Warehouse article management method, system and equipment based on industrial Internet of Things, and medium

Abstract

The invention relates to a warehouse article management method, system and device based on industrial Internet of Things and a medium, and the method comprises the steps: building a warehouse three-dimensional model, updating the state of a goods location in real time, and combining the basic information of to-be-stored goods and the predicted storage time, and determining a candidate storage region and the priority of the candidate storage region; and determining an optimal storage area according to the area priority and the real-time storage state, planning an optimal storage path, and finally controlling the goods moving equipment to complete the storage operation of the stored goods. The technical problem that in the prior art, a high-density stereoscopic warehouse lacks a dynamic optimization capability based on goods basic information and predicted storage duration, and consequently storage space distribution is unreasonable is solved, and the purposes of monitoring the storage state in real time based on the industrial Internet of Things and improving the storage efficiency are achieved. And intelligent storage position optimization distribution is carried out according to the basic information of the goods and the predicted storage duration, so that the technical effect of reasonable distribution of the storage space is realized.

Description

Technical Field

[0001] The present invention relates to the field of industrial Internet of Things, and particularly to a warehousing item management method, system, device and medium based on the industrial Internet of Things. Background Art

[0002] With the rapid development of modern logistics industry, high-density stereoscopic warehouses are widely used in various industries. In the process of warehousing item management, reasonable space allocation is of great significance for improving warehousing efficiency. At present, the storage location allocation of goods in high-density stereoscopic warehouses usually adopts the methods of fixed zoning or empirical management, lacking a dynamic optimization mechanism. Specifically, when the existing warehousing item management allocates the storage location of goods, it often only considers the current state of the warehousing space, and fails to fully utilize the basic information of the goods (such as volume, weight, category, etc.) and information such as storage duration, resulting in unreasonable utilization of the warehousing space and unreasonable warehousing space allocation. Summary of the Invention

[0003] The main purpose of this application is to provide a warehousing item management method, system, device and medium based on the industrial Internet of Things, aiming to solve the technical problem that the high-density stereoscopic warehouse in the prior art lacks the dynamic optimization ability based on the basic information of goods and predicted storage duration, resulting in unreasonable warehousing space allocation.

[0004] To achieve the above purpose, this application provides a warehousing item management method based on the industrial Internet of Things, which is applied to a warehousing item management system. The warehousing item management system includes a management platform, a sensing network platform and an object platform, and the object platform includes sensors installed on storage locations; the method includes: establishing a three-dimensional model of the target warehouse; collecting the occupancy status information of the storage locations in the target warehouse in real time through the sensors installed on the storage locations, and updating the three-dimensional model of the target warehouse based on the occupancy status information to obtain a real-time storage status model; obtaining the basic information of the goods to be stored, where the basic information includes the volume information, weight information and category information of the goods to be stored; according to the basic information, obtaining the predicted storage duration of the goods to be stored; determining a plurality of candidate storage areas based on the basic information, and determining the storage area priorities of the plurality of candidate storage areas based on the basic information and the predicted storage duration; determining the optimal storage area of the goods to be stored according to the storage area priorities of the plurality of candidate storage areas and the real-time storage status model; using the real-time storage status model to plan the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage area; controlling the goods moving device to store the goods to be stored in the optimal storage area according to the storage path, and updating the real-time storage status model after the goods to be stored are stored.

[0005] Optionally, obtaining the predicted storage duration of the goods to be stored according to the basic information includes: constructing a goods storage prediction network, which includes a goods analysis sub-model and a duration prediction sub-model; obtaining the storage characteristics of the goods to be stored according to the basic information and the goods analysis sub-model; and obtaining the predicted storage duration of the goods to be stored according to the basic information, the storage characteristics and the duration prediction sub-model.

[0006] Optionally, constructing the goods storage prediction network, which includes a goods analysis sub-model and a duration prediction sub-model, includes: obtaining historical goods storage records, and generating a historical goods basic information set, a historical goods storage characteristics set and a historical goods storage duration set based on the historical goods storage records, where the historical goods storage records have multiple historical storage categories; classifying the historical goods basic information set and the historical goods storage characteristics set according to the multiple historical storage categories to obtain multiple historical goods basic information subsets, multiple historical goods storage characteristics subsets and multiple historical goods storage duration subsets; establishing a category information extraction layer according to the multiple historical storage categories, and establishing multiple storage characteristics mapping layers according to the multiple historical goods basic information subsets and the multiple historical goods storage characteristics subsets; connecting the multiple storage characteristics mapping layers in parallel to the category information extraction layer to obtain the goods analysis sub-model; establishing multiple storage duration mapping layers according to the multiple historical goods basic information subsets, the multiple historical goods storage characteristics subsets and the multiple historical goods storage duration subsets to form the duration prediction sub-model; and connecting the goods analysis sub-model and the duration prediction sub-model to obtain the goods storage prediction network.

[0007] Optionally, determining multiple candidate storage areas based on the basic information, and determining the storage area priorities of the multiple candidate storage areas based on the basic information and the predicted storage duration includes: determining applicable bin specifications according to the volume information and weight information in the basic information, and determining multiple candidate storage areas based on the applicable bin specifications and the three-dimensional model of the target warehouse; obtaining the storage environment requirements of the goods to be stored according to the category information in the basic information; calculating the applicability scores of the multiple candidate storage areas according to the predicted storage duration and the storage environment requirements; and sorting the multiple candidate storage areas based on the applicability scores of the multiple candidate storage areas to obtain the storage area priorities of the candidate storage areas.

