A smart warehouse monitoring method, device and storage medium

Abstract

The present invention discloses a smart warehouse monitoring method, device and storage medium. The method includes: obtaining the total grabbing space size of the warehouse system and the actual storage structure data of the total grabbing space, so as to obtain the grabbing strength; according to the grabbing strength, traverse and grab all the storages in the warehouse to obtain the traversal grabbing results; according to the traversal grabbing results, calculate the average probability of the storage object being grabbed; according to the probability average, obtain the probability of the sub-storage object being left behind; according to the probability of the sub-storage object being left behind, obtain the estimated total grabbing volume, compare the estimated total grabbing volume with the preset target quantity, and obtain the actual probability of the storage object being left behind; according to the actual probability of the storage object being left behind and the probability average, obtain the warehouse monitoring result. This method can realize intelligent monitoring of storage warehouses, solve the monitoring problem of missed objects in storage warehouses, and improve the monitoring effect.

Description

Technical Field

[0001] The present invention relates to the field of smart warehouse monitoring and management technology, and in particular to a smart warehouse monitoring method, device and storage medium. Background Art

[0002] At present, warehousing is an indispensable part of modern logistics, and the warehousing system has gradually developed. The warehousing system is not a simple product display. With the rapid development of modern industry, the logistics volume has increased significantly. In order to realize the modern management of warehouses and improve the functions of warehouses, not only a large number of shelves are required, but also higher requirements are put forward for the safety and flexibility of shelves. Therefore, modern warehousing tends to be high-shelf and equipment-based. The intelligent warehousing system is the product of the perfect combination of traditional static warehousing and modern logistics technology, and is an important direction for the development of intelligent technology of logistics systems.

[0003] In one prior art, a smart warehouse management and monitoring method is that a smart warehouse usually consists of multiple sub-warehouses, and each sub-warehouse is divided into multiple storage spaces, which are used to store different storage objects; each storage space needs to encode information before storage; after storage, a metering sensor is set in the storage space to detect the number of storage objects in the storage space to obtain the current total number of storage objects in the storage space. Although the above method can analyze the in-and-out information of items in the storage space from the logistics in-and-out data, thereby obtaining the current total number, it cannot accurately distinguish whether there are any missing storage objects in the storage space, because there is a possibility that storage objects in the storage space are missed, resulting in reduced accuracy of the stored data. Summary of the invention

[0004] The present invention provides a smart warehouse monitoring method, device and storage medium to realize intelligent monitoring of warehouses, solve the monitoring problem of missed objects in warehouses, and improve the monitoring effect.

[0005] In a first aspect, in order to solve the above technical problems, the present invention provides a smart warehouse monitoring method, comprising:

[0006] Obtain the total crawling space size of the storage system and the actual storage structure data of the total crawling space;

[0007] Obtaining grasping strength according to the total grasping space size and actual storage structure data of the total grasping space;

[0008] According to the grabbing strength, all storage bins in the grabbing warehouse are traversed to obtain the traversal grabbing result;

[0009] According to the traversal and grasping results, the average probability of the storage object being grasped is calculated;

[0010] According to the probability average, the probability of leaving the sub-warehouse object is obtained;

[0011] According to the probability of the sub-storage objects being left behind, an estimated total grasping quantity is obtained, and the estimated total grasping quantity is compared with a preset target quantity to obtain the actual probability of the storage objects being left behind;

[0012] The storage monitoring result is obtained by comparing the actual probability of storage object being left behind with the probability average value.

[0013] As an optional implementation manner, the obtaining of the total crawling space size of the storage system and actual storage structure data of the total crawling space includes:

[0014] By modeling the actual shape and size of the storage space, the total space available for storing items in the storage space is obtained;

[0015] According to the space sum, the total crawling space size and the actual storage structure data of the total crawling space are obtained.

[0016] As an optional implementation manner, obtaining the crawling strength according to the total crawling space size and the actual storage structure data of the total crawling space includes:

[0017] Obtaining the physical objects to be detected in the total grasping space through the total grasping space size and the actual storage structure data of the total grasping space;

[0018] According to the physical object to be detected, a volume parameter of the physical object to be detected is obtained;

[0019] The grasping strength is obtained according to the volume parameter of the physical object to be detected.

[0020] As an optional implementation, traversing the sub-warehouses in the crawling warehouse according to the crawling strength to obtain the traversal crawling result includes:

[0021] According to the grasping strength, obtaining grasping spatial trajectory information;

[0022] According to the spatial trajectory information of the grabbing, traverse the sub-storages in the grabbing storage to obtain the items in the sub-storages;

[0023] According to the items in the sub-warehouse, a traversal and crawling result is obtained.

[0024] As an optional implementation manner, obtaining the grasping spatial trajectory information according to the grasping strength includes:

[0025] Determining the number of grasped objects according to the grasping strength;

[0026] According to the number of grasped objects, random division is performed to obtain random running trajectories;

[0027] According to the random running trajectory, obtaining grasping spatial trajectory information;

[0028] The random division is performed according to the number of grasped objects, including determining the random running trajectory through a random distribution model.

