Real-time warehouse management method and equipment based on digital twinning

Abstract

The embodiment of the invention discloses a real-time warehouse management method and equipment based on digital twinning, relates to the technical field of Internet of Things, and is used for solving the problems of low efficiency and high cost of existing warehouse management. The method comprises the following steps: constructing a digital twin storage model according to building data and Internet of Things data corresponding to a current storage scene; clustering and grouping the current goods according to the arrival scanning information of the current goods and the historical storage information to obtain key storage information of the current goods in each group; querying the digital twin storage model according to the key storage information to obtain storage area information corresponding to each group of current goods; according to the warehousing starting point position corresponding to each group of current goods, the position information of each warehousing area and the key storage information, a logistics warehousing path of each group of current goods is planned, an initial logistics warehousing path is obtained, scheduling optimization is performed on the initial logistics warehousing path based on a data twin warehousing model, and the logistics warehousing path of each group of current goods is obtained. And warehousing and storing the current goods of each group.

Description

Technical Field

[0001] This specification relates to the field of Internet of Things technology, and in particular to a real-time warehouse management method and device based on digital twins. Background Art

[0002] With the deep integration and rapid development of industrialization and informatization, the importance of the logistics industry as a bridge connecting production and consumption has become increasingly prominent, becoming a basic and strategic industry supporting the development of the national economy. In this context, warehousing logistics, as the core link in the logistics process, not only affects the storage and transit efficiency of goods, but also directly affects the response speed, cost control and customer satisfaction of the supply chain. Therefore, improving the management level of warehousing has become one of the key strategies for enterprises to enhance their market competitiveness and achieve sustainable development.

[0003] There are many deficiencies in the current manual monitoring and recording methods in warehouse management, such as low efficiency and prone to errors. In addition, the traditional warehouse does not effectively utilize the large amount of data generated in the warehouse, and does not realize data sharing, thus forming information islands, making the management efficiency of the entire warehouse low. With the continuous development of technologies such as the Internet of Things, big data, and artificial intelligence, intelligent management, especially intelligent management methods for warehouse logistics based on digital twin models, can effectively improve logistics efficiency and reduce operating costs, thereby improving the overall benefits and competitiveness of enterprises. However, in the existing solutions, it is difficult to intelligently manage the warehousing of goods in the warehouse in path planning and simulation. Summary of the invention

[0004] In order to solve the above technical problems, one or more embodiments of this specification provide a real-time warehouse management method and device based on digital twins.

[0005] One or more embodiments of this specification adopt the following technical solutions:

[0006] One or more embodiments of this specification provide a real-time warehouse management method based on digital twins, the method comprising:

[0007] According to the building data and IoT data corresponding to the current warehousing scene, a digital twin warehousing model corresponding to the current warehousing scene is constructed;

[0008] According to the arrival scanning information and historical storage information of the current goods, the current goods are clustered and grouped to determine the key storage information of each group of the current goods;

[0009] The digital twin warehousing model is queried according to the key storage information to obtain one or more storage area information corresponding to each group of current goods; wherein the storage area information includes: storage area location information and storage area space information;

[0010] According to the warehousing starting point location corresponding to each group of current goods, the location information of each storage area and the key storage information, the logistics warehousing path of each group of current goods is planned to obtain the initial logistics warehousing path;

[0011] The initial logistics entry paths are simulated according to the digital twin warehousing model to optimize the scheduling of the initial logistics entry paths and obtain the logistics entry paths of each group of current goods for warehousing storage.

[0012] Optionally, in one or more embodiments of the present specification, a digital twin warehousing model corresponding to the current warehousing scene is constructed according to the building data and IoT data corresponding to the current warehousing scene, specifically including:

[0013] Acquire the building data corresponding to the current storage scene, and input the building data into a preset modeling tool to construct a three-dimensional storage model corresponding to the current storage scene; wherein the building data includes: building structure data, storage shelf structure data and channel road network data;

[0014] Determine the location information of each IoT data in the current warehousing scene and the mapping object corresponding to each IoT data; wherein the mapping object includes: warehousing environment, warehousing goods and warehousing facilities and equipment;

[0015] Based on the location information and the mapping object, the Internet of Things data is mapped to the three-dimensional warehouse model to integrate the information of the Internet of Things data and obtain a digital twin warehouse model corresponding to the current warehouse scene.