[0008] Optionally, calculating the applicability scores of the multiple candidate storage areas according to the predicted storage duration and the storage environment requirements includes: constructing an applicability score calculation formula as shown in the following formula:

[0009] Among them, represents the applicability score of the candidate storage area, represents the predicted storage duration, represents the average storage duration of the candidate storage area, represents the required value of the i-th environmental indicator in the storage environment requirements, represents the actual value of the i-th environmental indicator of the candidate storage area, represents the weight of the i-th environmental indicator, represents the total number of environmental indicators, , is the weight coefficient, and ; Obtain the average storage duration and the actual values of the environmental indicators of each of the candidate storage areas; Based on the predicted storage duration of the goods to be stored, the storage environment requirements, and the average storage duration and the actual values of the environmental indicators of each candidate storage area, and in combination with the applicability score calculation formula, obtain the applicability scores of each candidate storage area.

[0010] Optionally, the determining the optimal storage area for the goods to be stored according to the storage area priorities of multiple candidate storage areas and the real-time storage status model includes: sequentially traversing multiple candidate storage areas based on the storage area priorities; querying the occupancy status of the currently traversed candidate storage area in the real-time storage status model; if the currently traversed candidate storage area is in an idle state, then determine the currently traversed candidate storage area as the optimal storage area.

[0011] Optionally, the using the real-time storage status model to plan the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage area includes: establishing a passable path network based on the real-time storage status model; in the passable path network, taking the position coordinates of the entrance as the starting node and taking the position coordinates of the optimal storage area as the target node; according to the starting node and the target node, searching for the shortest path in the passable path network to obtain the storage path.

[0012] In addition, to achieve the above object, the present application provides a warehouse item management system based on the industrial Internet of Things for implementing a warehouse item management method based on the industrial Internet of Things. The warehouse item management system includes a management platform, a sensing network platform, and an object platform that are communicatively connected in sequence. The object platform includes sensors installed on storage locations, and is used to collect in real time the information on the occupancy status of storage locations in the target warehouse. The sensing network platform is used to obtain the information on the occupancy status of storage locations and transmit the information on the occupancy status of storage locations to the management platform. The management platform includes a model establishment module, a warehouse modeling module, a goods information module, a duration prediction module, a region screening module, a region optimization module, a path planning module, and a storage execution module. Among them, the model establishment module is used to establish a three-dimensional model of the target warehouse; the warehouse modeling module is used to collect in real time the information on the occupancy status of storage locations in the target warehouse through the sensors installed on storage locations, and update the three-dimensional model of the target warehouse based on the information on the occupancy status of storage locations to obtain a real-time storage status model; the goods information module is used to obtain the basic information of the goods to be stored, where the basic information includes the volume information, weight information, and category information of the goods to be stored; the duration prediction module is used to obtain the predicted storage duration of the goods to be stored according to the basic information; the region screening module is used to determine multiple candidate storage regions based on the basic information, and determine the storage region priorities of the multiple candidate storage regions based on the basic information and the predicted storage duration; the region optimization module is used to determine the optimal storage region for the goods to be stored according to the storage region priorities of the multiple candidate storage regions and the real-time storage status model; the path planning module is used to plan the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage region by using the real-time storage status model; the storage execution module is used to control the goods moving device to store the goods to be stored in the optimal storage region according to the storage path, and update the real-time storage status model after the storage of the goods to be stored is completed.

[0013] In addition, to achieve the above object, the present application also provides an electronic device, including a memory and a processor. The memory is used to store a computer software program; the processor is used to read and execute the computer software program, and further implement a warehouse item management method based on the industrial Internet of Things.

[0014] In addition, the present application also provides a non-transitory computer-readable storage medium, in which a computer software program is stored, and when the computer software program is executed by a processor, a warehouse item management method based on the industrial Internet of Things is implemented.

[0015] The beneficial effects that the present application can achieve are as follows: Build a 3D model of the target warehouse to provide a model basis for subsequent storage item management; install sensors at the storage locations to collect the occupancy status information of the storage locations in the target warehouse in real time, and update the 3D model of the target warehouse based on the occupancy status information of the storage locations to obtain a real-time storage status model. Through the industrial Internet of Things system, the warehouse status can be grasped in real time, and a dynamic digital warehousing model can be constructed, providing an accurate data basis for subsequent optimization decisions. Obtain the basic information of the goods to be stored, where the basic information includes the volume information, weight information, and category information of the goods to be stored, providing the necessary goods characteristic data for allocating storage locations. According to the basic information, obtain the predicted storage duration of the goods to be stored, providing an important decision-making basis for the reasonable allocation of storage locations. Determine multiple candidate storage areas based on the basic information, and determine the storage area priorities of the multiple candidate storage areas based on the basic information and the predicted storage duration, establishing a storage area optimization evaluation mechanism. Determine the optimal storage area for the goods to be stored according to the storage area priorities of the multiple candidate storage areas and the real-time storage status model, realizing the intelligent decision-making of storage locations and ensuring the rationality of space allocation. Use the real-time storage status model to plan the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage area, improving the storage efficiency. According to the storage path, control the goods moving equipment to store the goods to be stored in the optimal storage area, and update the real-time storage status model after the storage of the goods to be stored is completed, realizing the automatic execution of the storage process and ensuring the real-time update of the warehousing status data.

[0016] Through the above steps, the technical problem in the prior art that the management of storage items lacks the dynamic optimization ability based on the basic information of the goods and the storage duration, resulting in unreasonable storage space allocation, is solved, and the reasonable allocation of storage space is realized. Brief Description of the Drawings

[0017] Figure 1 It is a schematic flowchart of the method for managing storage items based on the industrial Internet of Things provided by the present invention; Figure 2 It is a schematic structural diagram of the storage item management system based on the industrial Internet of Things provided by the present invention; Figure 3 It is a schematic structural diagram of the electronic device provided by the present invention; Figure 4 It is a schematic structural diagram of a computer-readable storage medium provided by the present invention.

