Unmanned warehouse management system based on artificial intelligence

Abstract

The invention discloses an artificial intelligence-based unmanned warehouse management system, which comprises a data collection module, a warehouse management module and a cargo delivery module, and is characterized in that the data collection module is used for reading cargo comprehensive information in cargo labels, collecting cargo weights and cargo visual images in real time, and inputting historical delivery data into the system; the warehouse management module is used for analyzing the attribute information of the goods, obtaining the goods warehousing priority, matching the positions of the goods on the goods shelves according to the goods warehousing priority, analyzing the size of the goods, the distance between the goods shelves and the distance between the layers of the goods shelves, and adjusting the position of the intelligent carrying equipment according to the analysis result. And the goods delivery module is used for analyzing whether the goods exist above the position of the target goods and dispatching a plurality of intelligent carrying devices to carry out auxiliary delivery according to the analysis result, and the goods delivery system has the advantages of improving accuracy and practicability.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse management, and in particular to an unmanned warehouse management system based on artificial intelligence. Background Art

[0002] A vertical warehouse, also known as a high-bay warehouse or elevated warehouse, generally refers to a warehouse that uses shelves of several layers, dozens of layers or even dozens of layers to store unit goods, and uses corresponding handling equipment to carry out pallet warehousing and outbound operations.

[0003] As the scale of enterprises continues to expand, the types and quantities of goods managed in warehouses are increasing, and the pressure of warehouse management is also increasing. Traditional warehouse management generally relies on manual entry and exit of goods and inventory of goods. Some enterprises also adopt automated warehouse management technology and use intelligent identification technologies such as RFID to realize automated entry and exit of warehouses. However, due to the different properties of incoming goods, including the size, shape, fragile nature, entry and exit frequency and other factors, the existing technology cannot accurately place the goods in a reasonable position, which is easy to cause damage to the goods. When picking up goods from the warehouse, it is necessary to identify the goods on the shelves one by one, which wastes a lot of time and leads to low efficiency of outbound delivery. Moreover, the existing technology adopts fixed program settings and cannot accurately analyze factors such as the size and shape of the goods, and regulate the intelligent handling equipment, which is easy to cause the goods to collide with the shelves during the handling process or placement process, resulting in damage to the goods, and even the dumping of goods on the shelves, which is poor in safety. Therefore, it is very necessary to design an unmanned warehouse management system based on artificial intelligence to improve accuracy and practicality. Summary of the invention

[0004] The purpose of the present invention is to provide an unmanned warehouse management system based on artificial intelligence to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an unmanned warehouse management system based on artificial intelligence, comprising a data collection module, a warehouse management module and a goods outbound module, wherein the data collection module is used to read the comprehensive information of goods in the goods label, collect the weight of the goods and the visual image of the goods in real time, and enter the historical outbound data into the system, the warehouse management module is used to analyze the attribute information of the goods, obtain the goods entry priority, match the position of the goods on the shelf according to the goods entry priority, analyze the volume of the goods, the distance between the shelves and the spacing between the shelves, adjust the position of the intelligent handling equipment according to the analysis results, and record the storage position of the goods, the goods outbound module is used to analyze whether there is goods above the position of the target goods, and dispatch a number of intelligent handling equipment to assist in outbound according to the analysis results, and the data collection module, the warehouse management module and the goods outbound module are interconnected in a network;

[0006] The warehouse management module includes a storage management module and a handling equipment management module, and the storage management module and the handling equipment management module are communicatively connected with each other;

[0007] The warehousing management module further includes a cargo attribute analysis submodule, a cargo priority evaluation submodule and a cargo position matching submodule, wherein the cargo attribute analysis submodule is used to read and analyze the attribute information of the cargo, wherein the attribute information includes weight and fragility, the cargo priority evaluation submodule is used to evaluate the warehousing priority of the cargo according to the analysis result of the attribute information of the cargo, and the cargo position matching submodule is used to match the corresponding stacking position for the cargo according to the priority of the cargo;

[0008] The handling equipment management module further includes an AI visual analysis submodule, a cargo position recording submodule and an equipment adjustment submodule. The AI ​​visual analysis submodule is used to analyze the movement trajectory of cargo during the handling process of the intelligent handling equipment, and determine whether the cargo will collide with the shelf or with nearby intelligent handling equipment. The equipment adjustment submodule is used to adjust the position of the handling equipment according to the analysis results. The cargo position recording module is used to record the effective operation data of the intelligent handling equipment, including the driving route and the telescopic length of the telescopic arm, and enter the effective operation data of the intelligent handling equipment into the cargo label.