[0016] Optionally, in one or more embodiments of the present specification, based on the location information and the mapping object, the IoT data is mapped to the three-dimensional warehouse model to integrate the IoT data and obtain a digital twin warehouse model corresponding to the current warehouse scene, specifically including:

[0017] Based on the location information and the mapping object, the three-dimensional warehouse model is searched to obtain corresponding three-dimensional warehouse model data, and a mapping relationship between the three-dimensional warehouse model data and the Internet of Things data is established;

[0018] According to the mapping relationship, the Internet of Things data is mapped to the corresponding position of the three-dimensional warehousing model, so that the three-dimensional warehousing model is dynamically updated according to the real-time update of the Internet of Things data to obtain the digital twin warehousing model corresponding to the current warehousing scene.

[0019] Optionally, in one or more embodiments of the present specification, the current goods are clustered and grouped according to the arrival scanning information and historical storage information of the current goods to determine the key storage information of each group of current goods, specifically including:

[0020] Obtaining a matching relationship between the arrival scanning information of the current goods and the historical storage information, so as to supplement the arrival scanning information according to the historical storage information corresponding to the current goods, and obtain the arrival storage related information corresponding to each of the current goods;

[0021] Performing vector conversion on the arrival storage related information to obtain a feature vector corresponding to each arrival storage related information;

[0022] Dividing each of the feature vectors based on a preset interval to obtain multiple groups of arrival storage related information, and randomly selecting any arrival storage related information in each group of arrival storage related information to obtain multiple initial clustering centers;

[0023] Taking the initial cluster center as the starting point, calculating the distance between each of the feature vectors and the initial cluster center, obtaining the initial cluster clusters corresponding to each initial cluster center, and determining the distance matrix between each of the initial cluster clusters according to the single linkage method;

[0024] The initial clustering clusters are merged based on the distance matrix, and the clustering matrix is ​​updated to iteratively update the clustering results corresponding to the feature vectors, so as to determine the key storage information of each group of current goods based on the clustering results.

[0025] Optionally, in one or more embodiments of the present specification, before clustering and grouping the current goods according to the arrival scanning information and historical storage information of the current goods to determine the key storage information of each group of the current goods, the method further includes:

[0026] Based on the Internet of Things platform corresponding to the current warehousing scene, obtaining the delivery information corresponding to the arrived goods of the current warehousing scene;

[0027] The arrival scanning information of the arrived goods is identified according to the preset scanning device, so as to compare the shipping information with the arrival scanning information and determine the qualified arrived goods as the current goods.

[0028] Optionally, in one or more embodiments of the present specification, the digital twin warehousing model is queried according to the key storage information to obtain one or more storage area information corresponding to each group of current goods, specifically including:

[0029] According to the real-time Internet of Things data corresponding to each location in the digital twin storage model, the storage range corresponding to the key storage information is screened and determined according to the real-time Internet of Things data;

[0030] According to the digital twin warehouse model, the outbound cargo data of each storage area within the storage range for multiple time periods are obtained, and the outbound cargo data sequence corresponding to each storage area is determined based on time series sorting, and the outbound cargo data sequence is input and output from the preset time series model to predict the outbound cargo data of each storage area in the next time period;

[0031] According to the outbound goods data of the next time period and the physical characteristics of each group of the current goods, each storage area within the storage range is screened to obtain one or more storage area information corresponding to each group of the current goods; wherein the physical characteristics include: the current goods quantity and the current goods size.

[0032] Optionally, in one or more embodiments of the present specification, according to the storage starting point position corresponding to each group of current goods, the location information of each storage area and the key storage information, the logistics storage path of each group of current goods is planned to obtain the initial logistics storage path, which specifically includes:

[0033] The starting point of each group of current goods and the location information of each storage area corresponding to each group of current goods are obtained to determine the movable area corresponding to each group of current goods;

[0034] Determine, according to the digital twin warehouse model and the key storage information, the area range within the movable area that does not conform to the current cargo storage environment, filter the movable area, obtain the remaining movable area, and determine the obstacle position of the remaining movable area based on the digital twin warehouse model;

[0035] Dividing the remaining movable area into a plurality of remaining movable sub-areas, so as to determine one or more logistics paths in each of the remaining movable sub-areas according to the channel road network data and the obstacle positions in the remaining movable sub-areas;

[0036] The logistics paths of the remaining movable sub-areas are connected to obtain one or more connected global paths as the initial logistics entry paths.