[0018] In the drawings, the components represented by each reference numeral are as follows: Warehouse item management system 100 based on industrial Internet of Things, management platform 101, sensing network platform 102, object platform 103, model establishment module 11, warehouse modeling module 12, goods information module 13, duration prediction module 14, area screening module 15, area optimization module 16, path planning module 17, storage execution module 18, electronic device 200, memory 210, processor 220, computer program 211, computer-readable storage medium 300.

[0019] The realization of the purpose of this application, functional features and advantages will be further described in conjunction with the embodiments and with reference to the accompanying drawings. Detailed implementation manners

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship and movement conditions between components in a certain preset posture (as shown in the accompanying drawings). If the preset posture changes, the directional indications will also change accordingly.

[0022] In the present invention, unless otherwise clearly defined and limited, terms such as "connection" and "fixation" should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0023] In addition, if the descriptions such as "first" and "second" are involved in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the meaning of "and / or" appearing throughout the text includes three parallel scenarios. Taking "A and / or B" as an example, it includes Scenario A, or Scenario B, or the scenario where both A and B are satisfied simultaneously. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0024] Embodiment 1: As Figure 1 shown, the embodiment of the present invention provides a method for managing storage items based on the industrial Internet of Things, which is applied to a storage item management system. The storage item management system can be, for example, a storage item management system based on the industrial Internet of Things. The storage item management system based on the industrial Internet of Things may include a management platform, a sensing network platform, and an object platform. The object platform includes sensors installed on the storage locations. The method includes: S1: Establish a three-dimensional model of the target warehouse; S2: Real-time collect the occupancy status information of the storage locations in the target warehouse through the sensors installed on the storage locations, and update the three-dimensional model of the target warehouse based on the occupancy status information to obtain a real-time storage status model; S3: Obtain the basic information of the goods to be stored, where the basic information includes the volume information, weight information, and category information of the goods to be stored; S4: According to the basic information, obtain the predicted storage duration of the goods to be stored; S5: Determine multiple candidate storage areas based on the basic information, and determine the storage area priorities of the multiple candidate storage areas based on the basic information and the predicted storage duration; S6: Determine the optimal storage area for the goods to be stored according to the storage area priorities of the multiple candidate storage areas and the real-time storage status model; S7: Use the real-time storage status model to plan the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage area; S8: According to the storage path, control the goods moving device to store the goods to be stored in the optimal storage area, and update the real-time storage status model after the goods to be stored are stored.

[0025] Specifically, the warehouse item management method based on the industrial Internet of Things proposed in the embodiments of the present application is specifically applied to a warehouse item management system based on the industrial Internet of Things. The warehouse item management system based on the industrial Internet of Things consists of three main platforms, namely, a management platform, a sensor network platform, and an object platform, where the object platform is configured with sensors installed on storage locations. The management platform serves as the central control unit of the system, responsible for data processing, execution of business logic, and presentation of the user interface; the sensor network platform acts as the intermediate layer for data transmission, responsible for coordinating and managing the communication network among various sensing devices to ensure the reliability and stability of information transmission; the object platform is the physical entity layer, including sensors installed on storage locations deployed in each storage location of the warehouse, used to collect information data such as the status and location of items in real time.

[0026] First, take a certain high-density stereoscopic warehouse as the target warehouse, and obtain the spatial dimension data of the target warehouse through laser ranging equipment, including basic parameters such as the length, width, and height of the warehouse. Then, use 3D modeling software to construct the basic framework model of the target warehouse according to the obtained spatial dimension data to obtain the 3D model of the target warehouse. Next, according to the shelf layout information inside the target warehouse, add shelf structures to the 3D model of the target warehouse and assign a unique 3D coordinate identifier to each storage location. Subsequently, install sensors at the storage locations to collect data in the target warehouse in real time. Among them, the sensors installed at the storage locations can be configured according to requirements, such as including but not limited to infrared sensors and gravity sensors. The infrared sensors are used to detect whether the storage location space is occupied, and the gravity sensors are used to confirm the actual placement status of the goods. Then, determine the occupancy status information of the storage locations in the target warehouse according to the data collected by the sensors installed at the storage locations, and update the 3D model of the target warehouse according to the occupancy status information, that is, map the occupancy status data collected by the sensor components to the attribute fields of the corresponding storage locations in the 3D model of the target warehouse through the unique identifier of the storage location to form a real-time storage status model. Whenever a change in the occupancy status is detected by the sensors installed at the storage locations, an update operation will be triggered to ensure that the status information in the real-time storage status model is consistent with the actual situation. Then, collect the volume information, weight information, and category information of the goods to be stored through the data collection equipment at the warehouse inbound end as the basic information of the goods to be stored. Among them, the volume information is obtained by scanning the goods to be stored with a 3D scanner, including the length, width, and height data of the goods; the weight information is collected by the electronic scale at the inbound end to record the actual weight value of the goods; the category information is obtained by scanning the electronic tag or barcode of the goods, including attribute information such as the type and specification of the goods. The collection process of the basic information is automated, which can ensure the accuracy and timeliness of the data. When the goods to be stored arrive at the inbound end, the data collection equipment automatically starts the collection process to complete the collection and recording of the basic information of the goods. At the same time, the collected data is preprocessed and formatted to ensure the standardization and usability of the data. These basic information will be used as an important basis for subsequent prediction of storage duration and determination of storage areas.