[0029] As an optional implementation, the calculating, based on the traversal and grasping results, an average probability of the storage object being grasped includes:

[0030] According to the traversal and crawling results, a valid combination having a traversal probability greater than or equal to a preset probability threshold is obtained;

[0031] According to the effective combination, the total grasping area is obtained;

[0032] According to the total grasping area, obtaining the probability of the area occupied by the effective combination in the total grasping area;

[0033] According to the probability of the area occupied by the effective combination in the total grasping area, the average probability of the storage object being grasped is obtained;

[0034] Wherein, the total grasping area is The probability of the effective combination occupying the total grasping area can be expressed by the following formula:

[0035] ;

[0036] In the formula, represents the total grasping area, s represents the library, represents the total area of ​​the total crawl space, It represents the probability of the area occupied by the i-th valid combination in the library in the total grasping space;

[0037] The average probability of the stored object being grasped is expressed by the following formula:

[0038] ;

[0039] In the formula, It represents the average probability of the storage object being grasped. represents the probability of the area occupied by the i-th valid combination in the library in the total capture space, It indicates the number of valid combinations.

[0040] As an optional implementation, obtaining an estimated total grasping quantity according to the left-behind probability of the sub-storage objects, and comparing the estimated total grasping quantity with a preset target grasping quantity to obtain the actual left-behind probability of the storage objects includes:

[0041] Obtaining the total amount of storage objects left behind according to the left-behind probability of the sub-storage objects;

[0042] Obtaining an estimated grasping amount based on the total amount of the stored objects left;

[0043] A first difference is obtained by subtracting the estimated grasping quantity from the preset grasping quantity, and an actual probability of left-behind storage objects is obtained based on the first difference.

[0044] As an optional implementation manner, the storage monitoring result is obtained by comparing the actual probability of the storage object being left behind with the average probability of the storage object being grabbed, including:

[0045] When the actual probability of the stored object being left behind is greater than or equal to the average probability of the stored object being grabbed, adjusting the system parameters;

[0046] When the actual probability of the stored object being left behind is less than the average probability of the stored object being grabbed, the storage monitoring result is obtained.

[0047] In a second aspect, the present invention provides a smart warehouse monitoring device, characterized in that it includes:

[0048] An information receiving module is used to obtain the total grabbing space size of the storage system and the actual storage structure data of the total grabbing space;

[0049] An information matching module, used for obtaining the grasping strength according to the total grasping space size and the actual storage structure data of the total grasping space;

[0050] A traversal processing module, used for traversing random sub-warehouses in the crawling warehouse according to the crawling strength, and obtaining a traversal crawling result;

[0051] A first numerical calculation module, used for calculating the average probability of the storage object being grasped according to the traversal grasping result;

[0052] A second numerical calculation module is used to obtain the probability of leaving the sub-storage object according to the average probability of the storage object being grabbed;

[0053] A data collection module is used to obtain an estimated total grasping quantity according to the probability of the sub-storage objects being left behind, and compare the estimated total grasping quantity with a preset target grasping quantity to obtain the actual probability of the storage objects being left behind;

[0054] The comparison and analysis module is used to compare the actual probability of the stored objects being left behind with the average probability of the stored objects being grabbed to obtain the storage monitoring result.

[0055] In a third aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned smart warehouse monitoring methods.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] The present invention provides a smart warehouse monitoring method, device and storage medium. The method is executed by a controller, including: obtaining the total grasping space size of a warehouse system and actual storage structure data of the total grasping space; obtaining grasping strength according to the total grasping space size and the actual storage structure data of the total grasping space; traversing all storages in the grasping warehouse according to the grasping strength to obtain traversal grasping results; calculating the average probability of a storage object being grasped according to the traversal grasping results; obtaining the probability of a sub-storage object being left behind according to the probability average; obtaining an estimated total grasping volume according to the probability of a sub-storage object being left behind, comparing the estimated total grasping volume with a preset target quantity to obtain the actual probability of a storage object being left behind; and obtaining a warehouse monitoring result according to comparing the actual probability of a storage object being left behind with the probability average. After the controller obtains the information of the total storage space and storage structure of the warehouse, it uses the collected data to calculate the grasping strength, that is, the grasping capacity per unit space. According to the grasping strength, simulate grasping is performed on all storage areas in the warehouse. Through the results of simulated grasping, the average probability of all items being grasped is calculated. According to the probability average, the probability of the ungrabbed items in the sub-warehouse is further calculated. The actual total grasping volume is estimated by the probability of being left behind, and compared with the preset target quantity. By comparing the estimated grasping volume and the target quantity, the actual probability of the storage object being left behind is obtained. Finally, the actual probability of being left behind is compared with the probability average to obtain the result of warehouse monitoring, so as to evaluate the monitoring efficiency and possible improvement measures. In this way, this method realizes intelligent monitoring of storage warehouses, solves the monitoring problem of missed objects in storage warehouses, and improves the monitoring effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of a smart warehouse monitoring method provided by the first embodiment of the present invention;

[0059] Figure 2 It is a structural schematic diagram of a smart warehouse monitoring device provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0060] 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.

