Digital storage picking path planning method, storage medium and equipment

Abstract

The invention discloses a digital storage picking path planning method, a storage medium and equipment. The method comprises the following steps: collecting commodity attribute information, picking behavior information and path relation information from digital storage; determining the relationship among the commodity, the picking behavior and the path from the collected commodity attribute information, the picking behavior information and the path relationship information, and constructing a storage knowledge graph; determining to-be-picked commodities according to the order data, and constructing a picking path planning cost function of the to-be-picked commodities in combination with the storage knowledge graph; and the order picking path is determined with the purpose of minimizing the cost function of order picking path planning. The picking path is planned according to the construction of the storage knowledge graph, so that the picking efficiency and adaptability are improved, and the manpower and material resource cost is greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of digital warehousing technology, specifically to a digital warehousing picking route planning method, storage medium, and equipment. Background Technology

[0002] Digital warehousing utilizes information technology to comprehensively digitize warehousing processes, covering the entire lifecycle from goods receiving, storage, picking to outbound delivery, achieving automation, intelligence, and visualization of warehousing activities. Unlike traditional warehousing, which relies on manual records or paper documents, digital warehousing collects data in real time through electronic entities or network applications, thereby building a dynamically updated digital object library to support precise management and efficient scheduling of warehousing resources.

[0003] However, existing digital warehousing relies on fixed location allocation and does not consider dynamic factors such as the sales frequency and correlation of goods. This results in high-frequency goods being located deep in the warehouse, increasing picking time. Secondly, existing digital warehousing processes orders according to their arrival order, without considering the habits of picking personnel, leading to chaotic picking routes and increased labor costs. Finally, the picking route planning of existing digital warehousing is based on fixed warehouse layout and experience-based selection, which cannot cope with temporary obstacles such as replenishment and equipment failure, resulting in the need for temporary detours or waiting in place. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides a digital warehouse picking route planning method, storage medium, and equipment. The picking route planning is based on the construction of a warehouse knowledge graph, which improves picking efficiency and adaptability and greatly reduces labor and material costs.

[0005] To achieve the above technical objectives, the present invention adopts the following technical solution: a digital warehouse picking route planning method, comprising the following steps: Step S1: Collect product attribute information, picking behavior information, and route relationship information from the digital warehouse; Step S2: Determine the relationships between products, picking behaviors, and routes from the collected product attribute information, picking behavior information, and route relationship information, and construct a warehouse knowledge graph; Step S3: Determine the items to be picked based on the order data, and construct the picking path planning cost function for the items to be picked by combining the warehouse knowledge graph; Step S4: Determine the picking route with the goal of minimizing the cost function of picking route planning.

[0006] Furthermore: The product attribute information includes: product SKU number, size, weight, storage location, associated products, and product purchase frequency; The picking behavior information includes: picker ID, picking speed, preferred path, and picking error rate; The path relationship information includes: product shelf ID, physical distance between product shelves, congestion rate of aisles between product shelves, picking equipment ID, and picking equipment status.

[0007] Furthermore, the construction process of the warehousing knowledge graph is as follows: The node types of the warehouse knowledge graph are determined, including: product nodes, picking behavior nodes, and path nodes. The product nodes contain attribute information such as the product's SKU number, size, weight, and storage location. The picking behavior nodes contain attribute information such as the picking personnel ID and picking speed. The path nodes contain the product shelf ID and picking equipment ID. The edge types of the warehouse knowledge graph are determined, including: product-related product edges, product-picking behavior edges, and path-path edges. The product-related product edges contain association strength information determined based on the related products. The product-picking behavior edges contain picking speed information of each picker. The path-path edges contain information on the physical distance between product shelves, the congestion rate of aisles between product shelves, and the status of picking equipment.

[0008] Furthermore, the storage location of the goods is dynamically adjusted according to the purchase frequency of the goods, and the warehouse knowledge graph is updated according to the adjusted storage location; the higher the purchase frequency of the goods, the closer the storage location of the goods is to the warehouse exit.

[0009] Furthermore, the process of constructing the picking route planning cost function is as follows:

[0010] in, This represents the evaluation value of the picking route planning cost function. This represents the normalized value of the cost of the picking route length. express The weight value, The normalized value representing the time taken for picking routes. express The weight value, This represents the normalized value of the penalty term. Includes a congestion cost normalization item and a picking equipment energy consumption normalization item. express The weight value.

[0011] Furthermore, the picking route planning cost function needs to satisfy the following constraints: Bundles of items must be picked in sequence; The load on the picking equipment must not exceed the maximum allowable load, and the energy consumption of the picking equipment must not exceed the remaining energy consumption. Picking equipment can only access aisles between authorized product shelves.

