logical partitions corresponding to the commodity classes with high overlap ratio according to the overlap ratio between the inventory commodity on the inventory container in the inventory system and the commodity in each commodity class.
In this embodiment, one or more inventory items may be stored in each inventory container of the inventory system, and there may be a certain difference between inventory items stored in different inventory containers, that is, inventory items stored in different inventory containers may be identical, may be different, or may be partially identical while another portion is different. For this reason, for each inventory container in the inventory system, the commodities stored in each inventory container may be respectively matched with the commodities in each commodity class, and the inventory containers in the inventory system may be divided into logical partitions corresponding to the commodity classes with high overlap ratio according to the overlap ratio between the inventory commodity in the inventory container and the commodities in each commodity class.
In the present embodiment, the stock container having the highest commodity overlap ratio may be divided into logical partitions corresponding to the matched commodity classes according to the overlap ratio between the commodity on the stock container and the commodity included in the commodity class. Optionally, the method may sort the inventory containers according to the coincidence degree between the commodities on the inventory containers and the commodities contained in the commodity class, and divide the inventory containers with the preset number in front of the sorting into the logical partitions corresponding to the commodity class matched with the inventory containers.
Illustratively, an inventory system includes three inventory receptacles and two categories of goods. The three stock containers are respectively a first stock container, a second stock container and a third stock container. Wherein the first inventory container stores a first commodity, a second commodity, a third commodity and a fourth commodity; the second inventory container stores a second commodity, a third commodity and a fourth commodity; the third stock container stores the first commodity, the fifth commodity, the sixth commodity and the seventh commodity. The two commodity classes are respectively a commodity class of the first logical partition and a commodity class of the second logical partition. Wherein the commodity class of the first logical partition includes: the first commodity, the second commodity, the third commodity and the fourth commodity, the commodity class of the second logical partition includes: the first commodity, the fifth commodity, the sixth commodity and the seventh commodity.
It is readily apparent that the items stored on the first stock container are all identical to the items contained in the first logically partitioned category of items, that the items stored on the second stock container are 3 identical items to the items contained in the first logically partitioned category of items, and that the items stored on the third stock container are only 1 identical item to the items contained in the first logically partitioned category of items. At this time, the first stock container, the second stock container, and the third stock container are sequentially arranged in order according to the degree of overlap between the commodity on each stock container and the commodity included in the commodity class of the first logical partition. And similarly, sorting according to the degree of coincidence between the commodities on each stock container and the commodities contained in the commodity class of the second logical partition, and sequentially arranging a third stock container, a second stock container and a first stock container.
Based on the analysis, the first inventory container having the highest degree of overlap with the commodity included in the commodity class of the first logical partition may be divided into the first logical partition, and the third inventory container having the highest degree of overlap with the commodity included in the commodity class of the second logical partition may be divided into the second logical partition.
S501c, dividing the inventory container bits in the inventory system into different logical partitions according to the quantity of the inventory containers associated with each logical partition.
In this embodiment, after each inventory container in the inventory system is divided into logical partitions to which each inventory container belongs, each logical partition may be associated with at least one inventory container. Whereas each inventory container location may correspond to only one inventory container at any one time, each inventory container may only be placed on the corresponding inventory container location. For this reason, after each inventory container in the inventory system is divided into logical partitions to which each inventory container belongs, it is also necessary to divide the inventory container bits in the inventory system into logical partitions. Specifically, the inventory container bits in the inventory system can be divided into different logical partitions according to the number of inventory containers associated with each logical partition. In order to ensure that the inventory containers of the same logical partition are placed in the same position range as far as possible, the inventory container positions in the inventory system can be sequentially divided into different logical partitions according to the quantity of the inventory containers associated with each logical partition and a preset azimuth sequence. The preset azimuth sequence may be understood as an azimuth sequence from left to right, right to left, front to back, or back to front.
Illustratively, FIG. 6 is a schematic diagram of a logical partitioning of inventory container bits provided in an embodiment of the invention. Referring to fig. 6, taking the example of dividing the inventory system into a first logical partition, a second logical partition and a third logical partition, the number of inventory containers associated with the first logical partition is 20, the number of inventory containers associated with the second logical partition is 30, and the number of inventory containers associated with the third logical partition is 40, the division of 20 inventory container bits into the first logical partition, the division of 30 inventory container bits into the second logical partition and the division of 40 inventory container bits into the third logical partition may be implemented according to the number of inventory containers associated with each logical partition, in order of left to right orientation.
S501d, dividing the stations in the inventory system into logic partitions close to the stations according to the distances between the stations and the inventory container positions associated with the logic partitions.
In this embodiment, there may be a plurality of stations in the inventory system, and the distances from different inventory container positions to the same station may be different, and the distances from different stations to the same inventory container position may be different, based on the positional relationship between each station and the inventory container position associated with each logical partition. For this purpose, the stations in the inventory system may be divided into logical partitions that are closer to each other according to the distance between the stations and the inventory container locations associated with each logical partition, so as to ensure that the distance from each station to the inventory container location in each logical partition is as short as possible. In this way, when the robot is required to be controlled to carry the inventory container in the inventory container position to the station, the station and the inventory container can be ensured to belong to the same associated logical partition, and the distance between the station and the inventory container is ensured to be as short as possible, so that the carrying distance of the robot is reduced.