[0009] According to the above technical solution, the data acquisition module includes a data reading module, a sensor module and a historical outbound data entry module. The data reading module is used to read the comprehensive information of the goods in the goods label, the sensor module is used to collect the weight and visual image of the goods in real time, and the historical outbound data of the warehouse is used to enter the historical outbound data of the warehouse into the system.

[0010] According to the above technical solution, the warehouse management module includes an warehousing management module, which is used to read and analyze the attribute information of the goods, further analyze the warehousing priority of the goods according to the analysis results, and match the stacking position for the goods according to the warehousing priority of the goods.

[0011] According to the above technical solution, the warehouse management module also includes a handling equipment management module, which is used to analyze the movement trajectory of goods during the handling process of the intelligent handling equipment, determine whether the goods will collide with the shelf, whether they will collide with nearby intelligent handling equipment, adjust the position of the intelligent handling equipment according to the analysis results, and record the stacking position of the goods.

[0012] According to the above technical solution, the cargo outbound module includes a cargo position analysis module and a cargo adjustment module. The cargo position analysis module is used to analyze whether the cargo in the vertical direction of the target cargo is outbound, and dispatch several intelligent handling equipment to assist in outbound delivery based on the analysis results.

[0013] According to the above technical solution, the operation method of the unmanned warehouse management system mainly includes the following steps:

[0014] Step S1: Establish a database, read the comprehensive information of the goods in the goods label through the data reading module, collect the weight and visual image of the goods in real time through the sensor module, enter the historical outbound data of the warehouse into the system through the historical inbound and outbound module, and store all the data in the database;

[0015] Step S2: When the goods are put into storage, the system starts the storage management module, starts to analyze the attribute information of the goods, analyzes and evaluates the storage priority of the goods, and matches the corresponding stacking position for the goods according to the analysis results;

[0016] Step S3: When the intelligent handling equipment is handling the goods, the system starts the handling equipment management module, starts to analyze the movement trajectory of the goods, analyzes whether the goods collide during transportation, adjusts the position of the intelligent handling equipment according to the analysis results, and records the position of the goods when the goods are stacked;

[0017] Step S4: When leaving the warehouse, the system starts to analyze whether the goods in the vertical direction have been left the warehouse, determines the location of the goods based on the analysis results, and dispatches several intelligent handling equipment to assist in leaving the warehouse.

[0018] According to the above technical solution, step S2 further includes the following steps:

[0019] Step S21: Obtain the target cargo attribute information read by the system, identify the material and vulnerability level of the target cargo, retrieve the corresponding basic vulnerability score Y1 in the database according to the material of the target cargo, retrieve the corresponding vulnerability influence coefficient α in the database according to the vulnerability level of the target cargo, calculate the cargo vulnerability score Y2=α·Y1 by the formula, where Y2 represents the cargo vulnerability score, retrieve the corresponding cargo limit load M and the influence coefficient η on the cargo in-and-out priority score in the database according to the cargo vulnerability score;

[0020] Step S22: Obtain the historical outbound data of the warehouse, identify the types of goods outbound and the corresponding outbound times m, and calculate the proportion of the outbound times of the target goods in the total outbound times by formula In the formula, Q represents the proportion of the target goods’ outbound times in the total outbound times, ε represents the deviation coefficient of the proportion, W represents the total number of historical outbound goods in the warehouse, and according to the proportion of the target goods’ outbound times in the total outbound times, the corresponding goods priority influence coefficient β in the database is retrieved;

[0021] Step S23: Obtain the proportion of the number of times the target goods are shipped out of the total number of shipments, retrieve the corresponding basic score P1 of the goods entry priority in the database according to the proportion, calculate the comprehensive score of the goods entry priority by the formula P2=β·η·P1, where P2 represents the comprehensive score of the goods entry priority, sort the comprehensive scores of the goods entry priority in ascending order, and enter the goods into the warehouse according to the order of the ascending order.