[0012] Furthermore: The calculation process for the normalized value of the picking route length cost is as follows: ; The calculation process for the normalized value of the picking route time is as follows: ; The calculation process for the normalized value of the penalty term is as follows: ; in, Indicates the first The cost of the length of the picking route, This represents the minimum cost of all picking paths. This represents the maximum length cost among all picking routes; Indicates the first The picking route takes time. This indicates the shortest time among all picking routes. This indicates the longest picking time among all picking routes; Indicates the first The congestion rate of each picking route. This represents the minimum congestion rate among all picking routes. This represents the maximum congestion rate across all picking routes. An adjustment coefficient representing the route congestion rate; Indicates the first Energy consumption of picking equipment along the picking path This represents the minimum energy consumption of the picking equipment across all picking paths. This indicates the maximum energy consumption of the picking equipment across all picking paths. This represents the adjustment coefficient for the energy consumption of the picking equipment.

[0013] Furthermore, the first Cost of picking route length The calculation process is as follows:

[0014] in, This indicates the number of shelves corresponding to the items to be picked. express index, Indicates the path length between adjacent product shelves. This indicates the path length from the last shelf to the warehouse exit. express The weighting coefficients, , This represents the query vector obtained by linearly varying the association strength between products on adjacent product shelves. This represents the key vector obtained by linearly transforming the association strength between products on adjacent product shelves. This represents a value vector obtained by linearly varying the correlation strength between products on adjacent product shelves. express Dimensions express Activation function This indicates transpose.

[0015] Furthermore, the present invention also provides a computer-readable storage medium storing a computer program, characterized in that the computer program causes a computer to execute the digital warehouse picking route planning method.

[0016] Furthermore, the present invention also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the digital warehouse picking path planning method.

[0017] Compared with the prior art, the present invention has the following beneficial effects: (1) The digital warehouse picking route planning method of the present invention constructs a warehouse knowledge graph based on the relationship between goods, picking behavior and route. It can adjust the storage location according to the purchase frequency of goods to facilitate picking and dynamically update the warehouse knowledge graph so that all warehouse information is presented in the warehouse knowledge graph, thereby improving the rationality of picking route planning. (2) The digital warehouse picking route planning method of the present invention guides the selection of picking routes through warehouse knowledge graph, reduces human decision-making bias, and constructs a picking route planning cost function that includes the length, time, congestion and energy consumption of picking routes. It comprehensively considers the impact of various factors on picking route planning, and improves the rationality and efficiency of picking route selection.

[0018] In summary, this invention plans picking routes based on the construction of a warehouse knowledge graph, which improves picking efficiency and adaptability, and greatly reduces labor and material costs. It is especially suitable for modern digital warehousing scenarios with high-frequency orders and dynamic layouts. Attached Figure Description

[0019] Figure 1 This is a flowchart of the digital warehouse picking route planning method of the present invention; Figure 2 This is a schematic diagram of the digital warehouse knowledge graph in this invention. Detailed Implementation

[0020] The technical solution of the present invention will be further explained and described below with reference to the accompanying drawings.

[0021] like Figure 1 This is a flowchart of the digital warehouse picking route planning method of the present invention. The digital warehouse picking route planning method includes the following steps: Step S1: Collect product attribute information, picking behavior information, and route relationship information from the digital warehouse; specifically: Product attribute information includes: product SKU number, size, weight, storage location, related products, and product purchase frequency. This provides a clear understanding of the characteristics of each product and lays the foundation for subsequent picking route planning. Picking behavior information includes: picker ID, picking speed, preferred path, and picking error rate, which reflects the dynamic situation in the actual picking process and helps to analyze picking efficiency and quality; The path relationship information includes: product shelf ID, physical distance between product shelves, aisle congestion rate between product shelves, picking equipment ID, and picking equipment status. This expresses the structural framework of the warehouse space, clarifies the accessibility and convenience between product storage locations, helps plan picking routes, and improves picking efficiency.

[0022] Step S2: Determine the relationships between products, picking behaviors, and routes from the collected product attribute information, picking behavior information, and route relationship information, and construct a warehouse knowledge graph. This can integrate multi-dimensional warehouse information, improve the efficiency of warehouse management, and enhance the rationality of picking route planning.