In this embodiment, optionally, for each station located in the inventory system, a distance between each station and the inventory container bits associated with the respective logical partition is calculated, a logical partition closest to the distance between the station located in the inventory system and the inventory container bits associated with the logical partition is determined, and the station located in the inventory system is partitioned into the logical partition closest to the distance. Optionally, for each station in the inventory system, calculating a distance between each station and the inventory container position associated with each logical partition, sorting the obtained distances, determining a preset number of logical partitions sorted in front, and dividing the station in the inventory system into the preset number of logical partitions sorted in front.
In this embodiment, optionally, dividing the workstation located in the inventory system into logical partitions located closer thereto according to the distance between the workstation and the inventory container locations associated with each logical partition includes: according to the position relation between the stock container positions associated with each logical partition and each station, calculating a first transportation distance required by each stock container position in the stock container positions associated with each logical partition to reach each station, and calculating a second transportation distance required by each station to reach the stock container positions associated with each logical partition; stations located in the inventory system are partitioned into logical partitions proximate thereto according to the first transportation distance and the second transportation distance.
S502, determining a logical partition to which a target order belongs from a plurality of logical partitions as a target logical partition when processing the target order; wherein, a logical partition associates at least one station and a plurality of stock containers, and at least one stock container in the plurality of stock containers associated with the target logical partition holds the stock goods required by the target order.
In this embodiment, one logical partition may be associated with at least one workstation, and one logical partition may be associated with a plurality of inventory receptacles. The target order may include the required inventory item information. At least one of the plurality of inventory receptacles associated with the target logical partition holds inventory items required for the target order. Illustratively, referring to FIG. 1, for example, the inventory system shown in FIG. 1 may include stations in workstation 140, inventory containers in inventory container zone 130, and robots 110. Each logical partition in the inventory system may be associated with at least one workstation located at workstation 140, and each logical partition may be associated with a plurality of inventory receptacles located in inventory receptacle zone 130. Wherein inventory receptacles located in inventory receptacle area 130 may be used to store inventory items.
S503, distributing the target order to one station associated with the target logical partition as a target station.
In this embodiment, in view of that in the inventory system, each logical partition may be associated with at least one station, after determining the target logical partition to which the target order belongs, the stations associated with the target logical partition may include a plurality of stations, and any one station may be selected as the target station.
S504, the control robot conveys a target stock container containing the stock articles required by the target order among the stock containers associated with the target logical partition to a target station.
In this embodiment, after the target order is assigned to the target station associated with the target logical partition, the robot may be controlled to carry the target inventory container (i.e., the inventory container containing the inventory item required for the target order among the plurality of inventory containers associated with the target logical partition) to the target station. At the corresponding target station, a worker or automated equipment may grasp the inventory items required for the target order from the target inventory container and place them into the order container for packaging. Of course, task operations such as article restocking and article inventory may be performed in addition to the operation of picking articles.
By adopting the technical scheme of the embodiment, the loading strategy of the commodities in the warehouse area can be guided according to the acquired multiple commodities, the logical partition of the warehouse area is realized, and only specific types of commodities are stored in each logical partition, so that the probability of long-distance conveying of the inventory containers by the robot is reduced, the average conveying distance of conveying the inventory containers by the robot is reduced, and the conveying efficiency is improved.
In another application scenario scheme of the present embodiment, a detailed scheme for determining an order wave grouping mode according to a commodity clustering result is provided in the present embodiment. The step of determining the order wave combining mode according to the commodity clustering result provided by the embodiment of the invention can comprise the following steps:
and combining different orders corresponding to different commodities contained in the same commodity class into the same order wave order task according to the acquired multiple commodity classes so as to distribute the order wave order task to the same workstation to execute the picking task.
In this embodiment, taking the first commodity and the second commodity under the same commodity class, the first order includes the first commodity, the second order includes the second commodity as an example, after obtaining a plurality of commodity classes, according to the clustering result between the first commodity and the second commodity, it can be known that the first commodity and the second commodity are located in the same commodity class, and the first order and the second order can be grouped into one wave and allocated to the same workstation to execute the task.
The technical scheme of the embodiment has the advantages that the first commodity and the second commodity are placed on the same stock container or two adjacent stock containers, and when the workstation processes the first order and the second order in one wave task, the workstation can hit as few stock containers as possible and pick the goods, so that the goods picking efficiency is improved, and the carrying times of the stock containers are reduced.
In still another application scenario scheme of the present embodiment, a detailed scheme for determining a shelf adjustment mode according to a commodity clustering result is provided in the present embodiment. The step of determining the goods shelf adjustment mode according to the goods clustering result provided by the embodiment of the invention can comprise the following steps:
according to the acquired multiple commodities, placing all commodities contained in the same commodity on an inventory container meeting the preset distance condition; or, according to the plurality of acquired goods, the plurality of goods which are placed on the stock container meeting the preset distance condition and are not contained in the same goods are peeled off.