[0061] At present, warehousing is an indispensable part of modern logistics, and the warehousing system has gradually developed. The warehousing system is not a simple product display. With the rapid development of modern industry, the logistics volume has increased significantly. In order to realize the modern management of warehouses and improve the functions of warehouses, not only a large number of shelves are required, but also higher requirements are put forward for the safety and flexibility of shelves. Therefore, modern warehousing tends to be high-shelf and equipment-based. The intelligent warehousing system is the product of the perfect combination of traditional static warehousing and modern logistics technology, and is an important direction for the development of intelligent technology of logistics systems.

[0062] In one prior art, a smart warehouse management and monitoring method is that a smart warehouse usually consists of multiple sub-warehouses, and each sub-warehouse is divided into multiple storage spaces, which are used to store different storage objects; each storage space needs to encode information before storage; after storage, a metering sensor is set in the storage space to detect the number of storage objects in the storage space to obtain the current total number of storage objects in the storage space. Although the above method can analyze the in-and-out information of items in the storage space from the logistics in-and-out data, thereby obtaining the current total number, it cannot accurately distinguish whether there are any missing storage objects in the storage space, because there is a possibility that storage objects in the storage space are missed, resulting in reduced accuracy of the stored data.

[0063] In order to solve the above problems, a smart warehouse monitoring method provided by the embodiment of the present application is introduced and explained in detail through the following specific embodiments.

[0064] Reference Figure 1 The first embodiment of the present invention provides a smart warehouse monitoring method, comprising the following steps:

[0065] S11, obtaining the total grabbing space size of the storage system and actual storage structure data of the total grabbing space;

[0066] S12, obtaining a grasping strength according to the total grasping space size and actual storage structure data of the total grasping space;

[0067] S13, according to the grabbing strength, traverse all the storages in the grabbing warehouse to obtain the traversal grabbing result;

[0068] S14, calculating the average probability of the storage object being grasped according to the traversal grasping results;

[0069] S15, obtaining the probability of leaving the sub-warehouse object according to the probability average value;

[0070] S16, obtaining an estimated total grasping quantity according to the left-behind probability of the sub-storage objects, and comparing the estimated total grasping quantity with a preset target quantity to obtain an actual left-behind probability of the stored objects;

[0071] S17, obtaining a storage monitoring result according to the comparison between the actual probability of the objects left behind in the warehouse and the probability average value.

[0072] It should be noted that the acquisition of the total grabbing space size of the storage system and the actual storage structure data of the total grabbing space is completed by the machine vision module, wherein the machine vision module is a key component in modern industrial automation and intelligent manufacturing. It captures and analyzes images through high-precision visual sensors to provide the necessary visual information for the automation system. This module usually includes different types of cameras, such as CCD (charge-coupled device) cameras, CMOS (complementary metal oxide semiconductor) cameras and line array cameras, each of which has unique advantages and application scenarios. CCD cameras are known for their high resolution, high sensitivity and excellent image quality, and are particularly suitable for applications that require high-quality image capture. CMOS cameras are favored for their fast imaging capabilities, low power consumption and cost-effectiveness, and are widely used in situations that require fast response. Line array cameras are used for continuous object detection and measurement tasks with their expertise in high-speed scanning and precise measurement.

[0073] Exemplarily, the machine vision module in this embodiment uses a CCD camera, and the total grasping space size of the storage system collected by the CCD camera is obtained according to the storage position of the CCD camera, and the actual storage structure data of the total grasping space is obtained according to the image of the storage space collected by the CCD camera. Among them, the actual storage structure data of the total grasping space needs to be further determined according to the actual storage layout and organization of the items in the storage space, and the actual storage layout and organization of the items include the placement and classification of the items.

[0074] In this embodiment, the total grasping space size of the storage system and the actual storage structure data of the total grasping space are obtained; the grasping strength is obtained according to the total grasping space size and the actual storage structure data of the total grasping space; according to the grasping strength, all storage objects in the warehouse are traversed to obtain the traversal grasping results; according to the traversal grasping results, the average probability of the storage object being grasped is calculated; according to the probability average, the probability of the sub-storage object being left behind is obtained; according to the probability average, the estimated total grasping volume is obtained, and the estimated total grasping volume is compared with the preset target quantity to obtain the actual probability of the storage object being left behind; according to the comparison of the actual probability of the storage object being left behind with the probability average, the storage monitoring result is obtained. In this embodiment, after the controller obtains the information of the total storage space and storage structure of the warehouse, it uses the collected data to calculate the grasping strength, that is, the grasping capacity within the unit space. According to the grasping strength, all storage areas in the warehouse are simulated for grasping. Through the results of the simulated grasping, the average probability of all items being grasped is calculated. According to the probability average, the probability of the ungrabbed items in the sub-warehouse is further calculated. The actual total grasping volume is estimated by the probability of being left behind, and compared with the preset target quantity. By comparing the estimated grasping volume and the target quantity, the actual probability of the storage object being left behind is obtained. Finally, the actual probability of being left behind is compared with the probability average to obtain the result of warehouse monitoring, so as to evaluate the grasping efficiency and possible improvement measures. In this way, the method realizes intelligent monitoring of storage warehouses, solves the monitoring problem of missed objects in storage warehouses, and improves the monitoring effect.