[0027] Subsequently, based on the basic information, obtain the predicted storage duration of the goods to be stored. For example, first extract the basic information and actual storage duration data of historical goods from the database of the warehouse management system to establish a statistical sample set; then, by analyzing the correlation between the basic information and the storage duration in the sample set, establish a regression prediction model. Specifically, using the multiple linear regression method, take the volume information and weight information of the goods as independent variables, and the storage duration as the dependent variable, and calculate the regression coefficients through the least squares method. For the category information, convert it into numerical features by one-hot encoding and then add it to the regression model. Finally, input the basic information of the goods to be stored into the trained regression model to obtain the predicted storage duration. Next, classify and extract the features of the storage areas in the target warehouse, and according to the basic information of the goods to be stored, such as parameters like volume and weight, screen out the candidate storage areas that meet the storage conditions from the classified storage areas. Then, comprehensively consider the storage requirements of the goods and the characteristic parameters of each candidate storage area, and use the predicted storage duration as an important indicator, and combine other storage conditions for comprehensive evaluation to calculate an applicability score for each candidate storage area. After that, sort the candidate storage areas according to the calculated applicability scores to determine the storage area priorities of each candidate storage area, ensuring that the goods to be stored are assigned to the most suitable storage area.

[0028] After that, adopt the method of priority traversal, and in the order from high to low of the storage area priorities, check the current status of each candidate storage area in the real-time storage status model one by one. When it is checked that a certain candidate storage area is in an idle state, directly determine this area as the optimal storage area, thus completing the determination of the storage area. Then, clarify the starting and ending positions of the goods transportation. Among them, the starting point is the entrance position of the target warehouse, and the ending point is the position of the determined optimal storage area. Subsequently, use the real-time storage status model to analyze the channel conditions in the current warehouse and avoid the occupied or blocked paths. After that, calculate a reasonable transportation path from the entrance to the optimal storage area through the path planning algorithm as the storage path of the goods to be stored to ensure the safety and efficiency of the goods transportation. Next, convert the planned storage path into a sequence of motion instructions that can be executed by the goods moving device. Send these instructions to the goods moving device to control it to transport the goods to be stored to the optimal storage area according to the predetermined path. When the goods moving device completes the storage task, receive the status feedback of the storage completion, and immediately update the occupancy status of the corresponding storage location in the real-time storage status model to maintain the consistency between the model and the actual warehousing status. This automated storage control method not only improves the storage efficiency but also ensures the real-time accuracy of the warehousing status information.

[0029] As an alternative implementation, the obtaining the predicted storage duration of the goods to be stored according to the basic information includes: S41: Construct a goods storage prediction network, where the goods storage prediction network includes a goods analysis sub-model and a duration prediction sub-model; S42: Obtain the storage characteristics of the goods to be stored according to the basic information and the goods analysis sub-model; S43: Obtain the predicted storage duration of the goods to be stored according to the basic information, the storage characteristics, and the duration prediction sub-model.

[0030] Specifically, when obtaining the predicted storage duration of the goods to be stored according to the basic information, first, construct a goods storage prediction network composed of a goods analysis sub-model and a duration prediction sub-model. This network adopts a dual-model structure design and can deeply analyze and predict goods information in stages. Input the basic information of the goods to be stored into the goods analysis sub-model for processing. The goods analysis sub-model obtains storage characteristics that can represent the storage characteristics of the goods to be stored by extracting and analyzing the basic information. These storage characteristics contain key attribute information of the goods during the warehousing process. Subsequently, input the basic information of the goods to be stored and the storage characteristics obtained through the goods analysis sub-model into the duration prediction sub-model. The duration prediction sub-model calculates the predicted storage duration of the goods to be stored based on the input information through the established prediction mapping relationship. This prediction method based on the dual model improves the prediction accuracy by extracting and utilizing goods information step by step.

[0031] As an optional implementation manner, the construction of the goods storage prediction network, where the goods storage prediction network includes a goods analysis sub-model and a duration prediction sub-model, includes: S411: Obtain historical goods storage records, and generate a historical goods basic information set, a historical goods storage characteristics set, and a historical goods storage duration set based on the historical goods storage records. The historical goods storage records have multiple historical storage categories; S412: Classify the historical goods basic information set and the historical goods storage characteristics set according to the multiple historical storage categories to obtain multiple historical goods basic information subsets, multiple historical goods storage characteristics subsets, and multiple historical goods storage duration subsets; S413: Establish a category information extraction layer according to the multiple historical storage categories, and establish multiple storage characteristic mapping layers according to the multiple historical goods basic information subsets and the multiple historical goods storage characteristics subsets; S414: Connect the multiple storage characteristic mapping layers to the category information extraction layer in parallel to obtain the goods analysis sub-model; S415: Establish multiple storage duration mapping layers based on the multiple historical goods basic information subsets, multiple historical goods storage feature subsets, and the multiple historical goods storage duration subsets to form the duration prediction sub-model; S416: Connect the goods analysis sub-model and the duration prediction sub-model to obtain the goods storage prediction network.

[0032] Specifically, when constructing the goods storage prediction network, first, obtain the historical goods storage records. The historical goods storage records contain the complete storage cycle data of the goods in the warehouse. Based on these records, extract the historical goods basic information set (including basic information such as the volume, weight, and category of the historical goods), the historical goods storage feature set (including the feature data shown by the historical goods during storage), and the historical goods storage duration set (including the actual storage duration data of the historical goods). These historical goods storage records cover multiple historical storage categories, ensuring the diversity and representativeness of the data. Then, classify and organize the extracted data sets based on multiple historical storage categories. Specifically, divide the historical goods basic information set and the historical goods storage feature set according to the category to obtain multiple historical goods basic information subsets, multiple historical goods storage feature subsets, and multiple historical goods storage duration subsets. This classification processing enables the subsequent model training to better capture the characteristics of different categories of goods.