[0037] Optionally, in one or more embodiments of the present specification, each of the initial logistics entry paths is simulated according to the digital twin warehousing model to schedule and optimize the initial logistics entry paths, and the logistics entry paths of each group of current goods are obtained for entry storage, specifically including:

[0038] Taking any initial logistics warehousing path as the current solution, and processing each path node in the current solution according to the digital twin model to obtain one or more neighborhood solutions of the current solution;

[0039] The objective function values ​​of the current solution and the neighborhood solution are respectively simulated and calculated by the digital twin model, and if it is determined that the objective function value of the neighborhood solution is better than the current solution, the neighborhood solution is updated to the current solution;

[0040] If the objective function value of the current solution is better than the neighborhood solution, updating the neighborhood solution;

[0041] The updating process of the current solution and the neighborhood solution is iterated to optimize the scheduling of the initial logistics warehousing path according to the current optimal solution, and the logistics warehousing path of each group of current goods is obtained for warehousing storage.

[0042] Optionally, in one or more embodiments of the present specification, after constructing a digital twin warehousing model corresponding to the current warehousing scene according to the building data and IoT data corresponding to the current warehousing scene, the method further includes:

[0043] Acquire the real-time IoT data of each location of the data twin storage model, so as to determine the target data range corresponding to each real-time IoT data based on the collection device corresponding to the real-time IoT data;

[0044] If it is determined that the real-time Internet of Things data exceeds the target data range, an alarm prompt instruction is generated according to the mapping object corresponding to the real-time Internet of Things data and the value of the real-time Internet of Things data exceeding the target data range;

[0045] The alarm prompt instruction is sent to a remote terminal corresponding to the mapping object so as to perform maintenance on the fault in the current storage scene.

[0046] One or more embodiments of this specification provide a real-time warehouse management device based on digital twins, the device comprising:

[0047] at least one processor; and,

[0048] a memory communicatively connected to the at least one processor; wherein,

[0049] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: execute any of the above-mentioned methods.

[0050] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:

[0051] According to the arrival scanning information and historical storage information of the goods, the goods are clustered and grouped to determine the key storage information, which can more accurately grasp the storage needs of the goods and realize the precise management of the goods. By querying the digital twin storage model, the storage area information corresponding to each group of goods can be obtained, which is convenient for dynamically adjusting the storage layout according to the actual situation of the goods and the information of the storage area, and improving the utilization rate of the storage space. The digital twin model is used to simulate and optimize the initial logistics entry path, ensuring that the goods can be entered into the warehouse with the optimal entry logistics, thereby improving the storage efficiency. In addition, by adding IoT data to the digital twin model, the data of the current storage environment is shared in real time, avoiding the problem of storage management errors caused by untimely information synchronization. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0053] Figure 1 A flowchart of a real-time warehouse management method based on digital twins provided in an embodiment of this specification;

[0054] Figure 2 A logical schematic diagram of constructing a data twin warehousing model provided in an embodiment of this specification;

[0055] Figure 3 A structural schematic diagram of a real-time warehouse management device based on digital twins provided in an embodiment of this specification. DETAILED DESCRIPTION

[0056] The embodiments of this specification provide a real-time warehouse management method and device based on digital twins.

[0057] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0058] like Figure 1 As shown, the embodiment of this specification provides a flowchart of a real-time warehouse management method based on digital twins. Figure 1 It can be seen that in one or more embodiments of this specification, a real-time warehouse management method based on digital twins includes the following steps:

[0059] S101: Construct a digital twin warehousing model corresponding to the current warehousing scene based on the building data and Internet of Things data corresponding to the current warehousing scene.

[0060] In order to solve the problems of low efficiency and error-proneness of manual monitoring and recording in current warehouse management, and the lack of data sharing of traditional large amounts of data, which easily forms information islands and makes the management efficiency of the entire warehouse low, the embodiments of this specification first construct a digital twin warehouse model corresponding to the current warehouse scene based on the building data and IoT data corresponding to the current warehouse scene. Constructing a digital twin warehouse model corresponding to the current warehouse scene helps to obtain integrated IoT data in real time, avoid the problem of untimely data sharing, and at the same time reduce the cost of manual monitoring, which helps to improve the efficiency of warehouse management.