[0022] According to the above technical solution, step S23 further includes the following steps:

[0023] Step S231: Obtain the visual image of the goods and the priority comprehensive score sorting sequence of the goods, identify the volume size of the goods, select the goods from the first to the nth order in the sorting sequence, identify the total length of the selected goods, calculate the difference S between the total length of the goods and the length of the shelf goods stacking layer, when the difference S is greater than the maximum threshold, reduce the number of selected goods, when the difference S is greater than the minimum threshold and less than the maximum threshold, the system continues to detect, when the difference S is less than the minimum threshold, identify the length of the goods at the n+1th order, calculate the difference F between the difference S and the length of the goods at the n+1th order, if the difference F is still less than the minimum threshold, continue to select the next order of goods, if the difference F is greater than the minimum threshold and less than the maximum threshold, the system will no longer increase the number of goods after selecting the goods at the n+1th order, otherwise the system deletes the goods at the n+1th order;

[0024] Step S232: When the goods stacking position matching is completed, the total weight of the goods vertically above the target goods is identified, and the difference G between the total weight of the goods and the maximum load-bearing capacity M of the goods is calculated. When the difference G is less than the threshold, the distance L1 between the top layer of goods vertically above the target goods and the top of the shelf stacking layer is identified, and goods with a weight less than the difference G and a height less than the distance L1 are retrieved for replenishment. When the difference G is greater than the threshold, the top layer of goods is removed, the difference G after removing the top layer of goods and the distance L1 between the top layer of goods and the top of the shelf stacking layer are identified, and goods with a weight less than the difference G and a height less than the distance L1 are retrieved for replenishment.

[0025] According to the above technical solution, step S3 further includes the following steps:

[0026] Step S31: obtaining a visual image of the cargo movement process, identifying cargo corner nodes, establishing a three-dimensional coordinate system, identifying the coordinates of cargo corner nodes, connecting cargo corner nodes, constructing a cargo model, identifying shelf edge nodes, connecting a vertical line to the horizontal plane through the shelf edge, constructing a vertical plane between the shelf edge and the horizontal plane, identifying the intersection of the cargo model and the vertical plane, and when an intersection exists, rotating the cargo clockwise around the center point, the rotation angle is θ, identifying the intersection of the rotated cargo model and the vertical plane, and if an intersection exists, continuing to rotate, otherwise stopping the rotation, and controlling the intelligent handling device to carry out the handling, and when no intersection exists, controlling the intelligent handling device to carry out the handling;

[0027] Step S32: Obtain the telescopic length and driving route and route length of the telescopic arm of the loading platform of the intelligent handling equipment, store the telescopic length and driving route and route length of the telescopic arm of the loading platform of the intelligent handling equipment in the database, and bind them with the cargo label.

[0028] According to the above technical solution, in step S4, the information of the goods to be shipped is obtained, the label of the goods to be shipped is identified, and the database is compared according to the driving route and route length of the intelligent handling equipment and the telescopic length L2 of the telescopic arm of the loading platform in the database of the goods to be shipped. If the driving route and route length of the intelligent handling equipment in the goods label in the database are the same as those of the goods to be shipped, the telescopic length L3 of the loading platform of the intelligent handling equipment in the goods label is identified, and the stacking layer where the goods to be shipped are located is retrieved according to L2, the height H of the stacking layer is identified, and L3 is compared with H. When L3 is greater than H, the goods are marked as having no impact. Goods, when L3 is less than H, then compare L2 with L3, if L3 is less than L2, then mark the goods as non-impact goods, otherwise mark the goods as impact goods, identify the number of goods with impact goods mark, and assign the goods with impact goods mark to the intelligent handling equipment in sequence according to the number of intelligent handling equipment corresponding to the number of goods, sort the telescopic lengths of the telescopic arms of the loading platforms of the intelligent handling equipment in descending order, arrange the intelligent handling equipment according to the sorting sequence, and obtain the goods according to the driving route and route length of the intelligent handling equipment in the goods label to be shipped and the telescopic length of the telescopic arm of the loading platform.