[0033] When establishing the model structure, first, establish a category information extraction layer according to multiple historical storage categories. This layer encodes and characterizes the category information to map goods of different categories into corresponding feature vectors. At the same time, establish multiple storage feature mapping layers based on multiple historical goods basic information subsets and multiple historical goods storage feature subsets. Each mapping layer establishes the conversion relationship of different categories of goods from basic information to storage features. By connecting multiple storage feature mapping layers in parallel to the category information extraction layer, a complete goods analysis sub-model is formed. This sub-model can obtain the storage features of goods based on the category and basic information of the goods. Then, use multiple historical goods basic information subsets, multiple historical goods storage feature subsets, and multiple historical goods storage duration subsets to establish multiple storage duration mapping layers. For each category, train the storage duration mapping layer based on the corresponding historical data so that it can predict the storage duration according to the basic information and storage features of the goods. These trained storage duration mapping layers constitute the duration prediction sub-model. After that, connect the goods analysis sub-model and the duration prediction sub-model to obtain a complete goods storage prediction network. This network extracts the goods features through the goods analysis sub-model and then predicts the storage duration by the duration prediction sub-model to achieve the prediction of the storage duration.

[0034] As an alternative implementation, determining multiple candidate storage areas based on the basic information and determining the storage area priorities of the multiple candidate storage areas based on the basic information and the predicted storage duration includes: S51: Determine the applicable storage location specifications according to the volume information and weight information in the basic information, and determine multiple candidate storage areas based on the applicable storage location specifications and the three-dimensional model of the target warehouse; S52: Obtain the storage environment requirements for the goods to be stored based on the category information in the basic information; S53: Calculate the applicability scores of the multiple candidate storage areas according to the predicted storage duration and the storage environment requirements; S54: Sort the multiple candidate storage areas based on the applicability scores of the multiple candidate storage areas to obtain the storage area priorities of the respective candidate storage areas.

[0035] Specifically, when determining the candidate storage areas and the storage area priorities, first, determine the applicable storage location specifications according to the volume information and weight information of the goods to be stored. Match the volume information of the goods to be stored with the dimensions of various storage locations in the target warehouse, and at the same time compare the weight information with the load-bearing capacity of the storage locations, so as to screen out the storage location specifications suitable for storing the goods. Then, based on the selected applicable storage location specifications and combined with the storage location distribution in the three-dimensional model of the target warehouse, determine multiple candidate storage areas that meet the storage conditions. Next, according to the category information of the goods to be stored, query the storage environment requirements for this type of goods from the preset storage environment parameter library. These requirements include various environmental parameter conditions that need to be met during the storage process of this type of goods.

[0036] Next, use the predicted storage duration and the storage environment requirements as evaluation indicators to calculate the applicability scores for each candidate storage area. The scoring process comprehensively considers the matching degree between the predicted storage duration and the characteristics of the candidate area, as well as the compliance degree of the environmental parameters. After that, sort the multiple candidate storage areas according to the calculated applicability scores to obtain the storage area priorities of the respective candidate storage areas. The level of priority reflects the degree of suitability of each storage area for the goods, providing a basis for selecting the optimal storage area later.

[0037] As an alternative implementation, the calculating the applicability scores of the multiple candidate storage areas according to the predicted storage duration and the storage environment requirements includes: S531: Construct an applicability score calculation formula as shown in the following formula:

[0038] where represents the applicability score of the candidate storage area, Indicates the predicted storage duration, Indicates the average storage duration of the candidate storage area, Indicates the required value of the i-th environmental indicator in the storage environment requirements, Indicates the actual value of the i-th environmental indicator of the candidate storage area, Indicates the weight of the i-th environmental indicator, Indicates the total number of environmental indicators, , Is the weight coefficient, and ; S532: Obtain the average storage duration and the actual environmental indicator values of each of the candidate storage areas; S533: Based on the predicted storage duration of the goods to be stored, the storage environment requirements, and the average storage duration and the actual environmental indicator values of each candidate storage area, and in combination with the applicability score calculation formula, obtain the applicability scores of each candidate storage area.

[0039] Specifically, when calculating the applicability score of a candidate storage area, first construct the applicability score calculation formula shown in the following formula:

[0040] This formula consists of two parts: The first part Reflects the matching degree of the storage duration, through the predicted storage duration And the average storage duration of the candidate storage area To measure; The second part Reflects the compliance degree of the environmental indicators, by calculating the required values of each environmental indicator in the storage environment requirements And the actual value of the candidate storage area To measure the deviation. Among them, Indicates the weight of the i-th environmental indicator, used to reflect the importance of different environmental indicators, Indicates the total number of environmental indicators, , Are both weight coefficients from 0 to 1 and satisfy , used to balance the proportion of the duration matching degree and the environmental compliance degree in the score, and are set by the expert group according to the requirements for the duration matching degree and the environmental compliance degree, such as = 0.65, = 0.35. Among them, the duration difference term And the environmental indicator deviation term The smaller the value, the higher the matching degree of the storage duration and the better the compliance degree of the environmental indicators. Therefore, the smaller the value of the applicability score, the more suitable the candidate storage area is for storing the goods to be stored.

[0041] Then, obtain the average storage duration and the actual environmental index values of each candidate storage area. Among them, the average storage duration is obtained by statistically analyzing historical storage data, and the actual environmental index values are obtained by collecting data through the environmental monitoring equipment in the storage area. Then, substitute the predicted storage duration and storage environment requirements of the goods to be stored, as well as the average storage duration and the actual environmental index values of each candidate storage area obtained, into the applicability scoring calculation formula to calculate the applicability scores of each candidate storage area. This scoring method comprehensively considers the duration matching degree and environmental adaptability, and can objectively reflect the applicability degree of each candidate storage area to the goods to be stored. Then, sort the candidate storage areas in ascending order according to the applicability scores. The candidate storage area with a smaller applicability score will be assigned a higher storage area priority. This scoring and sorting method comprehensively considers the duration matching degree and environmental adaptability, and can effectively identify the most suitable storage area for storing the goods to be stored.