[0061] Specifically, in one or more embodiments of the present specification, a digital twin warehousing model corresponding to the current warehousing scene is constructed according to the building data and IoT data corresponding to the current warehousing scene, which specifically includes the following processes:

[0062] First, obtain the building data corresponding to the current storage scene, and input the building data into the preset modeling tool, so as to construct the 3D storage model corresponding to the current storage scene with the help of the modeling tool; it can be understood that the building data includes: building structure data, storage shelf structure data and channel road network data, etc. Then, Figure 2 The location information of each IoT data in the current warehousing scene and the mapping object corresponding to each IoT data are determined as shown; wherein the mapping objects include: warehousing environment, warehousing goods, and warehousing facilities and equipment. Based on the location information and the mapping object, the IoT data can be mapped to the corresponding position of the three-dimensional warehousing model, thereby realizing the information integration of the IoT data in the three-dimensional warehousing model and obtaining the digital twin warehousing model corresponding to the current warehousing scene.

[0063] Mapping IoT data to the corresponding position of the three-dimensional warehouse model realizes the intuitive display and integration of IoT data, that is, the integration of different types of data. The integrated data can be uniformly managed and analyzed in the digital twin warehouse model, providing more comprehensive and accurate information support for warehouse operations. In addition, through the real-time collection and mapping of IoT data, the digital twin warehouse model can be dynamically updated according to the real-time changes of IoT data, monitor various parameters and states in the warehouse environment in real time, and reduce the time and labor costs brought by manual supervision.

[0064] Further, in one or more embodiments of the present specification, based on the location information and the mapping object, the IoT data is mapped to the three-dimensional warehouse model to integrate the IoT data and obtain the digital twin warehouse model corresponding to the current warehouse scene, which specifically includes the following process:

[0065] First, based on the location information and the mapping object, the three-dimensional warehouse model is searched. This search process is to locate the specific location or object corresponding to the Internet of Things data in the three-dimensional warehouse model. After finding the corresponding three-dimensional warehouse model data, a mapping relationship between the three-dimensional warehouse model data and the Internet of Things data is established. Among them, it can be understood that this mapping relationship can be direct, such as the Internet of Things data directly corresponding to a certain point or surface in the three-dimensional model, or it can be indirect, such as converting the Internet of Things data into a certain representation in the three-dimensional model through a certain algorithm or rule. According to the mapping relationship, the Internet of Things data is mapped to the corresponding position of the three-dimensional warehouse model, so that the real-time state or change of the Internet of Things data can be directly reflected in the three-dimensional model, realizing the dynamic integration of data. Then, with the real-time update of the Internet of Things data, the three-dimensional warehouse model will be dynamically updated, so as to obtain the digital twin warehouse model corresponding to the current warehouse scene. The above process realizes the real-time mapping and updating of the Internet of Things data and the three-dimensional warehouse model, ensuring the accuracy and real-time performance of the digital twin warehouse model. By mapping the Internet of Things data to the three-dimensional warehouse model, the integration of different types of Internet of Things data can be supported, so that the digital twin warehouse model provides comprehensive information support for managers.

[0066] S102: Clustering and grouping the current goods according to the arrival scanning information and the historical storage information of the current goods to determine key storage information of each group of the current goods.

[0067] In the field of warehousing and logistics, the types, quantities, arrival times, storage requirements, and transportation requirements of goods vary. In order to realize the automated warehousing of goods, improve the efficiency and accuracy of warehousing, optimize the utilization of storage space, and reduce logistics costs, the system needs to be able to intelligently group and store goods according to their characteristics. Therefore, in order to realize the automated warehousing of goods and improve the rationality of warehousing logistics in the embodiments of this specification, the current goods will be clustered and grouped according to the arrival scanning information and historical warehousing information of the current goods to determine the key storage information of each group of current goods.

[0068] Specifically, in one or more embodiments of the present specification, the current goods are clustered and grouped according to the arrival scanning information and historical storage information of the current goods to determine the key storage information of each group of current goods, specifically including:

[0069] Because the arrival scanning information may only contain the basic attributes of the goods, such as the goods ID, type, quantity, etc., while the historical storage information provides more detailed information such as the storage history, environmental requirements, and optimal storage location of the goods in the warehouse, in order to supplement the arrival scanning information, the matching relationship between the arrival scanning information of the current goods and the historical storage information will be obtained, so as to supplement the arrival scanning information according to the historical storage information corresponding to the current goods, and obtain the arrival storage related information corresponding to each current goods. Then, the arrival storage related information is vector-converted to obtain the feature vector corresponding to each arrival storage related information. Then, each feature vector is divided according to the preset interval to obtain multiple groups of arrival storage related information, and any arrival storage related information in each group of arrival storage related information is randomly selected to obtain multiple initial cluster centers. By dividing the feature vectors by the preset interval, the system can quickly form multiple potential cluster subsets, providing good initial conditions for the subsequent clustering algorithm. Then, starting from the initial cluster center, the distance between each feature vector and the initial cluster center is calculated to obtain the initial cluster clusters corresponding to each initial cluster center, and the distance matrix between each initial cluster cluster is determined according to the single linkage method. In order to merge the initial cluster clusters according to the distance matrix, and update the cluster matrix to iteratively update the cluster results corresponding to the feature vectors, and determine the key storage information of each group of current goods based on the cluster results, for example, a cluster of data with more data in the cluster cluster is selected as the key storage information. It should be noted that in the entire iterative process, each merged cluster pair and its distance are recorded, and a dendrogram is constructed. The dendrogram shows the hierarchical clustering structure of the data points, from the initial single cluster, that is, the initial cluster center, to the final merged result. According to the dendrogram, a suitable threshold or number of clusters is selected for truncation to determine the final clustering result. The selection of the threshold can be determined according to the tightness of the clustering result, business requirements or data characteristics.

[0070] Further, in one or more embodiments of the present specification, before clustering and grouping the current goods according to the arrival scanning information and historical storage information of the current goods to determine the key storage information of each group of the current goods, in order to ensure that the current goods that have not been put into storage are qualified and avoid the loss caused by unqualified goods or mis-delivered goods and erroneous storage, the method also includes the following process:

[0071] Based on the Internet of Things platform corresponding to the current warehousing scenario, the shipping information corresponding to the arrived goods in the current warehousing scenario is obtained, and then the arrival scanning information of the arrived goods is identified according to the preset scanning device to compare the shipping information with the arrival scanning information, and determine the qualified arrived goods as the current goods.

[0072] S103: Query the digital twin warehousing model according to the key storage information to obtain one or more storage area information corresponding to each group of current goods; wherein the storage area information includes: storage area location information and storage area space information.

[0073] After the key storage information is obtained based on the above step S102, the embodiment of this specification queries the digital twin warehouse model based on the key storage information, thereby obtaining the storage area information matching the key storage information as the storage area information corresponding to the current acquisition of each group. It can be understood that the storage area information includes: storage area location information and storage area space information and other information.

[0074] That is, key storage information can be determined as key data used to determine how goods should be stored and managed in the warehouse. The digital twin warehouse model is a very important tool. It is a virtual warehouse model that can reflect the actual situation of the warehouse in real time, including the location, space size, and distribution of goods in each storage area. This model can be updated synchronously with the actual warehouse to ensure the accuracy and real-time nature of the data. When the system obtains key storage information, it will query the digital twin warehouse model based on this information. The purpose of the query is to find a storage area that matches this key storage information. The matching process may involve multiple factors, such as the temperature and humidity required by the goods, which need to match the conditions of the storage area. Through the query, the system can obtain storage area information that matches the key storage information. This information includes the location information and space information of the storage area. The location information can help the system determine the specific location of the goods in the warehouse, which is convenient for the storage and management of the goods. The space information provides the capacity and distribution of the storage area, which helps the system to reasonably plan the placement of goods and maximize the use of space.

[0075] Specifically, in one or more embodiments of the present specification, the digital twin warehousing model is queried according to the key storage information to obtain one or more storage area information corresponding to each group of current goods, which specifically includes the following process:

[0076] According to the real-time IoT data corresponding to each location in the digital twin storage model, the storage range corresponding to the key storage information is screened and determined according to the real-time IoT data. Then, according to the digital twin storage model, the outbound cargo data of multiple time periods of each storage area within the storage range is obtained, and the outbound cargo data sequence corresponding to each storage area is determined based on the time series sorting, and the outbound cargo data sequence is input and output from the preset time series model to predict the outbound cargo data of each storage area in the next time period. Then, according to the outbound cargo data of the next time period and the physical characteristics of each group of current cargo, each storage area within the storage range is screened, so as to obtain one or more storage area information corresponding to each group of current cargo. Among them, it can be understood that the physical characteristics include: the current cargo quantity and the current cargo size. In this process, through the real-time IoT data, the storage range corresponding to the key storage information can be quickly screened and determined, avoiding the large amount of manual or inefficient screening process required in the traditional method. By inputting the outbound cargo data sequence into the preset time series model, the outbound cargo data of each storage area in the next time period can be predicted. Based on the prediction results and the physical characteristics of the current cargo, such as quantity and size, the storage area information corresponding to each group of current cargo can be intelligently screened. Through accurate prediction and screening, storage resources, such as warehouse space, shelf location, etc., can be allocated more reasonably. This can not only improve storage efficiency, but also reduce operating costs.