[0029] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention can accurately determine the stacking position of the goods by analyzing the proportion of the number of times the goods leave the warehouse and the degree of vulnerability of the goods, thereby avoiding deviations in the stacking position of the goods, which may cause the goods to be crushed and cause losses, thereby greatly improving the accuracy of the system, ensuring the safety of the goods and reducing losses; by analyzing the length of the goods and the length of the shelf stacking layer, it can accurately select a sufficient number of sequential goods, thereby avoiding vacancies in the shelf stacking layer and causing waste of shelf space, thereby greatly improving the accuracy of the system in matching the stacking position for the goods and the utilization rate of the shelves; by analyzing the stacking position of the goods after matching, the load-bearing capacity of the target goods and the distance between the top layer of the goods and the top of the shelf stacking layer are further analyzed, thereby the stacking position of the goods is determined. Adjustment can avoid the target goods from bearing too much weight, which may cause damage to the goods. It can also avoid large gaps in the stacking layer, greatly improving the accuracy of the goods stacking position matching and the utilization rate of the shelf. By analyzing whether there is an intersection between the cargo model and the vertical plane of the shelf edge node and the horizontal plane, it can accurately determine whether the goods will collide with the shelf during transportation, avoid damage to the goods, and thus reduce the loss caused by damage to the goods and reduce costs. By analyzing whether there are other goods above the goods to be shipped and dispatching a number of intelligent handling equipment for auxiliary transportation, the goods to be shipped out can be quickly transported, thereby greatly improving the efficiency of goods shipping out. At the same time, picking up goods according to the operating data recorded by the intelligent handling equipment when stacking the goods can reduce the time for identifying the goods and further improve the efficiency of goods shipping out. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0031] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] See also Figure 1The present invention provides a technical solution: an unmanned warehouse management system based on artificial intelligence, including a data collection module, a storage management module and a goods outbound module. The data collection module is used to read the comprehensive information of goods in the goods label, collect the weight of the goods and the visual image of the goods in real time, and enter the historical outbound data into the system. The storage management module is used to analyze the attribute information of the goods, obtain the goods entry priority, match the position of the goods on the shelf according to the goods entry priority, analyze the volume of the goods, the distance between the shelves and the spacing between the shelves, adjust the position of the intelligent handling equipment according to the analysis results, and record the storage position of the goods. The goods outbound module is used to analyze whether there is goods above the position of the target goods, and dispatch a number of intelligent handling equipment to assist in outbound according to the analysis results. The data collection module, the storage management module and the goods outbound module are interconnected in a network;

[0034] The warehouse management module includes a storage management module and a handling equipment management module, and the storage management module and the handling equipment management module are connected to each other in communication;

[0035] The warehousing management module further includes a cargo attribute analysis submodule, a cargo priority evaluation submodule and a cargo position matching submodule. The cargo attribute analysis submodule is used to read and analyze the attribute information of the cargo, and the attribute information includes weight and fragility. The cargo priority evaluation submodule is used to evaluate the warehousing priority of the cargo according to the analysis result of the attribute information of the cargo. The cargo position matching submodule is used to match the corresponding stacking position for the cargo according to the priority of the cargo.

[0036] The handling equipment management module further includes an AI visual analysis submodule, a cargo position recording submodule and an equipment adjustment submodule. The AI ​​visual analysis submodule is used to analyze the movement trajectory of cargo during the handling process of the intelligent handling equipment, and to determine whether the cargo will collide with the shelf or with nearby intelligent handling equipment. The equipment adjustment submodule is used to adjust the position of the handling equipment according to the analysis results. The cargo position recording module is used to record the effective operation data of the intelligent handling equipment, including the driving route and the telescopic length of the telescopic arm, and enter the effective operation data of the intelligent handling equipment into the cargo label.

[0037] The data acquisition module includes a data reading module, a sensor module and a historical outbound data entry module. The data reading module is used to read the comprehensive information of the goods in the goods label, the sensor module is used to collect the weight and visual images of the goods in real time, and the historical outbound and inbound module is used to enter the historical outbound data of the warehouse into the system.

[0038] The warehouse management module includes an incoming storage management module, which is used to read and analyze the attribute information of the goods, further analyze the incoming storage priority of the goods based on the analysis results, and match the stacking position for the goods based on the incoming storage priority of the goods.

[0039] The warehouse management module also includes a handling equipment management module, which is used to analyze the movement trajectory of goods during the handling process of the intelligent handling equipment, determine whether the goods will collide with the shelves, whether they will collide with nearby intelligent handling equipment, adjust the position of the intelligent handling equipment according to the analysis results, and record the stacking position of the goods.

[0040] The cargo outbound module includes a cargo location analysis module and a cargo adjustment module. The cargo location analysis module is used to analyze whether the cargo in the vertical direction of the target cargo is outbound, and dispatch several intelligent handling equipment to assist in outbound delivery based on the analysis results.

[0041] The operation method of the unmanned warehouse management system mainly includes the following steps:

[0042] Step S1: Establish a database, read the comprehensive information of the goods in the goods label through the data reading module, collect the weight and visual image of the goods in real time through the sensor module, enter the historical outbound data of the warehouse into the system through the historical inbound and outbound module, and store all the data in the database;

[0043] Step S2: When the goods are put into storage, the system starts the storage management module, starts to analyze the attribute information of the goods, analyzes and evaluates the storage priority of the goods, and matches the corresponding stacking position for the goods according to the analysis results;

[0044] Step S3: When the intelligent handling equipment is handling the goods, the system starts the handling equipment management module, starts to analyze the movement trajectory of the goods, analyzes whether the goods collide during transportation, adjusts the position of the intelligent handling equipment according to the analysis results, and records the position of the goods when the goods are stacked;

[0045] Step S4: When leaving the warehouse, the system starts to analyze whether the goods in the vertical direction have been left the warehouse, determines the location of the goods based on the analysis results, and dispatches several intelligent handling equipment to assist in leaving the warehouse.