[0075] In step S11, the total crawling space size of the storage system and the actual storage structure data of the total crawling space are obtained, including:

[0076] By modeling the actual shape and size of the storage space, the total space available for storing items in the storage space is obtained;

[0077] According to the space sum, the total crawling space size and the actual storage structure data of the total crawling space are obtained.

[0078] It should be noted that the shape and area size of the storage space are obtained by visual sensors, and the images transmitted by the visual sensors are analyzed. A model of the storage space is established through three-dimensional modeling software, and the total space used to store items in the storage space is obtained through the established model.

[0079] In step S12, the total crawling space size and the actual storage structure data of the total crawling space are used to obtain the crawling strength, including:

[0080] Obtaining the physical objects to be detected in the total grasping space through the total grasping space size and the actual storage structure data of the total grasping space;

[0081] According to the physical object to be detected, a volume parameter of the physical object to be detected is obtained;

[0082] The grasping strength is obtained according to the volume parameter of the physical object to be detected.

[0083] It should be noted that the shapes of the physical objects to be detected in the total grasping space include square and irregular shaped objects. The volume parameters of the physical objects to be detected are obtained by estimating the size and shape of the physical objects to be detected. The number of the physical objects to be detected in the current storage is determined according to the volume parameters of the physical objects to be detected, and then the grasping strength is obtained. The grasping strength can be expressed in terms of quantity or as a percentage of the total space occupied.

[0084] In step S13, according to the grabbing strength, all storages in the grabbing warehouse are traversed to obtain the traversal grabbing results, including:

[0085] According to the grasping strength, obtaining grasping spatial trajectory information;

[0086] According to the spatial trajectory information of the grabbing, traverse the sub-storages in the grabbing storage to obtain the items in the sub-storages;

[0087] According to the items in the sub-warehouse, a traversal and crawling result is obtained.

[0088] It should be noted that, obtaining the grasping spatial trajectory information according to the grasping strength includes: determining the number of grasped objects according to the grasping strength;

[0089] According to the number of grasped objects, random division is performed to obtain random running trajectories;

[0090] According to the random running trajectory, obtaining grasping spatial trajectory information;

[0091] The random division is performed according to the number of grasped objects, including determining the random running trajectory through a random distribution model.

[0092] It should be further explained that the random distribution model divides the grasping space into a three-dimensional space structure of a×b×c, and then randomly samples the three-dimensional space structure, thereby randomly grasping an object from the three-dimensional space structure. If there is a repeated grasping object in the process of determining the running trajectory, the grasping strength is increased by one amount; if there are n repeated grasping objects, the grasping strength is increased by n amounts.

[0093] Exemplarily, the three-dimensional space is a three-dimensional space of 100×100×100, and when performing random sampling, it is determined by the following formula:

[0094] ;

[0095] In the formula, Indicates the horizontal coordinate value of the randomly sampled item, It represents a function that generates a random decimal between 0 and 1;

[0096] ;

[0097] In the formula, Indicates the ordinate value of the randomly sampled item. It represents a function that generates a random decimal between 0 and 1;

[0098] ;

[0099] In the formula, Indicates the vertical coordinate value of the randomly sampled item. It represents a function that generates a random decimal between 0 and 1;

[0100] Among them, the horizontal coordinate, vertical coordinate and vertical coordinate are expressed in a three-dimensional coordinate system, and the three-dimensional coordinate system is established with the warehouse entrance as the origin of the coordinate system, the long side of the warehouse as the x-axis, the short side as the y-axis, and the height of the warehouse as the z-axis.

[0101] In step S14, the average probability of the storage object being grasped is calculated based on the traversal grasping results, including:

[0102] According to the traversal and crawling results, a valid combination having a traversal probability greater than or equal to a preset probability threshold is obtained;

[0103] According to the effective combination, the total grasping area is obtained;

[0104] According to the total grasping area, obtaining the probability of the area occupied by the effective combination in the total grasping area;

[0105] According to the probability of the area occupied by the effective combination in the total grasping area, the average probability of the storage object being grasped is obtained;

[0106] Wherein, the total grasping area is The probability of the effective combination occupying the total grasping area can be expressed by the following formula:

[0107] ;

[0108] In the formula, represents the total grasping area, s represents the library, represents the total area of ​​the total crawl space, It represents the probability of the area occupied by the i-th valid combination in the library in the total grasping space;

[0109] The average probability of the stored object being grasped is expressed by the following formula:

[0110] ;

[0111] In the formula, It represents the average probability of the storage object being grasped. represents the probability of the area occupied by the i-th valid combination in the library in the total capture space, It indicates the number of valid combinations.