[0077] S104: According to the warehousing starting point position corresponding to each group of current goods, the location information of each storage area and the key storage information, the logistics warehousing path of each group of current goods is planned to obtain an initial logistics warehousing path.

[0078] In order to ensure that the goods can be efficiently and accurately transported from the starting point of warehousing to the designated storage area, unnecessary transportation links and waiting time are reduced, thereby improving the efficiency of warehousing. In the embodiment of this specification, the logistics warehousing path of each group of current goods will be planned according to the starting point of warehousing corresponding to each group of current goods and the location information of each storage area and the key storage information, and the initial logistics warehousing path is obtained. For example: in a certain scene, according to the information of the storage area, the storage area B meets the storage conditions corresponding to the key storage information of the electronic product. At this time, the starting point of warehousing is the receiving area of ​​the logistics company. Then, starting from the receiving area, along the passage inside the warehouse, a shortest path can be determined as the initial logistics warehousing path to reach the storage area B. That is, in this process, by rationally planning the warehousing path, problems such as misplacement and omission of goods caused by human operation errors or inaccurate information can be reduced, the accuracy of warehousing management can be improved, and storage space and equipment resources can be fully utilized to improve resource utilization and storage capacity. In addition, efficient warehousing path planning can shorten the overall time from warehousing to outbound delivery of goods and improve the response speed of logistics services.

[0079] Specifically, in one embodiment of the present specification, in addition to using the shortest path as the initial logistics entry path, the logistics entry path of each group of current goods is planned according to the entry starting point position corresponding to each group of current goods, the location information of each storage area and the key storage information, and the initial logistics entry path is obtained, which can also be determined based on the following process:

[0080] First, according to the storage starting point corresponding to each group of current goods and the location information of each storage area corresponding to each group of current goods, the movable area corresponding to each group of current goods can be determined. It can be understood that this movable area is the range that the goods may pass from the starting point to the end point. Then, according to the digital twin storage model and key storage information, the area range that does not meet the current goods storage environment in the movable area can be determined, so as to filter the movable area, obtain the remaining movable area, and determine the obstacle position of the remaining movable area based on the digital twin storage model. Then, the remaining movable area is divided to obtain multiple remaining movable sub-areas, so as to determine one or more logistics paths in each remaining movable sub-area according to the channel road network data and obstacle position in the remaining movable sub-area. That is, the remaining movable area is divided into multiple smaller sub-areas to plan the logistics path more accurately. In each sub-area, one or more feasible logistics paths are determined according to the channel road network data and obstacle position. Finally, the logistics paths of each remaining movable sub-area are connected to form one or more connected global paths, which are the initial logistics storage paths.

[0081] By combining the starting point of each group of goods, the location information of the storage area, and the digital twin storage model, the movable area of ​​the goods can be accurately determined, and the areas that do not meet the storage environment can be effectively filtered out, thereby greatly improving the accuracy of path planning. It also fully considers the problem of path interruption caused by obstacles in the storage environment, that is, the problem that the goods are difficult to transport smoothly through the path where the obstacles are located due to obstacles, alleviating the cost waste caused by blind transportation.

[0082] S105: Simulate each of the initial logistics entry paths according to the digital twin warehousing model to optimize the scheduling of the initial logistics entry paths and obtain the logistics entry paths of each group of current goods for warehousing storage.

[0083] Traditional methods may be based on experience or simple rules for path planning, resulting in inaccurate paths, low transportation efficiency, and the inability to flexibly adjust according to the type, quantity, storage requirements, and changes in the storage environment of the goods, resulting in a waste of storage space and equipment resources. Therefore, in the embodiment of this specification, the initial logistics entry paths obtained in the above step S104 will be simulated based on the digital twin warehousing model to schedule and optimize the initial logistics entry paths, and obtain the logistics entry paths of each group of current goods for storage. Through simulation and optimization, the optimal logistics entry path can be found to reduce transportation time and waiting time, and by reducing unnecessary transportation links and repetitive labor, the operating costs of the enterprise can be reduced.