In this embodiment, the inventory containers of the preset distance condition are the same inventory container, or a plurality of inventory containers with a distance between inventory containers smaller than or equal to the preset distance threshold.
The technical scheme of the embodiment has the beneficial effects that as the warehouse entry and the warehouse exit of the warehouse commodity are a real-time dynamic process, the clustering result of each commodity can be utilized to provide a guiding principle for the adjustment of the inventory container, the position of the warehouse is adjusted in time, and the conveying distance and the conveying efficiency of the robot in conveying the inventory container are reduced.
In still another application scenario scheme of the present embodiment, a detailed scheme for determining a cross-warehouse sorting mode according to a commodity clustering result is provided in the present embodiment. The step of determining the cross-warehouse sorting mode according to the commodity clustering result provided by the embodiment of the invention can comprise the following steps:
dividing each store into different store combinations according to the coincidence degree between the goods contained in each goods class and the goods required by each store order;
the same sorting time period is allocated to a plurality of stores belonging to the same store combination so that the plurality of stores belonging to the same store combination perform the commodity sorting operation in the same sorting time period.
In this embodiment, the concept of the warehouse crossing is to cross the warehouse link, generally apply to the sorting of goods in the store, and allocate the goods to the store at regular time, when the goods are required to be allocated, the goods are directly sent from the supplier (the sent goods are bulk goods placed on the tray), then the goods are sorted according to the store and then directly sent to the store, and the goods do not need to be stored in the warehouse for a long time to wait for allocation to the store, so that the use fee required by the warehouse is saved. Therefore, the origin of the over-warehouse sorting scenario is limited and not as large as the warehouse.
In this embodiment, after obtaining a plurality of products, each of the stores may be divided into different store combinations according to the degree of coincidence between the products included in each product and the products required for each store order, and the same sorting time period may be allocated to the stores belonging to the same store combination, so that the stores belonging to the same store combination may perform the product sorting operation within the same sorting time period.
By adopting the technical scheme of the embodiment, a plurality of shops belonging to the same shop combination can be arranged in the same time period for sorting, for example, the shops 1 and 2 are all placed in the morning for sorting, so that trays can be used as little as possible during sorting, and more shops can be processed as much as possible under the condition that the warehouse-crossing sorting field is limited and only limited sorting stations can be accommodated.
Fig. 7 is a schematic structural diagram of a device for clustering commodities provided in an embodiment of the present invention, and the embodiment of the present invention may be applied to a scenario in which commodities are clustered according to commodity relevance. The apparatus may be implemented in software and/or hardware, and the apparatus may be integrated on any device having network communication functionality.
As shown in fig. 7, the apparatus for clustering commodities in an embodiment of the present invention may include: a construction module 701, a determination module 702 and a clustering module 703. Wherein:
the construction module 701 is configured to map a commodity to a network node, map frequencies of co-occurrence of commodities corresponding to any two network nodes in a historical order to association weights between the two network nodes, and construct a commodity association network between commodities;
the determining module 702 is configured to determine a feature value of a commodity corresponding to each network node in the commodity correlation network according to a graph embedding algorithm;
and the clustering module 703 is used for clustering the commodities according to the characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes.
On the basis of the above embodiment, optionally, the apparatus may further include:
and the application module 704 is used for determining a commodity storage mode, an order wave-grouping mode, a goods shelf adjustment mode and/or a warehouse-crossing sorting mode in the warehouse according to the acquired multiple commodity types.
Based on the above embodiments, optionally, the application module 704 may include:
the logic partition dividing unit is used for dividing the inventory system of the warehouse into a plurality of logic partitions according to the acquired plurality of commodity types; any one stock container and any one station in the stock system are provided with a logic partition to which the stock container belongs;
A target partition determination unit configured to determine, when one target order is processed, a logical partition to which the target order belongs from among a plurality of logical partitions, as a target logical partition; wherein one of the logical partitions is associated with at least one station and a plurality of inventory containers, and at least one inventory container of the plurality of inventory containers associated with the target logical partition is used for containing inventory items required by the target order;
the target order allocation unit is used for allocating the target order to one station associated with the target logical partition as a target station;
and the target order processing unit is used for controlling the robot to convey the target inventory container containing the inventory items required by the target order to the target station.
Based on the above embodiments, optionally, the application module 704 may include:
the logic partition determining subunit is used for determining a plurality of logic partitions according to the acquired plurality of commodity types;
the first dividing subunit is used for dividing the inventory containers in the inventory system into logic partitions corresponding to the commodity classes with high overlap ratio according to the overlap ratio between the inventory commodity on the inventory container in the inventory system and the commodity in each commodity class;
The second dividing subunit is used for dividing the inventory container bits in the inventory system into different logic partitions according to the quantity of the inventory containers associated with each logic partition;
and the third dividing subunit is used for dividing the stations in the inventory system into logic partitions close to the stations according to the distances between the stations and the inventory container positions associated with each logic partition.
Based on the above embodiments, optionally, the application module 704 may include:
and the order combining unit is used for combining different orders corresponding to different commodities contained in the same commodity class into the same order wave order task according to the acquired multiple commodity classes so as to distribute the order wave order task to the same workstation to execute the picking task.
Based on the above embodiments, optionally, the application module 704 may include:
the first goods shelf adjusting unit is used for placing all goods contained in the same goods on an inventory container meeting the preset distance condition according to the acquired multiple goods; or alternatively, the process may be performed,