[0023] like Figure 2 The specific process of constructing the warehouse knowledge graph is as follows: The node types of the warehouse knowledge graph are determined, including: product nodes, picking behavior nodes, and path nodes. Product nodes contain attribute information such as the product's SKU number, size, weight, and storage location. When there is an order, the specific storage location of the required product can be quickly located, reducing the time spent searching for the product. Picking behavior nodes contain attribute information such as the picker ID and picking speed. Path nodes contain the product shelf ID and picking equipment ID. The edge types of the warehouse knowledge graph are determined, including: product-related product edges, product-picking behavior edges, and path-path edges. Among them, product-related product edges contain information on the association strength determined based on related products, product-picking behavior edges contain information on the picking speed of each picker, and path-path edges contain information on the physical distance between product shelves, the congestion rate of aisles between product shelves, and the status of picking equipment.

[0024] Step S3: Determine the items to be picked based on order data, and construct the picking route planning cost function for the items to be picked using the warehouse knowledge graph:

[0025] in, This represents the evaluation value of the picking route planning cost function. This represents the normalized value of the cost of the picking route length. , Indicates the first The cost of the length of the picking route, This represents the minimum cost of all picking paths. This represents the maximum cost of the picking route. express The weight value; The normalized value representing the time taken for picking routes. , Indicates the first The picking route takes time. This indicates the shortest time among all picking routes. This indicates the longest picking time among all picking routes. express The weight value; This represents the normalized value of the penalty term. Includes a congestion cost normalization item and a picking equipment energy consumption normalization item. , Indicates the first The congestion rate of each picking route. This represents the minimum congestion rate among all picking routes. This represents the maximum congestion rate across all picking routes. An adjustment coefficient representing the route congestion rate; Indicates the first Energy consumption of picking equipment along the picking path This represents the minimum energy consumption of the picking equipment across all picking paths. This indicates the maximum energy consumption of the picking equipment across all picking paths. The adjustment coefficient representing the energy consumption of the picking equipment. express The weight value.

[0026] The picking route planning cost function of this invention quantifies costs of different natures in a unified manner, making it easier to compare them comprehensively. Among them, the picking route length cost reflects the basic cost brought by distance, the time consumption reflects the value of time, the energy consumption is related to energy consumption and operating costs, and congestion will lead to additional waiting time and energy waste. By integrating these factors into the picking route evaluation, the true cost of the picking route can be measured more accurately, providing a more comprehensive basis for picking route decision-making.

[0027] In one technical solution of the present invention, the first Cost of picking route length The calculation process is as follows:

[0028] in, This indicates the number of shelves corresponding to the items to be picked. express index, Indicates the path length between adjacent product shelves. This indicates the path length from the last shelf to the warehouse exit. express The weighting coefficients, , This represents the query vector obtained by linearly varying the association strength between products on adjacent product shelves. This represents the key vector obtained by linearly transforming the association strength between products on adjacent product shelves. This represents a value vector obtained by linearly varying the correlation strength between products on adjacent product shelves. express Dimensions express Activation function This indicates transpose.

[0029] In this invention, the cost of the picking path length is affected by the product association strength, which reflects the frequency with which products are picked together in an order. Arranging products that are frequently picked together on shelves that are close to each other reduces the walking distance between different product shelves for picking personnel in a single picking task, thereby further improving picking efficiency.

[0030] In one technical solution of the present invention, the picking route planning cost function needs to satisfy the following constraints: Bundles of items must be picked in sequence; The load on the picking equipment must not exceed the maximum allowable load, and the energy consumption of the picking equipment must not exceed the remaining energy consumption. Picking equipment can only access aisles between authorized product shelves.

[0031] Step S4: Determine the picking route with the goal of minimizing the cost function of picking route planning.

[0032] In one technical solution of the present invention, the storage location of goods is dynamically adjusted according to the purchase frequency of goods, and the warehouse knowledge graph is updated in real time according to the adjusted storage location to ensure the real-time nature of picking route planning; wherein, the higher the purchase frequency of goods, the closer the storage location of goods is to the warehouse exit, which facilitates picking and further improves picking efficiency.

[0033] The digital warehouse picking route planning method of this invention guides the selection of picking routes through a warehouse knowledge graph, reducing human decision-making bias. By utilizing the product association strength information, picking speed of picking personnel, and the correlation between paths in the warehouse knowledge graph, a picking route with the lowest overall cost can be planned. By comprehensively considering the impact of various factors on picking route planning, the rationality and efficiency of picking route selection are improved.

[0034] In one embodiment of the present invention, a computer-readable storage medium is also provided, storing a computer program that enables a computer to execute the digital warehouse picking route planning method of the present invention.

[0035] In one technical solution of the present invention, an electronic device is also provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the digital warehouse picking path planning method of the present invention.

[0036] In the embodiments disclosed in this application, a computer storage medium may be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0037] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0038] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should be considered within the scope of protection of the present invention.