[0084] Specifically, in one or more embodiments of the present specification, after constructing a digital twin warehousing model corresponding to the current warehousing scene according to the building data and IoT data corresponding to the current warehousing scene, the method further includes the following process:

[0085] First, obtain the real-time IoT data of each location in the data twin warehouse model to determine the target data range corresponding to each real-time IoT data based on the collection device corresponding to the real-time IoT data. If it is determined that the real-time IoT data exceeds the target data range, an alarm prompt instruction is generated according to the mapping object corresponding to the real-time IoT data and the value of the real-time IoT data exceeding the target data range. Then send the alarm prompt instruction to the remote terminal corresponding to the mapping object to maintain the fault of the current warehouse scene. In this process, the real-time IoT data can be accurately mapped to the corresponding position in the warehouse model, so that the management personnel can obtain relevant information of the current warehouse environment, avoiding the problem caused by untimely information sharing. When the real-time IoT data exceeds the preset target data range, the system will automatically generate an alarm prompt instruction, which is convenient for the management personnel to quickly locate the problem for maintenance, reducing the idleness of equipment and waste of resources.

[0086] like Figure 3 As shown, the embodiment of this specification provides a structural schematic diagram of a real-time warehouse management device based on digital twins. Figure 3 It can be seen that in one or more embodiments of this specification, a real-time warehouse management device based on digital twins includes:

[0087] at least one processor; and,

[0088] a memory communicatively connected to the at least one processor; wherein,

[0089] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: execute any of the above-mentioned methods.

[0090] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0091] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A real-time warehouse management method based on digital twins, characterized in that: The method comprises: Constructing a digital twin warehousing model corresponding to the current warehousing scene based on the building data and IoT data corresponding to the current warehousing scene; According to the arrival scanning information and historical storage information of the current goods, the current goods are clustered and grouped to determine the key storage information of each group of the current goods; The digital twin warehousing model is queried according to the key storage information to obtain one or more storage area information corresponding to each group of current goods; wherein the storage area information includes: storage area location information and storage area space information; According to the warehousing starting point location corresponding to each group of current goods, the location information of each storage area and the key storage information, the logistics warehousing path of each group of current goods is planned to obtain the initial logistics warehousing path; The initial logistics warehousing paths are simulated according to the digital twin warehousing model to optimize the scheduling of the initial logistics warehousing paths and obtain the logistics warehousing paths of each group of current goods for warehousing storage.

2. A real-time warehouse management method based on digital twins according to claim 1, characterized in that: According to the building data and IoT data corresponding to the current warehousing scene, a digital twin warehousing model corresponding to the current warehousing scene is constructed, specifically including: Acquire the building data corresponding to the current storage scene, and input the building data into a preset modeling tool to construct a three-dimensional storage model corresponding to the current storage scene; wherein the building data includes: building structure data, storage shelf structure data and channel road network data; Determine the location information of each IoT data in the current warehousing scene and the mapping object corresponding to each IoT data; wherein the mapping object includes: warehousing environment, warehousing goods and warehousing facilities and equipment; Based on the location information and the mapping object, the Internet of Things data is mapped to the three-dimensional warehouse model to integrate the information of the Internet of Things data and obtain a digital twin warehouse model corresponding to the current warehouse scene.

3. A real-time warehouse management method based on digital twins according to claim 2, characterized in that: Based on the location information and the mapping object, the IoT data is mapped to the three-dimensional warehouse model to integrate the IoT data and obtain a digital twin warehouse model corresponding to the current warehouse scene, specifically including: Based on the location information and the mapping object, the three-dimensional warehouse model is searched to obtain corresponding three-dimensional warehouse model data, and a mapping relationship between the three-dimensional warehouse model data and the Internet of Things data is established; According to the mapping relationship, the Internet of Things data is mapped to the corresponding position of the three-dimensional warehousing model, so that the three-dimensional warehousing model is dynamically updated according to the real-time update of the Internet of Things data to obtain the digital twin warehousing model corresponding to the current warehousing scene.

4. The real-time warehouse management method based on digital twin according to claim 1 is characterized in that: According to the arrival scanning information and historical storage information of the current goods, the current goods are clustered and grouped to determine the key storage information of each group of current goods, including: Obtaining a matching relationship between the arrival scanning information of the current goods and the historical storage information, so as to supplement the arrival scanning information according to the historical storage information corresponding to the current goods, and obtain the arrival storage related information corresponding to each of the current goods; Performing vector conversion on the arrival storage related information to obtain a feature vector corresponding to each arrival storage related information; Dividing each of the feature vectors based on a preset interval to obtain multiple groups of arrival storage related information, and randomly selecting any arrival storage related information in each group of arrival storage related information to obtain multiple initial clustering centers; Taking the initial cluster center as the starting point, calculating the distance between each of the feature vectors and the initial cluster center, obtaining the initial cluster clusters corresponding to each initial cluster center, and determining the distance matrix between each of the initial cluster clusters according to the single linkage method; The initial clustering clusters are merged based on the distance matrix, and the clustering matrix is ​​updated to iteratively update the clustering results corresponding to the feature vectors, so as to determine the key storage information of each group of current goods based on the clustering results.