[0046] Step S2 further comprises the following steps:

[0047] Step S21: Obtain the target cargo attribute information read by the system, identify the material and vulnerability level of the target cargo, retrieve the corresponding basic vulnerability score Y1 in the database according to the material of the target cargo, retrieve the corresponding vulnerability influence coefficient α in the database according to the vulnerability level of the target cargo, calculate the cargo vulnerability score Y2=α·Y1 by the formula, where Y2 represents the cargo vulnerability score, retrieve the corresponding cargo limit load M and the influence coefficient η on the cargo in-and-out priority score in the database according to the cargo vulnerability score;

[0048] Step S22: Obtain the historical outbound data of the warehouse, identify the types of goods outbound and the corresponding outbound times m, and calculate the proportion of the outbound times of the target goods in the total outbound times by formula In the formula, Q represents the proportion of the target goods’ outbound times in the total outbound times, ε represents the deviation coefficient of the proportion, W represents the total number of historical outbound goods in the warehouse, and according to the proportion of the target goods’ outbound times in the total outbound times, the corresponding goods priority influence coefficient β in the database is retrieved;

[0049] Step S23: Obtain the proportion of the number of outbound times of the target goods in the total number of outbound times, retrieve the corresponding basic score P1 of the goods warehousing priority in the database according to the proportion, calculate the comprehensive score P2 of the goods warehousing priority by the formula P2=β·η·P1, where P2 represents the comprehensive score of the goods warehousing priority, sort the comprehensive scores of the goods warehousing priority in ascending order, and put the goods into storage according to the order of the ascending order. By analyzing the proportion of the outbound times of the goods and the fragility of the goods, the stacking position of the goods can be accurately determined to avoid deviations in the stacking position of the goods, which may cause the goods to be crushed and cause losses, thereby greatly improving the accuracy of the system, ensuring the safety of the goods and reducing losses.

[0050] Step S23 further includes the following steps:

[0051] Step S231: Obtain the visual image of the goods and the priority comprehensive score sorting sequence of the goods, identify the volume of the goods, select the goods from the first to the nth order in the sorting sequence, identify the total length of the selected goods, calculate the difference S between the total length of the goods and the length of the stacking layer of the goods on the shelf, and when the difference S is greater than the maximum threshold, reduce the number of selected goods. When the difference S is greater than the minimum threshold and less than the maximum threshold, the system continues to detect. When the difference S is less than the minimum threshold, identify the length of the goods at the n+1th order, calculate the difference S and the length of the n+1th order. The difference F of the length of the goods in the order. If the difference F is still less than the minimum threshold, the next order of goods will be selected. If the difference F is greater than the minimum threshold and less than the maximum threshold, the system will no longer increase the number of goods after selecting the goods in the order of n+1. Otherwise, the system will delete the goods in the order of n+1. By analyzing the length of the goods and the length of the shelf stacking layer, a sufficient number of goods in the order sequence can be accurately selected to avoid vacancies in the shelf stacking layer, resulting in waste of shelf space, thereby greatly improving the accuracy of the system in matching the stacking position for the goods and the utilization rate of the shelves;

[0052] Step S232: When the goods stacking position matching is completed, the total weight of the goods vertically above the target goods is identified, and the difference G between the total weight of the goods and the maximum load-bearing capacity M of the goods is calculated. When the difference G is less than the threshold, the distance L1 between the top layer of goods vertically above the target goods and the upper top of the shelf stacking layer is identified, and goods with a weight less than the difference G and a height less than the distance L1 are retrieved for replenishment. When the difference G is greater than the threshold, the top layer of goods is removed, and the difference G after removing the top layer of goods and the distance L1 between the top layer of goods and the upper top of the shelf stacking layer are identified, and goods with a weight less than the difference G and a height less than the distance L1 are retrieved for replenishment. By analyzing the stacking position of the goods after matching, the load-bearing capacity of the target goods and the distance between the top layer of goods and the upper top of the shelf stacking layer are further analyzed, and then the stacking position of the goods is adjusted, which can avoid excessive load-bearing of the target goods, resulting in damage to the goods, and can also avoid large gaps in the stacking layer, greatly improving the accuracy of the goods stacking position matching and the utilization rate of the shelf.