and the second goods shelf adjusting unit is used for stripping the goods which are not contained in the same goods class and are placed on the inventory container meeting the preset distance condition according to the acquired goods class.
Based on the foregoing embodiment, optionally, the inventory containers of the preset distance condition are the same inventory container, or a plurality of inventory containers with distances between inventory containers smaller than or equal to a preset distance threshold.
Based on the above embodiments, optionally, the application module 704 may include:
the store dividing unit is used for dividing each store into different store combinations according to the coincidence degree between the goods contained in each goods class and the goods required by each store order;
and the sorting time distribution unit is used for distributing the same sorting time period to a plurality of shops belonging to the same shop combination so as to enable the plurality of shops belonging to the same shop combination to perform commodity sorting operation in the same sorting time period.
On the basis of the above embodiment, optionally, the apparatus may further include:
the dimension reduction processing module 705 is configured to take a feature value as a dimension, and perform dimension reduction processing on feature values of commodities corresponding to each network node in the commodity correlation network.
Based on the above embodiments, optionally, the determining module 702 may include:
and the characteristic value determining unit is used for calculating the characteristic value of the commodity corresponding to each network node in the commodity correlation network by adopting a deep walk algorithm or a large-scale information network embedding algorithm.
On the basis of the above embodiment, optionally, the feature value determining unit is configured to:
when each random walk is carried out, uniformly and randomly sampling a network node from the commodity correlation network as a starting point of the random walk, uniformly and randomly sampling an adjacent point with correlation weight for the last accessed node in the walk process until the walk reaches a preset maximum length to finish the random walk, and finally obtaining a plurality of node sequences;
training the plurality of node sequences through machine learning to obtain characteristic value vectors of commodities corresponding to each network node.
On the basis of the above embodiment, optionally, the feature value determining unit is configured to:
determining first-order similarity among network nodes in the commodity correlation network, and optimizing the first-order similarity among the network nodes to obtain a first characteristic value vector of the commodity corresponding to each network node;
determining the second-order similarity among all network nodes in the commodity correlation network, and optimizing the second-order similarity among all network nodes to obtain a second characteristic value vector of commodities corresponding to all network nodes;
and splicing the first eigenvalue vector and the second eigenvalue vector to obtain eigenvalue vectors of commodities corresponding to each network node.
The commodity clustering device provided by the embodiment of the invention can execute the commodity clustering method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the commodity clustering method.
Fig. 8 is a schematic structural view of an apparatus according to an embodiment of the present invention. Fig. 8 illustrates a block diagram of an exemplary device 812 suitable for use in implementing embodiments of the present invention. The device 812 shown in fig. 8 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in FIG. 8, device 812 is in the form of a general purpose computing device. Components of device 812 may include, but are not limited to: one or more processors or processing units 816, a system memory 828, and a bus 818 that connects the various system components, including the system memory 828 and the processing unit 816.
Bus 818 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Device 812 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by device 812 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 828 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 830 and/or cache memory 832. Device 812 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 834 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 8, commonly referred to as a "hard disk drive"). Although not shown in fig. 8, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 818 through one or more data medium interfaces. Memory 828 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.
A program/utility 840 having a set (at least one) of program modules 842 may be stored in, for example, memory 828, such program modules 842 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 842 generally perform the functions and/or methods in the embodiments described herein.
The device 812 may also communicate with one or more external devices 814 (e.g., keyboard, pointing device, display 824, etc.), one or more devices that enable a user to interact with the device 812, and/or any devices (e.g., network card, modem, etc.) that enable the device 812 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 822. Also, device 812 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, e.g., the internet, through network adapter 820. As shown, the network adapter 820 communicates with other modules of the device 812 over the bus 818. It should be appreciated that although not shown in fig. 8, other hardware and/or software modules may be used in connection with device 812, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 816 executes various functional applications and data processing by running programs stored in the system memory 828, for example, to implement a method for clustering commodities provided in an embodiment of the present invention, the method including:
mapping commodities into network nodes, mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into the association weight between the two network nodes, and constructing a commodity association network between commodities;
determining characteristic values of commodities corresponding to all network nodes in the commodity correlation network according to a graph embedding algorithm;
and clustering the commodities according to the characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes.
Of course, those skilled in the art will understand that the processor may also implement the technical solution in the method for clustering commodities provided in any embodiment of the present invention.
There is also provided in an embodiment of the present invention a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of clustering articles as provided in an embodiment of the present invention, the method comprising:
mapping commodities into network nodes, mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into the association weight between the two network nodes, and constructing a commodity association network between commodities;
Determining characteristic values of commodities corresponding to all network nodes in the commodity correlation network according to a graph embedding algorithm;
and clustering the commodities according to the characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes.
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present invention is not limited to the operations of the method for clustering commodities as described above, but may also perform related operations in the method for clustering commodities provided in any embodiment of the present invention, and has corresponding functions and beneficial effects.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
The computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++, python and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims (22)