5. A real-time warehouse management method based on digital twins according to claim 4, characterized in that: Before clustering and grouping the current goods according to the arrival scanning information and the historical storage information of the current goods to determine the key storage information of each group of the current goods, the method further includes: Based on the Internet of Things platform corresponding to the current warehousing scene, obtaining the delivery information corresponding to the arrived goods of the current warehousing scene; The arrival scanning information of the arrived goods is identified according to the preset scanning device, so as to compare the shipping information with the arrival scanning information and determine the qualified arrived goods as the current goods.

6. The real-time warehouse management method based on digital twin according to claim 1 is characterized in that: The digital twin warehousing model is queried according to the key storage information to obtain one or more storage area information corresponding to each group of current goods, specifically including: According to the real-time Internet of Things data corresponding to each location in the digital twin storage model, the storage range corresponding to the key storage information is screened and determined according to the real-time Internet of Things data; According to the digital twin warehouse model, the outbound cargo data of each storage area within the storage range for multiple time periods are obtained, and the outbound cargo data sequence corresponding to each storage area is determined based on time series sorting, and the outbound cargo data sequence is input and output from the preset time series model to predict the outbound cargo data of each storage area in the next time period; According to the outbound goods data of the next time period and the physical characteristics of each group of the current goods, each storage area within the storage range is screened to obtain one or more storage area information corresponding to each group of the current goods; wherein the physical characteristics include: the current goods quantity and the current goods size.

7. The real-time warehouse management method based on digital twin according to claim 1 is characterized in that: According to the entry starting point location corresponding to each group of current goods, the location information of each storage area and the key storage information, the logistics entry path of each group of current goods is planned to obtain the initial logistics entry path, which specifically includes: The starting point of each group of current goods and the location information of each storage area corresponding to each group of current goods are obtained to determine the movable area corresponding to each group of current goods; Determine, according to the digital twin warehouse model and the key storage information, the area range within the movable area that does not conform to the current cargo storage environment, filter the movable area, obtain the remaining movable area, and determine the obstacle position of the remaining movable area based on the digital twin warehouse model; Dividing the remaining movable area into a plurality of remaining movable sub-areas, so as to determine one or more logistics paths in each of the remaining movable sub-areas according to the channel road network data and the obstacle positions in the remaining movable sub-areas; The logistics paths of the remaining movable sub-areas are connected to obtain one or more connected global paths as the initial logistics entry paths.

8. The real-time warehouse management method based on digital twin according to claim 1 is characterized in that: The initial logistics entry paths are simulated according to the digital twin warehousing model to optimize the scheduling of the initial logistics entry paths, and the logistics entry paths of each group of current goods are obtained for entry storage, specifically including: Taking any initial logistics warehousing path as the current solution, and processing each path node in the current solution according to the digital twin model to obtain one or more neighborhood solutions of the current solution; The objective function values ​​of the current solution and the neighborhood solution are respectively simulated and calculated by the digital twin model, and if it is determined that the objective function value of the neighborhood solution is better than the current solution, the neighborhood solution is updated to the current solution; If the objective function value of the current solution is better than the neighborhood solution, updating the neighborhood solution; The updating process of the current solution and the neighborhood solution is iterated to optimize the scheduling of the initial logistics warehousing path according to the current optimal solution, and the logistics warehousing path of each group of current goods is obtained for warehousing storage.

9. The real-time warehouse management method based on digital twin according to claim 2 is characterized in that: After constructing a digital twin storage model corresponding to the current storage scene according to the building data and the Internet of Things data corresponding to the current storage scene, the method further includes: Acquire the real-time IoT data of each location of the data twin storage model, so as to determine the target data range corresponding to each real-time IoT data based on the collection device corresponding to the real-time IoT data; If it is determined that the real-time Internet of Things data exceeds the target data range, an alarm prompt instruction is generated according to the mapping object corresponding to the real-time Internet of Things data and the value of the real-time Internet of Things data exceeding the target data range; The alarm prompt instruction is sent to a remote terminal corresponding to the mapping object so as to perform maintenance on the fault in the current storage scene.

10. A real-time warehouse management device based on digital twins, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: execute any of the methods described in claims 1-9.

Images