[0053] Step S3 further comprises the following steps:

[0054] Step S31: obtaining a visual image of the cargo movement process, identifying cargo corner nodes, establishing a three-dimensional coordinate system, identifying the coordinates of cargo corner nodes, connecting cargo corner nodes, constructing a cargo model, identifying shelf edge nodes, connecting a vertical line to the horizontal plane through the shelf edge, constructing a vertical plane between the shelf edge and the horizontal plane, identifying the intersection of the cargo model and the vertical plane, and when an intersection exists, rotating the cargo clockwise around the center point, with a rotation angle of θ, identifying the intersection of the rotated cargo model and the vertical plane, and if an intersection exists, continuing to rotate, otherwise stopping the rotation, and controlling the intelligent handling equipment to carry out the handling, and when no intersection exists, controlling the intelligent handling equipment to carry out the handling, by analyzing whether there is an intersection between the cargo model and the shelf edge node and the vertical plane of the horizontal plane, it is possible to accurately determine whether the cargo will collide with the shelf during the handling process, thereby avoiding damage to the cargo, and thus reducing the loss caused by damage to the cargo and reducing costs;

[0055] Step S32: Obtain the telescopic length and driving route and route length of the telescopic arm of the loading platform of the intelligent handling equipment, store the telescopic length and driving route and route length of the telescopic arm of the loading platform of the intelligent handling equipment in the database, and bind them with the cargo label.

[0056] In step S4, the information of the goods to be shipped is obtained, the label of the goods to be shipped is identified, and the database is compared according to the driving route and route length of the intelligent handling equipment and the telescopic length L2 of the telescopic arm of the loading platform in the database of the goods to be shipped. If the driving route and route length of the intelligent handling equipment in the goods label in the database are the same as those of the goods to be shipped, the telescopic length L3 of the loading platform of the intelligent handling equipment in the goods label is identified, and the stacking layer where the goods to be shipped are located is retrieved according to L2, and the height H of the stacking layer is identified, and L3 is compared with H. When L3 is greater than H, it means that the goods and the goods to be shipped are not in the same stacking layer, and the goods are marked as unaffected goods. When L3 is less than H, L2 and L3 are compared. If L3 is less than L2, it means that the goods are below the goods to be shipped, and the goods are marked as unaffected goods. Otherwise, it means that the goods are above the goods to be shipped. , affecting the outbound delivery of goods, marking the goods as affected goods, identifying the number of goods with the affected goods mark, and allocating the goods with the affected goods mark to the intelligent handling equipment in sequence according to the number of intelligent handling equipment corresponding to the number of goods, sorting the telescopic lengths of the telescopic arms of the loading platforms of the intelligent handling equipment in descending order, arranging the intelligent handling equipment according to the sorting sequence, and obtaining the goods according to the driving routes and route lengths of the intelligent handling equipment in the labels of the goods to be delivered and the telescopic lengths of the telescopic arms of the loading platforms, analyzing whether there are other goods above the goods to be delivered, and dispatching a number of intelligent handling equipment for auxiliary handling, the goods to be delivered can be quickly delivered, thereby greatly improving the outbound delivery efficiency of the goods, and picking up the goods according to the operating data recorded by the intelligent handling equipment when stacking the goods, which can reduce the time for identifying the goods and further improve the outbound delivery efficiency of the goods.

[0057] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0058] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An unmanned warehouse management system based on artificial intelligence, including a data collection module, a warehouse management module and a goods outbound module, characterized in that: The data acquisition module is used to read the comprehensive information of the goods in the goods label, collect the weight of the goods and the visual image of the goods in real time, and enter the historical outbound data into the system. The warehouse management module is used to analyze the attribute information of the goods, obtain the priority of the goods entering the warehouse, match the position of the goods on the shelf according to the priority of the goods entering the warehouse, analyze the volume of the goods, the distance between the shelves and the spacing between the layers of the shelves, adjust the position of the intelligent handling equipment according to the analysis results, and record the storage position of the goods. The goods outbound module is used to analyze whether there is goods above the position of the target goods, and dispatch a number of intelligent handling equipment to assist in outbound according to the analysis results. The data acquisition module, the warehouse management module and the goods outbound module are interconnected in a network; The warehouse management module includes a storage management module and a handling equipment management module, and the storage management module and the handling equipment management module are communicatively connected with each other; The warehousing management module further includes a cargo attribute analysis submodule, a cargo priority evaluation submodule and a cargo position matching submodule, wherein the cargo attribute analysis submodule is used to read and analyze the attribute information of the cargo, wherein the attribute information includes weight and fragility, the cargo priority evaluation submodule is used to evaluate the warehousing priority of the cargo according to the analysis result of the attribute information of the cargo, and the cargo position matching submodule is used to match the corresponding stacking position for the cargo according to the priority of the cargo; The handling equipment management module further includes an AI visual analysis submodule, a cargo position recording submodule and an equipment adjustment submodule. The AI ​​visual analysis submodule is used to analyze the movement trajectory of cargo during the handling process of the intelligent handling equipment, and determine whether the cargo will collide with the shelf or with nearby intelligent handling equipment. The equipment adjustment submodule is used to adjust the position of the handling equipment according to the analysis results. The cargo position recording module is used to record the effective operation data of the intelligent handling equipment, including the driving route and the telescopic length of the telescopic arm, and enter the effective operation data of the intelligent handling equipment into the cargo label.