1. A method of clustering items of merchandise, the method comprising:
mapping commodities into network nodes, mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into the association weight between the two network nodes, and constructing a commodity association network between commodities;
determining characteristic values of commodities corresponding to all network nodes in the commodity correlation network according to a graph embedding algorithm;
clustering the commodities according to the characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes;
The method comprises the steps of clustering the commodities according to characteristic values of the commodities corresponding to the network nodes, and after obtaining a plurality of commodity classes, further comprises the following steps:
determining a commodity storage mode, an order wave-grouping mode, a goods shelf adjustment mode and/or a warehouse-crossing sorting mode in a warehouse according to the acquired multiple commodity types;
the method for determining the commodity storage mode in the warehouse according to the acquired multiple commodity types comprises the following steps:
dividing an inventory system of a warehouse into a plurality of logic partitions according to the acquired multiple commodity classes; any one stock container and any one station in the stock system are provided with a logic partition to which the stock container belongs;
when a target order is processed, determining a logical partition to which the target order belongs from a plurality of logical partitions as a target logical partition; wherein one of the logical partitions is associated with at least one station and a plurality of inventory containers, and at least one inventory container of the plurality of inventory containers associated with the target logical partition is used for containing inventory items required by the target order;
distributing the target order to a station associated with the target logical partition as a target station;
and controlling a robot to convey the target stock container containing the stock articles required by the target order to the target station in the plurality of stock containers associated with the target logical partition.
2. The method of claim 1, wherein dividing the inventory system of the warehouse into a plurality of logical partitions based on the plurality of acquired categories of goods comprises:
determining a plurality of logical partitions according to the acquired plurality of commodity classes;
dividing the inventory container in the inventory system into logic partitions corresponding to the commodity classes with high overlap ratio according to the overlap ratio between the inventory commodity on the inventory container in the inventory system and the commodity in each commodity class;
dividing the inventory container bits in the inventory system into different logical partitions according to the number of the inventory containers associated with each logical partition;
stations in the inventory system are partitioned into logical partitions that are closer to each other based on the distance between the stations and the inventory container locations associated with each logical partition.
3. The method of claim 1, wherein determining the order group wave pattern in the warehouse based on the plurality of acquired categories of goods comprises:
and combining different orders corresponding to different commodities contained in the same commodity class into the same order wave order task according to the acquired multiple commodity classes so as to distribute the order wave order task to the same workstation to execute the picking task.
4. The method of claim 1, wherein determining a shelf adjustment in the warehouse based on the plurality of acquired categories of goods comprises:
according to the acquired multiple commodities, placing all commodities contained in the same commodity on an inventory container meeting the preset distance condition; or alternatively, the process may be performed,
and according to the acquired multiple commodities, stripping the multiple commodities which are placed on the inventory container meeting the preset distance condition and are not contained in the same commodity.
5. The method of claim 4, wherein the inventory receptacles of the preset distance condition are the same inventory receptacle or a plurality of inventory receptacles having a distance between inventory receptacles less than or equal to a preset distance threshold.
6. The method of claim 1, wherein determining the over-library sort pattern based on the plurality of acquired categories of goods comprises:
dividing each store into different store combinations according to the coincidence degree between the goods contained in each goods class and the goods required by each store order;
the same sorting time period is allocated to a plurality of stores belonging to the same store combination so that the plurality of stores belonging to the same store combination perform the commodity sorting operation in the same sorting time period.
7. The method of claim 1, further comprising, after determining the feature value of the commodity corresponding to each network node in the commodity correlation network according to a graph embedding algorithm:
and taking the characteristic value as a dimension, and performing dimension reduction processing on the characteristic value of the commodity corresponding to each network node in the commodity correlation network.
8. The method of claim 1, wherein determining the feature value of the commodity corresponding to each network node in the commodity correlation network according to a graph embedding algorithm comprises:
and calculating characteristic values of commodities corresponding to all network nodes in the commodity correlation network by adopting a deep walk algorithm or a large-scale information network embedding algorithm.
9. The method of claim 8, wherein calculating the feature value of the commodity corresponding to each network node in the commodity correlation network using a deep walk algorithm comprises:
when each random walk is carried out, uniformly and randomly sampling a network node from the commodity correlation network as a starting point of the random walk, uniformly and randomly sampling an adjacent point with correlation weight for the last accessed node in the walk process until the walk reaches a preset maximum length to finish the random walk, and finally obtaining a plurality of node sequences;
Training the plurality of node sequences through machine learning to obtain characteristic value vectors of commodities corresponding to each network node.
10. The method of claim 8, wherein calculating the characteristic value of the commodity corresponding to each network node in the commodity correlation network using a large-scale information network embedding algorithm comprises:
determining first-order similarity among network nodes in the commodity correlation network, and optimizing the first-order similarity among the network nodes to obtain a first characteristic value vector of the commodity corresponding to each network node;
determining the second-order similarity among all network nodes in the commodity correlation network, and optimizing the second-order similarity among all network nodes to obtain a second characteristic value vector of commodities corresponding to all network nodes;
and splicing the first eigenvalue vector and the second eigenvalue vector to obtain eigenvalue vectors of commodities corresponding to each network node.
11. An apparatus for clustering articles, the apparatus comprising:
the construction module is used for mapping commodities into network nodes, mapping the frequency of the common occurrence of commodities corresponding to any two network nodes in a historical order into the association weight between the two network nodes, and constructing a commodity association network between the commodities;