[0112] It should be noted that the preset probability value is preset by the user, and the preset value may be 0.3, which is not specifically limited in the present invention. The valid combination whose traversal probability is greater than or equal to the preset probability threshold is the traversal probability obtained by dividing the number of occurrences of each coordinate point by the total number of traversals in multiple simulated traversal capture processes. When the traversal probability is greater than or equal to the preset probability threshold, the coordinate point is marked as a valid combination.

[0113] In step S15, the probability of leaving the sub-warehouse object is obtained according to the probability average value.

[0114] It should be noted that the probability average is obtained by traversing the grabbing results. According to the probability average, the probability of the item being grabbed can be obtained. Since the total storage is divided into multiple sub-storages, each sub-storage can be grabbed more randomly. Under the restriction of a certain grabbing strength, the total grabbing space has the possibility of being completely grabbed. By calculating the average probability value of a single storage object under a certain grabbing strength, the probability of each storage object in the warehouse remaining in the warehouse after being randomly grabbed under the set grabbing strength can be calculated. By comparison, the probability of each storage in the warehouse under the maximum grabbing strength can be obtained, so that the probability of the sub-storage object being left can be calculated.

[0115] In step S16, the estimated total grasping quantity is obtained according to the probability of the sub-storage objects being left behind, and the estimated total grasping quantity is compared with the preset target grasping quantity to obtain the actual probability of the storage objects being left behind, including:

[0116] Obtaining the total amount of storage objects left behind according to the left-behind probability of the sub-storage objects;

[0117] Obtaining an estimated grasping amount based on the total amount of the stored objects left;

[0118] A first difference is obtained by subtracting the estimated grasping quantity from the preset grasping quantity, and an actual probability of left-behind storage objects is obtained based on the first difference.

[0119] It should be noted that the remaining amount of the sub-warehouse objects is obtained by multiplying the probability of the objects left behind in the sub-warehouse by the total number of the sub-warehouse objects, and the total amount of the objects left behind in the warehouse is added up to obtain the total amount of the objects left behind; the estimated grasping amount can be obtained by subtracting the total amount of the objects left behind from the total amount of the warehouse objects; the omission error percentage is obtained by dividing the first difference by the total amount of the warehouse objects, and the actual probability of the objects left behind is obtained by summing the omission error percentage and the probability of the omission of the sub-warehouse. The preset grasping quantity is preset by the user, and the preset grasping quantity can be 400, which is not specifically limited in the present invention.

[0120] In step S17, the actual probability of the object being left behind is compared with the average probability of the object being grabbed to obtain a storage monitoring result, including:

[0121] When the actual probability of the stored object being left behind is greater than or equal to the average probability of the stored object being grabbed, adjusting the system parameters;

[0122] When the actual probability of the stored object being left behind is less than the average probability of the stored object being grabbed, the storage monitoring result is obtained.

[0123] It should be noted that the adjustment of system parameters includes adjusting the grasping strength, and then obtaining the probability of stored objects being left behind through operation. When the grasping strength is increased, the actual probability of stored objects being left behind decreases, and the grasping strength is continued to be increased to reach the optimal point. At this time, the warehouse monitoring effect is the best; similarly, when the grasping strength is reduced, the actual probability of stored objects being left behind decreases, and the grasping strength is continued to be increased to reach the optimal point. At this time, the warehouse monitoring effect is the best; when the adjusted grasping strength makes the probability of stored objects being left behind less than the average probability of the stored objects being grasped, it indicates that the warehouse monitoring method at this time has met the requirements.

[0124] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0125] In this embodiment, a smart warehouse monitoring system is proposed, which consists of the following key parts: data collection end, trajectory processing end, probability calculation end, grasping strength setting end, deviation analysis end, and performance evaluation end. These components work together to ensure the normal operation of the smart warehouse monitoring system.

[0126] The working process is as follows:

[0127] Step 1: Collect the total crawling space associated with the video-monitored storage system and the actual storage structure of the total crawling space;

[0128] Step 2: Count the actual trajectory of the total grasping space under the set grasping intensity;

[0129] Step 3: Process the actual trajectory of the total grasping space, obtain the traversed grasping space, and then obtain the random traversal grasping information. This includes counting the total grasping area and the area covered by the actual trajectory in the total grasping space, traversing the edge of the total grasping space, obtaining the edge coverage area of ​​the final total grasping space, and comparing and analyzing each area in the sub-tracking area set with the total trajectory area;

[0130] Step 4: Sampling is performed based on the random traversal grabbing information to obtain the probability of randomly grabbing the storage objects in the warehouse, including collecting target combinations, combinations with traversal probabilities greater than preset probabilities, counting the total grabbing area in the combinations, and counting the probability of the combination with traversal probabilities greater than preset probabilities occupying the total grabbing area.