Claims

1. A digital warehouse picking route planning method, characterized in that, Includes the following steps: Step S1: Collect product attribute information, picking behavior information, and route relationship information from the digital warehouse; Step S2: Determine the relationships between products, picking behaviors, and routes from the collected product attribute information, picking behavior information, and route relationship information, and construct a warehouse knowledge graph; Step S3: Determine the items to be picked based on the order data, and construct the picking path planning cost function for the items to be picked by combining the warehouse knowledge graph; Step S4: Determine the picking route with the goal of minimizing the cost function of picking route planning.

2. The digital warehouse picking route planning method according to claim 1, characterized in that: The product attribute information includes: product SKU number, size, weight, storage location, associated products, and product purchase frequency; The picking behavior information includes: picker ID, picking speed, preferred path, and picking error rate; The path relationship information includes: product shelf ID, physical distance between product shelves, congestion rate of aisles between product shelves, picking equipment ID, and picking equipment status.

3. The digital warehouse picking route planning method according to claim 2, characterized in that, The process of constructing the warehouse knowledge graph is as follows: The node types of the warehouse knowledge graph are determined, including: product nodes, picking behavior nodes, and path nodes. The product nodes contain attribute information such as the product's SKU number, size, weight, and storage location. The picking behavior nodes contain attribute information such as the picking personnel ID and picking speed. The path nodes contain the product shelf ID and picking equipment ID. The edge types of the warehouse knowledge graph are determined, including: product-related product edges, product-picking behavior edges, and path-path edges. The product-related product edges contain association strength information determined based on the related products. The product-picking behavior edges contain picking speed information of each picker. The path-path edges contain information on the physical distance between product shelves, the congestion rate of aisles between product shelves, and the status of picking equipment.

4. The digital warehouse picking route planning method according to claim 3, characterized in that, The storage location of the goods is dynamically adjusted based on the purchase frequency of the goods, and the warehouse knowledge graph is updated based on the adjusted storage location; the higher the purchase frequency of the goods, the closer the storage location of the goods is to the warehouse exit.

5. The digital warehouse picking route planning method according to claim 3, characterized in that, The process of constructing the picking route planning cost function is as follows: in, This represents the evaluation value of the picking route planning cost function. This represents the normalized value of the cost of the picking route length. express The weight value, The normalized value representing the time taken for picking routes. express The weight value, This represents the normalized value of the penalty term. Includes a congestion cost normalization item and a picking equipment energy consumption normalization item. express The weight value.

6. The digital warehouse picking route planning method according to claim 5, characterized in that, The cost function for picking route planning needs to satisfy the following constraints: Bundles of items must be picked in sequence; The load on the picking equipment must not exceed the maximum allowable load, and the energy consumption of the picking equipment must not exceed the remaining energy consumption. Picking equipment can only access aisles between authorized product shelves.

7. The digital warehouse picking route planning method according to claim 5, characterized in that: The calculation process for the normalized value of the picking route length cost is as follows: ; The normalized value of the picking route time is calculated as follows: ; The calculation process for the normalized value of the penalty term is as follows: ; in, Indicates the first The cost of the length of the picking route, This represents the minimum cost of all picking paths. This represents the maximum length cost among all picking routes; Indicates the first The picking route takes time. This indicates the shortest time among all picking routes. This indicates the longest picking time among all picking routes; Indicates the first Congestion rate of each picking route This represents the minimum congestion rate among all picking routes. This represents the maximum congestion rate across all picking routes. An adjustment coefficient representing the route congestion rate; Indicates the first Energy consumption of picking equipment along the picking path This represents the minimum energy consumption of the picking equipment across all picking paths. This indicates the maximum energy consumption of the picking equipment across all picking paths. This represents the adjustment coefficient for the energy consumption of the picking equipment.

8. The digital warehouse picking route planning method according to claim 5, characterized in that, The first Cost of picking route length The calculation process is as follows: in, This indicates the number of shelves corresponding to the items to be picked. express index, Indicates the path length between adjacent product shelves. This indicates the path length from the last shelf to the warehouse exit. express The weighting coefficients, , This represents the query vector obtained by linearly varying the association strength between products on adjacent product shelves. This represents the key vector obtained by linearly transforming the association strength between products on adjacent product shelves. This represents a value vector obtained by linearly varying the correlation strength between products on adjacent product shelves. express Dimensions express Activation function This indicates transpose.

9. A computer-readable storage medium storing a computer program, characterized in that, The computer program causes the computer to execute the digital warehouse picking route planning method as described in any one of claims 1-8.

10. An electronic device, characterized in that, include: The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the digital warehouse picking route planning method as described in any one of claims 1-8.

Images