[0042] As an alternative implementation, determining the optimal storage area for the goods to be stored according to the storage area priorities of multiple candidate storage areas and the real-time storage status model includes: S61: Traverse multiple candidate storage areas in sequence based on the storage area priorities; S62: Query the occupancy status of the currently traversed candidate storage area in the real-time storage status model; S63: If the currently traversed candidate storage area is in an idle state, determine the currently traversed candidate storage area as the optimal storage area.

[0043] Specifically, when determining the optimal storage area for the goods to be stored according to the storage area priorities and the real-time storage status model, first traverse multiple candidate storage areas based on the storage area priorities, and visit the candidate storage areas one by one in the order from high to low priority. For the currently traversed candidate storage area, query its occupancy status information in the real-time storage status model. The occupancy status information reflects whether the storage area is currently occupied by other goods. When it is detected that the currently traversed candidate storage area is in an idle state, it indicates that the area can be used to store goods, and the traversal is immediately stopped, and the candidate storage area is determined as the optimal storage area. This traversal method based on priorities ensures that the most suitable storage area is preferentially selected on the premise of meeting the storage conditions.

[0044] As an alternative implementation, using the real-time storage status model to plan the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage area includes: S71: Establish a passable path network based on the real-time storage status model; S72: In the traversable path network, the location coordinates of the storage entrance are used as the starting node, and the location coordinates of the optimal storage area are used as the target node; S73: Searching for the shortest path in the traversable path network according to the starting node and the target node to obtain the storage path.

[0045] Specifically, when planning the storage path of the goods to be stored, first, a passable path network is established based on the real-time storage status model. Specifically, by analyzing the occupancy of the cargo space in the real-time storage status model, the channels in the current warehouse that are not occupied and can be passed by the cargo transportation equipment are identified. For the occupied cargo space or channel, it is marked as an inaccessible area. By connecting all the passable channels, a complete passable path network is formed, which accurately reflects the actual traffic conditions inside the current warehouse. Then, the starting point and end point of the path planning are determined in the constructed passable path network. The three-dimensional position coordinates of the target warehouse entrance are set as the starting node, which represents the initial position of the goods entering the warehouse; the three-dimensional position coordinates of the determined optimal storage area are set as the target node, which represents the target position of the goods for final storage. The determination of these two nodes provides clear spatial constraints for subsequent path search. Afterwards, in the passable path network, a path search algorithm (such as Dijkstra algorithm or A* algorithm) is used to search for a passable path with the shortest distance with the starting node and the target node as constraints. During the search process, the width of the channel, turning radius and other constraints are taken into account to ensure that the planned path meets the movement requirements of the cargo transportation equipment. The shortest path searched is the storage path from the warehouse entrance to the optimal storage area for the goods to be stored. This path ensures the shortest transportation distance and the feasibility of the transportation process.

[0046] The second embodiment of the present application provides a warehouse goods management system based on the industrial Internet of Things, such as Figure 2As shown in the figure, the warehouse item management system 100 based on the industrial Internet of Things includes a management platform 101, a sensing network platform 102, and an object platform 103 that are communicatively connected in sequence. The object platform 103 includes sensors installed in storage locations, and is used to collect the occupancy status information of storage locations in the target warehouse in real time. The sensing network platform 102 is used to obtain the occupancy status information of storage locations and transmit the occupancy status information of storage locations to the management platform 101. The management platform 101 includes a model establishment module 11, a warehouse modeling module 12, a goods information module 13, a duration prediction module 14, a region screening module 15, a region optimization module 16, a path planning module 17, and a storage execution module 18. Among them, the model establishment module 11 is used to establish a three-dimensional model of the target warehouse; the warehouse modeling module 12 is used to collect the occupancy status information of storage locations in the target warehouse in real time through the sensors installed in storage locations, and update the three-dimensional model of the target warehouse based on the occupancy status information of storage locations to obtain a real-time storage status model; the goods information module 13 is used to obtain the basic information of the goods to be stored, where the basic information includes the volume information, weight information, and category information of the goods to be stored; the duration prediction module 14 is used to obtain the predicted storage duration of the goods to be stored according to the basic information; the region screening module 15 is used to determine multiple candidate storage regions based on the basic information, and determine the storage region priorities of the multiple candidate storage regions based on the basic information and the predicted storage duration; the region optimization module 16 is used to determine the optimal storage region of the goods to be stored according to the storage region priorities of the multiple candidate storage regions and the real-time storage status model; the path planning module 17 is used to use the real-time storage status model to plan the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage region; the storage execution module 18 is used to control the goods moving device to store the goods to be stored in the optimal storage region according to the storage path, and update the real-time storage status model after the goods to be stored are stored.

[0047] As an optional implementation manner, the duration prediction module 14 includes a prediction network construction unit, a storage feature acquisition unit, and a storage duration acquisition unit. Among them, the prediction network construction unit is used to construct a goods storage prediction network, and the goods storage prediction network includes a goods analysis sub-model and a duration prediction sub-model; the storage feature acquisition unit is used to obtain the storage features of the goods to be stored according to the basic information and the goods analysis sub-model; the storage duration acquisition unit is used to obtain the predicted storage duration of the goods to be stored according to the basic information, the storage features, and the duration prediction sub-model.