[0131] Step 5: Process the probability of randomly grabbing the storage objects in the warehouse to obtain the storage probability under random grabbing. This includes: extracting the single traversal information from step 2, calculating the probability of missing in the random inventory according to the probability calculated in step 4, and obtaining the storage probability under random grabbing according to the probability of missing in the random inventory.

[0132] Step 6: Predict the actual inventory risk of the stored objects based on the storage probability under random grabbing. Count and set the grabbing intensity during the actual inventory.

[0133] Step 7: Detect and track the actual target grasping trajectory to obtain the actual target grasping information of the actual target grasping trajectory.

[0134] Step 8: Preset the deviation error value, count and compare the deviation information with the preset value.

[0135] Step 9: Display storage monitoring results or remind to adjust storage parameters.

[0136] Through the above steps and system design, a smart warehouse monitoring method, device and storage medium of the present invention can realize intelligent monitoring of warehouses, solve the monitoring problem of missed objects in warehouses, and improve the monitoring effect.

[0137] In summary, the present invention provides a smart warehouse monitoring method, device and storage medium. The method is executed by a controller, including: obtaining the total grasping space size of the warehouse system and the actual storage structure data of the total grasping space; obtaining the grasping strength according to the total grasping space size and the actual storage structure data of the total grasping space; traversing all storage spaces in the grasping warehouse according to the grasping strength to obtain the traversal grasping results; calculating the average probability of the warehouse object being grasped according to the traversal grasping results; obtaining the probability of leaving behind a sub-warehouse object according to the probability average; obtaining an estimated total grasping volume according to the probability of leaving behind the sub-warehouse object, comparing the estimated total grasping volume with the preset target quantity to obtain the actual probability of leaving behind of the warehouse object; obtaining the warehouse monitoring result according to comparing the actual probability of leaving behind of the warehouse object with the probability average. After the controller obtains the information of the total storage space and storage structure of the warehouse, it uses the collected data to calculate the grasping strength, that is, the grasping capacity per unit space. According to the grasping strength, simulate grasping is performed on all storage areas in the warehouse. Through the results of simulated grasping, the average probability of all items being grasped is calculated. According to the probability average, the probability of the ungrabbed items in the sub-warehouse is further calculated. The actual total grasping volume is estimated by the probability of being left behind, and compared with the preset target quantity. By comparing the estimated grasping volume and the target quantity, the actual probability of the storage object being left behind is obtained. Finally, the actual probability of being left behind is compared with the probability average to obtain the result of warehouse monitoring, so as to evaluate the monitoring efficiency and possible improvement measures. In this way, this method realizes intelligent monitoring of storage warehouses, solves the monitoring problem of missed objects in storage warehouses, and improves the monitoring effect.

[0138] Reference Figure 2 The second embodiment of the present invention provides a smart warehouse monitoring device, comprising:

[0139] An information receiving module is used to obtain the total grabbing space size of the storage system and the actual storage structure data of the total grabbing space;

[0140] An information matching module, used for obtaining the grasping strength according to the total grasping space size and the actual storage structure data of the total grasping space;

[0141] A traversal processing module, used for traversing random sub-warehouses in the crawling warehouse according to the crawling strength, and obtaining a traversal crawling result;

[0142] A first numerical calculation module, used for calculating the average probability of the storage object being grasped according to the traversal grasping result;

[0143] A second numerical calculation module is used to obtain the probability of leaving the sub-storage object according to the average probability of the storage object being grabbed;

[0144] A data collection module is used to obtain an estimated total grasping quantity according to the probability of the sub-storage objects being left behind, and compare the estimated total grasping quantity with a preset target grasping quantity to obtain the actual probability of the storage objects being left behind;

[0145] The comparison and analysis module is used to compare the actual probability of the stored objects being left behind with the average probability of the stored objects being grabbed to obtain the storage monitoring result.

[0146] In one implementation, the information receiving module is used to:

[0147] By modeling the actual shape and size of the storage space, the total space available for storing items in the storage space is obtained;

[0148] According to the space sum, the total crawling space size and the actual storage structure data of the total crawling space are obtained.

[0149] It should be noted that the shape and area size of the storage space are obtained by visual sensors, and the images transmitted by the visual sensors are analyzed. A model of the storage space is established through three-dimensional modeling software, and the total space used to store items in the storage space is obtained through the established model.

[0150] In one implementation, the information matching module is used to:

[0151] Obtaining the physical objects to be detected in the total grasping space through the total grasping space size and the actual storage structure data of the total grasping space;

[0152] According to the physical object to be detected, a volume parameter of the physical object to be detected is obtained;

[0153] The grasping strength is obtained according to the volume parameter of the physical object to be detected.