The determining module is used for determining characteristic values of commodities corresponding to all network nodes in the commodity correlation network according to a graph embedding algorithm;
the clustering module is used for clustering the commodities according to the characteristic values of the commodities corresponding to the network nodes to obtain a plurality of commodity classes;
the apparatus further comprises:
the application module is used for determining a commodity storage mode, an order wave-grouping mode, a goods shelf adjustment mode and/or a warehouse-crossing sorting mode in a warehouse according to the acquired multiple commodity types;
the application module comprises:
the logic partition dividing unit is used for dividing the inventory system of the warehouse into a plurality of logic partitions according to the acquired plurality of commodity types; any one stock container and any one station in the stock system are provided with a logic partition to which the stock container belongs;
a target partition determination unit configured to determine, when one target order is processed, a logical partition to which the target order belongs from among a plurality of logical partitions, as a target logical partition; wherein one of the logical partitions is associated with at least one station and a plurality of inventory containers, and at least one inventory container of the plurality of inventory containers associated with the target logical partition is used for containing inventory items required by the target order;
The target order allocation unit is used for allocating the target order to one station associated with the target logical partition as a target station;
and the target order processing unit is used for controlling the robot to convey the target inventory container containing the inventory items required by the target order to the target station.
12. The apparatus of claim 11, wherein the application module comprises:
the logic partition determining subunit is used for determining a plurality of logic partitions according to the acquired plurality of commodity types;
the first dividing subunit is used for dividing the inventory containers in the inventory system into logic partitions corresponding to the commodity classes with high overlap ratio according to the overlap ratio between the inventory commodity on the inventory container in the inventory system and the commodity in each commodity class;
the second dividing subunit is used for dividing the inventory container bits in the inventory system into different logic partitions according to the quantity of the inventory containers associated with each logic partition;
and the third dividing subunit is used for dividing the stations in the inventory system into logic partitions close to the stations according to the distances between the stations and the inventory container positions associated with each logic partition.
13. The apparatus of claim 11, wherein the application module comprises:
and the order combining unit is used for combining different orders corresponding to different commodities contained in the same commodity class into the same order wave order task according to the acquired multiple commodity classes so as to distribute the order wave order task to the same workstation to execute the picking task.
14. The apparatus of claim 11, wherein the application module comprises:
the first goods shelf adjusting unit is used for placing all goods contained in the same goods on an inventory container meeting the preset distance condition according to the acquired multiple goods; or alternatively, the process may be performed,
and the second goods shelf adjusting unit is used for stripping the goods which are not contained in the same goods class and are placed on the inventory container meeting the preset distance condition according to the acquired goods class.
15. The apparatus of claim 14, wherein the inventory receptacles of the preset distance condition are the same inventory receptacle or a plurality of inventory receptacles having a distance between inventory receptacles less than or equal to a preset distance threshold.
16. The apparatus of claim 11, wherein the application module comprises:
The store dividing unit is used for dividing each store into different store combinations according to the coincidence degree between the goods contained in each goods class and the goods required by each store order;
and the sorting time distribution unit is used for distributing the same sorting time period to a plurality of shops belonging to the same shop combination so as to enable the plurality of shops belonging to the same shop combination to perform commodity sorting operation in the same sorting time period.
17. The apparatus of claim 11, wherein the apparatus further comprises:
and the dimension reduction processing module is used for taking a characteristic value as a dimension and carrying out dimension reduction processing on the characteristic value of the commodity corresponding to each network node in the commodity correlation network.
18. The apparatus of claim 11, wherein the means for determining comprises:
and the characteristic value determining unit is used for calculating the characteristic value of the commodity corresponding to each network node in the commodity correlation network by adopting a deep walk algorithm or a large-scale information network embedding algorithm.
19. The apparatus according to claim 18, wherein the feature value determining unit is configured to:
when each random walk is carried out, uniformly and randomly sampling a network node from the commodity correlation network as a starting point of the random walk, uniformly and randomly sampling an adjacent point with correlation weight for the last accessed node in the walk process until the walk reaches a preset maximum length to finish the random walk, and finally obtaining a plurality of node sequences;
Training the plurality of node sequences through machine learning to obtain characteristic value vectors of commodities corresponding to each network node.
20. The method according to claim 18, wherein the feature value determining unit is configured to:
determining first-order similarity among network nodes in the commodity correlation network, and optimizing the first-order similarity among the network nodes to obtain a first characteristic value vector of the commodity corresponding to each network node;
determining the second-order similarity among all network nodes in the commodity correlation network, and optimizing the second-order similarity among all network nodes to obtain a second characteristic value vector of commodities corresponding to all network nodes;
and splicing the first eigenvalue vector and the second eigenvalue vector to obtain eigenvalue vectors of commodities corresponding to each network node.
21. An electronic device, the electronic device comprising:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of merchandise clustering of any one of claims 1-10 above.
22. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements a method of clustering articles according to any one of the preceding claims 1-10.
CN201910107025.4A 2018-12-30 2019-02-02 Commodity clustering method, device, equipment and storage medium Active CN111523918B (en)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN201910107025.4A CN111523918B (en) 2019-02-02 2019-02-02 Commodity clustering method, device, equipment and storage medium
EP19907152.3A EP3905154A4 (en) 2018-12-30 2019-12-26 Order processing method, apparatus and device, and storage medium
US17/419,724 US20220051178A1 (en) 2018-12-30 2019-12-26 Order processing method, apparatus and device, and storage medium
PCT/CN2019/128557 WO2020140818A1 (en) 2018-12-30 2019-12-26 Order processing method, apparatus and device, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910107025.4A CN111523918B (en) 2019-02-02 2019-02-02 Commodity clustering method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN111523918A CN111523918A (en) 2020-08-11
CN111523918B true CN111523918B (en) 2023-09-19