[0048] As an alternative implementation, the prediction network construction unit includes a data set acquisition subunit, a data set classification subunit, a hierarchy establishment subunit, a goods analysis sub-model establishment subunit, a duration prediction sub-model establishment subunit, and a model connection subunit. Among them, the data set acquisition subunit is used to acquire historical goods storage records, and generate a historical goods basic information set, a historical goods storage feature set, and a historical goods storage duration set based on the historical goods storage records. The historical goods storage records have multiple historical storage categories; the data set classification subunit is used to classify the historical goods basic information set and the historical goods storage feature set according to the multiple historical storage categories, and obtain multiple historical goods basic information subsets, multiple historical goods storage feature subsets, and multiple historical goods storage duration subsets; the hierarchy establishment subunit is used to establish a category information extraction layer according to the multiple historical storage categories, and establish multiple storage feature mapping layers according to the multiple historical goods basic information subsets and the multiple historical goods storage feature subsets; the goods analysis sub-model establishment subunit is used to connect the multiple storage feature mapping layers to the category information extraction layer in parallel to obtain the goods analysis sub-model; the duration prediction sub-model establishment subunit is used to establish multiple storage duration mapping layers according to the multiple historical goods basic information subsets, the multiple historical goods storage feature subsets, and the multiple historical goods storage duration subsets to form the duration prediction sub-model; the model connection subunit is used to connect the goods analysis sub-model and the duration prediction sub-model to obtain the goods storage prediction network.

[0049] As an alternative implementation, the area screening module 15 includes a candidate area determination unit, a storage environment requirement acquisition unit, an applicability scoring unit, and a priority determination unit. Among them, the candidate area determination unit is used to determine the applicable bin specifications according to the volume information and weight information in the basic information, and determine multiple candidate storage areas based on the applicable bin specifications and the three-dimensional model of the target warehouse; the storage environment requirement acquisition unit is used to acquire the storage environment requirements of the goods to be stored based on the category information in the basic information; the applicability scoring unit is used to calculate the applicability scores of the multiple candidate storage areas according to the predicted storage duration and the storage environment requirements; the priority determination unit is used to sort the multiple candidate storage areas based on the applicability scores of the multiple candidate storage areas to obtain the storage area priorities of the candidate storage areas.

[0050] As an alternative implementation, the applicability scoring unit includes a formula construction subunit, an area information acquisition subunit, and a score acquisition subunit. Among them, the formula construction subunit is used to construct an applicability scoring calculation formula as shown in the following formula:

[0051] Among them, Indicates the applicability score of the candidate storage area, Indicates the predicted storage duration, Indicates the average storage duration of the candidate storage area, Indicates the required value of the i-th environmental indicator in the storage environment requirements, Indicates the actual value of the i-th environmental indicator of the candidate storage area, Indicates the weight of the i-th environmental indicator, Indicates the total number of environmental indicators, 、 Is the weight coefficient, and 。

[0052] The area information acquisition subunit is used to acquire the average storage duration and the actual values of the environmental indicators of each of the candidate storage areas; the score acquisition subunit is used to obtain the applicability scores of each candidate storage area based on the predicted storage duration of the goods to be stored, the storage environment requirements, and the average storage duration and the actual values of the environmental indicators of each candidate storage area, in combination with the applicability score calculation formula.

[0053] As an optional implementation manner, the area preference module 16 includes a candidate storage area traversal unit, an occupancy status query unit, and an optimal storage area determination unit. Among them, the candidate storage area traversal unit is used to sequentially traverse multiple candidate storage areas based on the storage area priority; the occupancy status query unit is used to query the occupancy status of the currently traversed candidate storage area in the real-time storage status model; the optimal storage area determination unit is used to determine the currently traversed candidate storage area as the optimal storage area if the currently traversed candidate storage area is in an idle state.

[0054] As an optional implementation manner, the path planning module 17 includes a path network establishment unit, a start and end target determination unit, and a storage path acquisition unit. Among them, the path network establishment unit is used to establish a passable path network based on the real-time storage status model; the start and end target determination unit is used to use the position coordinates of the inbound port as the start node and the position coordinates of the optimal storage area as the target node in the passable path network; the storage path acquisition unit is used to search for the shortest path in the passable path network according to the start node and the target node to obtain the storage path.

[0055] The third embodiment of the present application provides an electronic device, as Figure 3 shown. The electronic device 200 includes a memory 210, a processor 220, and a computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the computer program 211, it implements a warehousing item management method based on the industrial Internet of Things.

[0056] The fourth embodiment of the present application provides a computer-readable storage medium. As Figure 4 shown, a computer program 211 is stored on the computer-readable storage medium 300. When the computer program 211 is executed by a processor, it implements a method for managing storage items based on the industrial Internet of Things.

[0057] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied to other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for managing storage items based on the industrial Internet of Things, characterized in that, Applied to a warehousing item management system, the warehousing item management system includes a management platform, a sensing network platform, and an object platform. The object platform includes sensors installed on storage locations. The method includes: Establish a three-dimensional model of the target warehouse; Real-time collect the occupancy status information of storage locations in the target warehouse through the sensors installed on the storage locations, and update the three-dimensional model of the target warehouse based on the occupancy status information of the storage locations to obtain a real-time storage status model; Obtain the basic information of the goods to be stored, where the basic information includes the volume information, weight information, and category information of the goods to be stored; According to the basic information, obtain the predicted storage duration of the goods to be stored; Based on the basic information, determine multiple candidate storage areas, and based on the basic information and the predicted storage duration, determine the storage area priorities of the multiple candidate storage areas; According to the storage area priorities of the multiple candidate storage areas and the real-time storage status model, determine the optimal storage area for the goods to be stored; Use the real-time storage status model to plan the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage area; According to the storage path, control the goods moving device to store the goods to be stored in the optimal storage area, and update the real-time storage status model after the goods to be stored are stored.