2. The unmanned warehouse management system based on artificial intelligence according to claim 1, characterized in that: The data acquisition module includes a data reading module, a sensor module and a historical outbound data entry module. The data reading module is used to read the comprehensive information of the goods in the goods label, the sensor module is used to collect the weight and visual image of the goods in real time, and the historical outbound and inbound module is used to enter the historical outbound data of the warehouse into the system.

3. The unmanned warehouse management system based on artificial intelligence according to claim 2 is characterized in that: The warehouse management module includes a storage management module, which is used to read and analyze the attribute information of the goods, further analyze the storage priority of the goods according to the analysis result, and match the stacking position for the goods according to the storage priority of the goods.

4. The unmanned warehouse management system based on artificial intelligence according to claim 3 is characterized in that: The warehouse management module also includes a handling equipment management module, which is used to analyze the movement trajectory of goods during the handling process of the intelligent handling equipment, determine whether the goods will collide with the shelf, whether they will collide with nearby intelligent handling equipment, adjust the position of the intelligent handling equipment according to the analysis results, and record the stacking position of the goods.

5. The unmanned warehouse management system based on artificial intelligence according to claim 4 is characterized in that: The cargo outbound module includes a cargo position analysis module and a cargo adjustment module. The cargo position analysis module is used to analyze whether the cargo in the vertical direction of the target cargo is outbound, and dispatch a number of intelligent handling equipment to assist in outbound delivery according to the analysis results.

6. The unmanned warehouse management system based on artificial intelligence according to claim 5 is characterized in that: The operation method of the unmanned warehouse management system mainly includes the following steps: Step S1: Establish a database, read the comprehensive information of the goods in the goods label through the data reading module, collect the weight and visual image of the goods in real time through the sensor module, enter the historical outbound data of the warehouse into the system through the historical inbound and outbound module, and store all the data in the database; Step S2: When the goods are put into storage, the system starts the storage management module, starts to analyze the attribute information of the goods, analyzes and evaluates the storage priority of the goods, and matches the corresponding stacking position for the goods according to the analysis results; Step S3: When the intelligent handling equipment is handling the goods, the system starts the handling equipment management module, starts to analyze the movement trajectory of the goods, analyzes whether the goods collide during transportation, adjusts the position of the intelligent handling equipment according to the analysis results, and records the position of the goods when the goods are stacked; Step S4: When leaving the warehouse, the system starts to analyze whether the goods in the vertical direction have been left the warehouse, determines the location of the goods based on the analysis results, and dispatches several intelligent handling equipment to assist in leaving the warehouse.

7. The unmanned warehouse management system based on artificial intelligence according to claim 6 is characterized in that: The step S2 further comprises the following steps: Step S21: Obtain the target cargo attribute information read by the system, identify the material and vulnerability level of the target cargo, retrieve the corresponding basic vulnerability score Y1 in the database according to the material of the target cargo, retrieve the corresponding vulnerability influence coefficient α in the database according to the vulnerability level of the target cargo, calculate the cargo vulnerability score Y2=α·Y1 by the formula, where Y2 represents the cargo vulnerability score, retrieve the corresponding cargo limit load M and the influence coefficient η on the cargo in-and-out priority score in the database according to the cargo vulnerability score; Step S22: Obtain the historical outbound data of the warehouse, identify the types of goods outbound and the corresponding outbound times m, and calculate the proportion of the outbound times of the target goods in the total outbound times by formula In the formula, Q represents the proportion of the target goods’ outbound times in the total outbound times, ε represents the deviation coefficient of the proportion, W represents the total number of historical outbound goods in the warehouse, and the corresponding goods priority influence coefficient β in the database is retrieved according to the proportion of the target goods’ outbound times in the total outbound times; Step S23: Obtain the proportion of the number of times the target goods are shipped out of the total number of shipments, retrieve the corresponding basic score P1 of the goods entry priority in the database according to the proportion, calculate the comprehensive score of the goods entry priority by the formula P2=β·η·P1, where P2 represents the comprehensive score of the goods entry priority, sort the comprehensive scores of the goods entry priority in ascending order, and enter the goods into the warehouse according to the order of the ascending order.