Family

ID=71900658

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910107025.4A Active CN111523918B (en) 2018-12-30 2019-02-02 Commodity clustering method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111523918B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113763080A (en) * 2020-08-26 2021-12-07 北京沃东天骏信息技术有限公司 Method and device for determining recommended article, electronic equipment and storage medium
CN113763014A (en) * 2021-01-05 2021-12-07 北京沃东天骏信息技术有限公司 Article co-occurrence relation determining method and device and judgment model obtaining method and device
CN113111182A (en) * 2021-04-15 2021-07-13 北京沃东天骏信息技术有限公司 Information recommendation method and device and computer-readable storage medium
CN116402438A (en) * 2023-03-29 2023-07-07 乐麦信息技术(杭州)有限公司 Warehouse management method and system

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101251859A (en) * 2008-03-17 2008-08-27 北京科文书业信息技术有限公司 Commercial articles clustering system and method based on shopping behaviors
JP2009205365A (en) * 2008-02-27 2009-09-10 Nec Corp System, method and program for optimizing inventory management and sales of merchandise
CN102254028A (en) * 2011-07-22 2011-11-23 青岛理工大学 Personalized commodity recommending method and system which integrate attributes and structural similarity
CN105469237A (en) * 2015-11-18 2016-04-06 北京京东尚科信息技术有限公司 Method and system for automatic logistics processing
CN106446943A (en) * 2016-09-19 2017-02-22 大连海事大学 Commodity correlation big data sparse network quick clustering method
CN106886524A (en) * 2015-12-15 2017-06-23 天津科技大学 A kind of community network community division method based on random walk
CN106919921A (en) * 2017-03-06 2017-07-04 重庆邮电大学 With reference to sub-space learning and the gait recognition method and system of tensor neutral net
CN107545381A (en) * 2016-06-24 2018-01-05 北京京东尚科信息技术有限公司 Manage the method and warehouse management system of warehouse inventory
CN107851218A (en) * 2015-02-10 2018-03-27 D-波系统公司 For the system of quantum processor architecture, device, article and method
CN107944896A (en) * 2016-10-13 2018-04-20 北京京东尚科信息技术有限公司 Determine the method and device of commodity association degree
CN108053268A (en) * 2017-12-29 2018-05-18 广州品唯软件有限公司 A kind of commercial articles clustering confirmation method and device
CN108182621A (en) * 2017-12-07 2018-06-19 合肥美的智能科技有限公司 The Method of Commodity Recommendation and device for recommending the commodity, equipment and storage medium
CN108388651A (en) * 2018-02-28 2018-08-10 北京理工大学 A kind of file classification method based on the kernel of graph and convolutional neural networks
CN108846609A (en) * 2018-06-15 2018-11-20 北京极智嘉科技有限公司 Picking method, device, server and medium based on order taking responsibility
CN108898459A (en) * 2018-06-25 2018-11-27 中国联合网络通信集团有限公司 A kind of Method of Commodity Recommendation and device
CN108932598A (en) * 2018-05-31 2018-12-04 广东工业大学 A kind of grand scale logistic allocator based on cloud platform
CN109214730A (en) * 2017-06-29 2019-01-15 北京京东尚科信息技术有限公司 Information-pushing method and device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9792577B2 (en) * 2012-10-04 2017-10-17 Amazon Technologies, Inc. Filling an order at an inventory pier