2. The method according to claim 1, wherein The step of obtaining the predicted storage duration of the goods to be stored according to the basic information includes: Construct a goods storage prediction network, which includes a goods analysis sub-model and a duration prediction sub-model; According to the basic information and the goods analysis sub-model, obtain the storage characteristics of the goods to be stored; According to the basic information, the storage characteristics, and the duration prediction sub-model, obtain the predicted storage duration of the goods to be stored.

3. The method according to claim 2, characterized in that, The step of constructing the goods storage prediction network includes: Obtain historical goods storage records, and generate a historical goods basic information set, a historical goods storage characteristics set, and a historical goods storage duration set based on the historical goods storage records. The historical goods storage records have multiple historical storage categories; Classify the historical goods basic information set and the historical goods storage characteristics set according to the multiple historical storage categories to obtain multiple historical goods basic information subsets, multiple historical goods storage characteristics subsets, and multiple historical goods storage duration subsets; Establish a category information extraction layer according to the multiple historical storage categories, and establish multiple storage characteristics mapping layers according to the multiple historical goods basic information subsets and the multiple historical goods storage characteristics subsets; Parallelly connect the multiple storage characteristics mapping layers to the category information extraction layer to obtain the goods analysis sub-model; Establish multiple storage duration mapping layers according to the multiple historical goods basic information subsets, the multiple historical goods storage characteristics subsets, and the multiple historical goods storage duration subsets to form the duration prediction sub-model; Connect the goods analysis sub-model and the duration prediction sub-model to obtain the goods storage prediction network.

4. The method according to claim 1, characterized in that Determining a plurality of candidate storage areas based on the basic information, and determining the storage area priorities of the plurality of candidate storage areas based on the basic information and the predicted storage duration, includes: Determining applicable bin specifications according to the volume information and weight information in the basic information, and determining a plurality of candidate storage areas based on the applicable bin specifications and the three-dimensional model of the target warehouse; Obtaining the storage environment requirements of the goods to be stored based on the category information in the basic information; Calculating the applicability scores of the plurality of candidate storage areas according to the predicted storage duration and the storage environment requirements; Sorting the plurality of candidate storage areas based on the applicability scores of the plurality of candidate storage areas to obtain the storage area priorities of the respective candidate storage areas.

5. The method according to claim 4, characterized in that, The calculating the applicability scores of the plurality of candidate storage areas according to the predicted storage duration and the storage environment requirements includes: Constructing an applicability score calculation formula as shown in the following formula: Among them, represents the applicability score of the candidate storage area, represents the predicted storage duration, represents the average storage duration of the candidate storage area, represents the required value of the i-th environmental indicator in the storage environment requirements, represents the actual value of the i-th environmental indicator of the candidate storage area, represents the weight of the i-th environmental indicator, represents the total number of environmental indicators, 、 is the weight coefficient, and ; Obtaining the average storage duration and the actual environmental index values of each of the candidate storage areas; Based on the predicted storage duration of the goods to be stored, the storage environment requirements, as well as the average storage duration and the actual environmental index values of each candidate storage area, and combining with the applicability score calculation formula, obtaining the applicability scores of each candidate storage area.

6. The method according to claim 1, characterized in that, The determining the optimal storage area for the goods to be stored according to the storage area priorities of the plurality of candidate storage areas and the real-time storage status model includes: Traversing the plurality of candidate storage areas in sequence based on the storage area priorities; Querying the occupancy status of the currently traversed candidate storage area in the real-time storage status model; If the currently traversed candidate storage area is in an idle state, determining the currently traversed candidate storage area as the optimal storage area.

7. The method according to claim 1, wherein The planning the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage area by using the real-time storage status model includes: Establishing a passable path network based on the real-time storage status model; In the passable path network, taking the position coordinates of the entrance as the starting node and the position coordinates of the optimal storage area as the target node; Searching for the shortest path in the passable path network according to the starting node and the target node to obtain the storage path.

8. A warehousing item management system based on the Industrial Internet of Things, characterized in that The warehousing item management system includes a management platform, a sensing network platform, and an object platform that are communicatively connected in sequence. The object platform includes bin-mounted sensors. The object platform is used to collect the bin occupancy status information in the target warehouse in real time. The sensing network platform is used to obtain the bin occupancy status information and transmit the bin occupancy status information to the management platform. The management platform includes: A model establishment module for establishing a three-dimensional model of the target warehouse; A warehousing modeling module for collecting the bin occupancy status information in the target warehouse in real time through the bin-mounted sensors, and updating the three-dimensional model of the target warehouse based on the bin occupancy status information to obtain a real-time storage status model; A goods information module, configured to obtain the basic information of the goods to be stored, where the basic information includes the volume information, weight information, and category information of the goods to be stored; A duration prediction module, configured to obtain the predicted storage duration of the goods to be stored according to the basic information; A region screening module, configured to determine a plurality of candidate storage regions based on the basic information, and determine the storage region priorities of the plurality of candidate storage regions based on the basic information and the predicted storage duration; A region optimization module, configured to determine the optimal storage region of the goods to be stored according to the storage region priorities of the plurality of candidate storage regions and the real-time storage status model; A path planning module, configured to use the real-time storage status model to plan the storage path of the goods to be stored from the entrance of the target warehouse to the optimal storage region; A storage execution module, configured to control a goods moving device to store the goods to be stored in the optimal storage region according to the storage path, and update the real-time storage status model after the storage of the goods to be stored is completed.

9. An electronic device, characterized in that, Comprising: A memory, configured to store a computer software program; A processor, configured to read and execute the computer software program, so as to implement the method according to any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that, A computer software program is stored in the storage medium, and when the computer software program is executed by a processor, the method according to any one of claims 1-7 is implemented.

Images