[0154] In one implementation, the traversal processing module is used to:

[0155] According to the grasping strength, obtaining grasping spatial trajectory information;

[0156] According to the spatial trajectory information of the grabbing, traverse the sub-storages in the grabbing storage to obtain the items in the sub-storages;

[0157] According to the items in the sub-warehouse, a traversal and crawling result is obtained.

[0158] In one implementation, the first numerical calculation module is used to:

[0159] According to the traversal and crawling results, a valid combination having a traversal probability greater than or equal to a preset probability threshold is obtained;

[0160] According to the effective combination, the total grasping area is obtained;

[0161] According to the total grasping area, obtaining the probability of the area occupied by the effective combination in the total grasping area;

[0162] According to the probability of the area occupied by the effective combination in the total grasping area, the average probability of the storage object being grasped is obtained;

[0163] Wherein, the total grasping area is The probability of the effective combination occupying the total grasping area can be expressed by the following formula:

[0164] ;

[0165] In the formula, represents the total grasping area, s represents the library, represents the total area of ​​the total crawl space, It represents the probability of the area occupied by the i-th valid combination in the library in the total grasping space;

[0166] The average probability of the stored object being grasped is expressed by the following formula:

[0167] ;

[0168] In the formula, It represents the average probability of the storage object being grasped. represents the probability of the area occupied by the i-th valid combination in the library in the total capture space, It indicates the number of valid combinations.

[0169] In one implementation, the second numerical calculation module is used to:

[0170] According to the probability average value, the probability of leaving the sub-warehouse object is obtained.

[0171] Among them, the probability average value is obtained by traversing the grabbing results. According to the probability average value, the probability of the item being grabbed can be obtained. Since the total storage is divided into multiple sub-storages, each sub-storage can be grabbed more randomly. Under the restriction of a certain grabbing strength, the total grabbing space has the possibility of being fully grabbed. By calculating the average probability value of a single storage object under a certain grabbing strength, the probability of each storage object in the warehouse remaining in the warehouse after being randomly grabbed under the set grabbing strength can be calculated. By comparison, the probability of each storage in the warehouse under the maximum grabbing strength can be obtained, so that the probability of the sub-storage object being left can be calculated.

[0172] In one embodiment, the data collection module is used to:

[0173] Obtaining the total amount of storage objects left behind according to the left-behind probability of the sub-storage objects;

[0174] Obtaining an estimated grasping amount based on the total amount of the stored objects left;

[0175] A first difference is obtained by subtracting the estimated grasping quantity from the preset grasping quantity, and an actual probability of left-behind storage objects is obtained based on the first difference.

[0176] In one embodiment, the comparative analysis module is used to:

[0177] When the actual probability of the stored object being left behind is greater than or equal to the average probability of the stored object being grabbed, adjusting the system parameters;

[0178] When the actual probability of the stored object being left behind is less than the average probability of the stored object being grabbed, the storage monitoring result is obtained.

[0179] It should be noted that the smart warehouse monitoring device provided in an embodiment of the present invention is used to execute all the process steps of a smart warehouse monitoring method in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be elaborated on.

[0180] In summary, the present invention provides a smart warehouse monitoring method, device and storage medium. The method is executed by a controller, including: obtaining the total grasping space size of the warehouse system and the actual storage structure data of the total grasping space; obtaining the grasping strength according to the total grasping space size and the actual storage structure data of the total grasping space; traversing all storage spaces in the grasping warehouse according to the grasping strength to obtain the traversal grasping results; calculating the average probability of the warehouse object being grasped according to the traversal grasping results; obtaining the probability of leaving behind a sub-warehouse object according to the probability average; obtaining an estimated total grasping volume according to the probability of leaving behind the sub-warehouse object, comparing the estimated total grasping volume with the preset target quantity to obtain the actual probability of leaving behind of the warehouse object; obtaining the warehouse monitoring result according to comparing the actual probability of leaving behind of the warehouse object with the probability average. After the controller obtains the information of the total storage space and storage structure of the warehouse, it uses the collected data to calculate the grasping strength, that is, the grasping capacity per unit space. According to the grasping strength, simulate grasping is performed on all storage areas in the warehouse. Through the results of simulated grasping, the average probability of all items being grasped is calculated. According to the probability average, the probability of the ungrabbed items in the sub-warehouse is further calculated. The actual total grasping volume is estimated by the probability of being left behind, and compared with the preset target quantity. By comparing the estimated grasping volume and the target quantity, the actual probability of the storage object being left behind is obtained. Finally, the actual probability of being left behind is compared with the probability average to obtain the result of warehouse monitoring, so as to evaluate the monitoring efficiency and possible improvement measures. In this way, this method realizes intelligent monitoring of storage warehouses, solves the monitoring problem of missed objects in storage warehouses, and improves the monitoring effect.

[0181] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a random distribution model. When the processor executes the computer program, the steps in the above-mentioned smart warehouse monitoring method embodiments are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the information matching module.