8. The artificial intelligence-based unmanned warehouse management system according to claim 7, characterized in that: The step S23 further comprises the following steps: Step S231: Obtain the visual image of the goods and the priority comprehensive score sorting sequence of the goods, identify the volume size of the goods, select the goods from the first to the nth order in the sorting sequence, identify the total length of the selected goods, calculate the difference S between the total length of the goods and the length of the shelf goods stacking layer, when the difference S is greater than the maximum threshold, reduce the number of selected goods, when the difference S is greater than the minimum threshold and less than the maximum threshold, the system continues to detect, when the difference S is less than the minimum threshold, identify the length of the goods at the n+1th order, calculate the difference F between the difference S and the length of the goods at the n+1th order, if the difference F is still less than the minimum threshold, continue to select the next order of goods, if the difference F is greater than the minimum threshold and less than the maximum threshold, the system will no longer increase the number of goods after selecting the goods at the n+1th order, otherwise the system deletes the goods at the n+1th order; Step S232: When the goods stacking position matching is completed, the total weight of the goods vertically above the target goods is identified, and the difference G between the total weight of the goods and the maximum load-bearing capacity M of the goods is calculated. When the difference G is less than the threshold, the distance L1 between the top layer of goods vertically above the target goods and the top of the shelf stacking layer is identified, and goods with a weight less than the difference G and a height less than the distance L1 are retrieved for replenishment. When the difference G is greater than the threshold, the top layer of goods is removed, the difference G after removing the top layer of goods and the distance L1 between the top layer of goods and the top of the shelf stacking layer are identified, and goods with a weight less than the difference G and a height less than the distance L1 are retrieved for replenishment.

9. The artificial intelligence-based unmanned warehouse management system according to claim 8, characterized in that: The step S3 further comprises the following steps: Step S31: obtaining a visual image of the cargo movement process, identifying cargo corner nodes, establishing a three-dimensional coordinate system, identifying the coordinates of cargo corner nodes, connecting cargo corner nodes, constructing a cargo model, identifying shelf edge nodes, connecting a vertical line to the horizontal plane through the shelf edge, constructing a vertical plane between the shelf edge and the horizontal plane, identifying the intersection of the cargo model and the vertical plane, and when an intersection exists, rotating the cargo clockwise around the center point, the rotation angle is θ, identifying the intersection of the rotated cargo model and the vertical plane, and if an intersection exists, continuing to rotate, otherwise stopping the rotation, and controlling the intelligent handling device to carry out the handling, and when no intersection exists, controlling the intelligent handling device to carry out the handling; Step S32: Obtain the telescopic length and driving route and route length of the telescopic arm of the loading platform of the intelligent handling equipment, store the telescopic length and driving route and route length of the telescopic arm of the loading platform of the intelligent handling equipment in the database, and bind them with the cargo label.

10. The unmanned warehouse management system based on artificial intelligence according to claim 9, characterized in that: In the step S4, the information of the goods to be shipped is obtained, the label of the goods to be shipped is identified, and the database is compared according to the driving route and route length of the intelligent handling equipment and the telescopic length L2 of the telescopic arm of the loading platform in the database of the goods to be shipped. If the driving route and route length of the intelligent handling equipment in the goods label in the database are the same as those of the goods to be shipped, the telescopic length L3 of the loading platform of the intelligent handling equipment in the goods label is identified, and the stacking layer where the goods to be shipped are located is retrieved according to L2, and the height H of the stacking layer is identified. L3 is compared with H. When L3 is greater than H, the goods are marked as non-influenced goods. When L When 3 is less than H, L2 and L3 are compared. If L3 is less than L2, the goods are marked as non-impacted goods, otherwise the goods are marked as impacted goods, and the number of goods marked as impacted goods is identified. According to the number of intelligent handling devices corresponding to the number of goods, the goods marked as impacted goods are allocated to the intelligent handling devices in sequence, the telescopic lengths of the telescopic arms of the loading platforms of the intelligent handling devices are sorted in descending order, and the intelligent handling devices are arranged according to the sorting sequence. The goods are obtained according to the driving route and route length of the intelligent handling equipment in the label of the goods to be shipped and the telescopic length of the telescopic arm of the loading platform.

Images