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009205365A (en) * 2008-02-27 2009-09-10 Nec Corp System, method and program for optimizing inventory management and sales of merchandise
CN101251859A (en) * 2008-03-17 2008-08-27 北京科文书业信息技术有限公司 Commercial articles clustering system and method based on shopping behaviors
CN102254028A (en) * 2011-07-22 2011-11-23 青岛理工大学 Personalized commodity recommending method and system which integrate attributes and structural similarity
CN107851218A (en) * 2015-02-10 2018-03-27 D-波系统公司 For the system of quantum processor architecture, device, article and method
CN105469237A (en) * 2015-11-18 2016-04-06 北京京东尚科信息技术有限公司 Method and system for automatic logistics processing
CN106886524A (en) * 2015-12-15 2017-06-23 天津科技大学 A kind of community network community division method based on random walk
CN107545381A (en) * 2016-06-24 2018-01-05 北京京东尚科信息技术有限公司 Manage the method and warehouse management system of warehouse inventory
CN106446943A (en) * 2016-09-19 2017-02-22 大连海事大学 Commodity correlation big data sparse network quick clustering method
CN107944896A (en) * 2016-10-13 2018-04-20 北京京东尚科信息技术有限公司 Determine the method and device of commodity association degree
CN106919921A (en) * 2017-03-06 2017-07-04 重庆邮电大学 With reference to sub-space learning and the gait recognition method and system of tensor neutral net
CN109214730A (en) * 2017-06-29 2019-01-15 北京京东尚科信息技术有限公司 Information-pushing method and device
CN108182621A (en) * 2017-12-07 2018-06-19 合肥美的智能科技有限公司 The Method of Commodity Recommendation and device for recommending the commodity, equipment and storage medium
CN108053268A (en) * 2017-12-29 2018-05-18 广州品唯软件有限公司 A kind of commercial articles clustering confirmation method and device
CN108388651A (en) * 2018-02-28 2018-08-10 北京理工大学 A kind of file classification method based on the kernel of graph and convolutional neural networks
CN108932598A (en) * 2018-05-31 2018-12-04 广东工业大学 A kind of grand scale logistic allocator based on cloud platform
CN108846609A (en) * 2018-06-15 2018-11-20 北京极智嘉科技有限公司 Picking method, device, server and medium based on order taking responsibility
CN108898459A (en) * 2018-06-25 2018-11-27 中国联合网络通信集团有限公司 A kind of Method of Commodity Recommendation and device

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
具有统计不相关性的核化图嵌入算法;卢桂馥;林忠;金忠;;中国图象图形学报;16(第04期);618-624 *
垂直电子商务网站的混合型推荐系统;洪文兴;翁洋;朱顺痣;李茂青;;系统工程理论与实践(第05期);928-935 *
基于K-MEANS聚类的电商网站用户行为分析;王召义;薛晨杰;;温州大学学报(自然科学版)(第03期);53-58 *
基于聚类的因子分解机推荐算法研究;谢桂林;詹志强;李凯;;软件;37(第10期);113-117 *
数据质量的历史沿革和发展趋势;蔡莉;梁宇;朱扬勇;何婧;;计算机科学(第04期);7-16 *

Also Published As

Publication number Publication date
CN111523918A (en) 2020-08-11

Similar Documents

Publication Publication Date Title
CN110197309B (en) Order processing method, device, equipment and storage medium
CN111523918B (en) Commodity clustering method, device, equipment and storage medium
US11182743B2 (en) Order processing method and device, server, and storage medium
CN109117999B (en) Seeding bit distribution method, device, server and medium
WO2020140818A1 (en) Order processing method, apparatus and device, and storage medium
CN109733783B (en) Goods shelving method and device, electronic equipment and storage medium
CN109118137A (en) A kind of order processing method, apparatus, server and storage medium
JP7268172B2 (en) Returnable Box Guidance in Warehouse Order Fulfillment Operations
CN109840729B (en) Method and system for positioning bin, storage medium and electronic equipment
KR20230067645A (en) Order processing and shipping methods, devices, systems and storage media
WO2023020105A1 (en) Supplies inventory method and apparatus, and device and storage medium
CN109118150B (en) Commodity volume estimation method and device, computer equipment and storage medium
CN113269494A (en) Inventory scheduling method, equipment and system
CN112007865A (en) Warehouse entry sorting method, warehouse entry sorting device, electronic equipment and storage medium
WO2024093758A1 (en) Transportation scheduling method and apparatus for vertical warehouse
JP7268171B2 (en) Optimized Tote Recommendation Process in Warehouse Order Fulfillment Behavior
CN111382969B (en) Order processing method, device, equipment and storage medium
Ouzidan et al. On solving the order processing in picking workstations
CN114229312B (en) Cargo handling method, device, server and storage medium
CN110577048A (en) Method and system for warehousing scheduling
CN113689140A (en) Method and device for task scheduling
CN113570179A (en) Container determination method and device, electronic equipment and computer-readable storage medium
Wang et al. A multi-stage heuristic algorithm for matching problem in the modified miniload automated storage and retrieval system of e-commerce
Matthews SKU assignment in a multiple picking line order picking system.
CN115239256B (en) Article sorting and shelf returning method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 100020 No. 1 Building, No. 36 Chuangyuan Road, Chaoyang District, Beijing 101

Applicant after: Beijing jizhijia Technology Co.,Ltd.

Address before: 100020 No. 1 Building, No. 36 Chuangyuan Road, Chaoyang District, Beijing 101

Applicant before: Beijing Geekplus Technology Co.,Ltd.

GR01 Patent grant
GR01 Patent grant