[0182] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0183] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0184] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0185] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0186] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0187] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0188] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A smart warehouse monitoring method, characterized in that: include: Obtain the total crawling space size of the storage system and the actual storage structure data of the total crawling space; Obtaining grasping strength according to the total grasping space size and actual storage structure data of the total grasping space; According to the grabbing strength, all storage bins in the grabbing warehouse are traversed to obtain the traversal grabbing result; According to the traversal and grasping results, the average probability of the storage object being grasped is calculated; According to the probability average, the probability of leaving the sub-warehouse object is obtained; According to the probability of the sub-storage objects being left behind, an estimated total grasping quantity is obtained, and the estimated total grasping quantity is compared with a preset target quantity to obtain the actual probability of the storage objects being left behind; Obtaining a storage monitoring result according to the comparison between the actual probability of the object being left in storage and the probability average value; Wherein, the grasping strength is obtained according to the total grasping space size and the actual storage structure data of the total grasping space, including: obtaining the physical items to be detected in the total grasping space through the total grasping space size and the actual storage structure data of the total grasping space; estimating the size and shape of the physical items to be detected to obtain the volume parameters of the physical items to be detected, and judging the number of the items to be detected in the current storage according to the volume parameters of the items to be detected to obtain the grasping strength; wherein, the grasping strength is expressed in terms of the number or the percentage of the total space occupied; Among them, the probability of leaving a sub-storage object is obtained based on the probability average value, including: calculating the probability that each storage object in the warehouse remains in the warehouse after being randomly grabbed under the set grasping intensity; obtaining the probability of remaining in each storage in the warehouse under the condition of the maximum grasping intensity by comparison, thereby obtaining the probability of leaving a sub-storage object.

2. The intelligent warehouse monitoring method according to claim 1 is characterized in that: The obtaining of the total crawling space size of the storage system and the actual storage structure data of the total crawling space includes: By modeling the actual shape and size of the storage space, the total space available for storing items in the storage space is obtained; According to the space sum, the total crawling space size and the actual storage structure data of the total crawling space are obtained.

3. The intelligent warehouse monitoring method according to claim 1 is characterized in that: According to the crawling strength, traversing the sub-warehouses in the crawling warehouse to obtain the traversal crawling results includes: According to the grasping strength, obtaining grasping spatial trajectory information; According to the spatial trajectory information of the grabbing, traverse the sub-storages in the grabbing storage to obtain the items in the sub-storages; Obtain traversal and crawling results based on the items in the sub-warehouse; Wherein, obtaining the spatial trajectory information of grasping according to the grasping strength includes: determining the number of grasped items according to the grasping strength; performing random division according to the number of grasped items to obtain a random operation trajectory; obtaining the spatial trajectory information of grasping according to the random operation trajectory; wherein, performing random division according to the number of grasped items includes determining the random operation trajectory through a random distribution model.

4. The intelligent warehouse monitoring method according to claim 1 is characterized in that: The calculating, based on the traversal and grasping results, the average probability of the storage object being grasped includes: According to the traversal and crawling results, a valid combination with a traversal probability greater than or equal to a preset probability threshold is obtained; wherein the valid combination with a traversal probability greater than or equal to the preset probability threshold is a traversal probability obtained by dividing the number of occurrences of each coordinate point by the total number of traversals in multiple simulated traversal and crawling processes, and when the traversal probability is greater than or equal to the preset probability threshold, the coordinate point is marked as a valid combination; The total grasping area is obtained by counting; According to the total grasping area, obtaining the probability of the area occupied by the effective combination in the total grasping area; According to the probability of the area occupied by the effective combination in the total grasping area, the average probability of the storage object being grasped is obtained; Wherein, the total grasping area is The probability of the effective combination occupying the total grasping area can be expressed by the following formula: ； In the formula, represents the total grabbing area, s represents the sub-warehouse, represents the total area of ​​the space of the total crawl space, It represents the probability of the area occupied by the i-th valid combination in the library in the total grasping space; The average probability of the stored object being grasped is expressed by the following formula: ； In the formula, It represents the average probability of the storage object being grasped. represents the probability of the area occupied by the i-th valid combination in the library in the total capture space, It indicates the number of valid combinations.

5. The intelligent warehouse monitoring method according to claim 1 is characterized in that: The method of obtaining an estimated total grasping quantity according to the probability of the sub-storage objects being left behind, and comparing the estimated total grasping quantity with a preset target grasping quantity to obtain the actual probability of the storage objects being left behind includes: The remaining amount of the sub-storage objects is obtained by multiplying the remaining probability of the sub-storage objects by the total number of the sub-storage objects, and the remaining amounts of all the sub-storage objects are added together to obtain the total amount of the storage objects left behind; The estimated grasping amount is obtained by subtracting the total amount of the stored objects left behind from the total amount of the stored objects; Subtracting the estimated grasping amount from the preset grasping amount to obtain a first difference value; The omission error percentage is obtained by dividing the first difference by the total amount of stored objects, and the actual probability of left-behind stored objects is obtained by summing the omission error percentage and the sub-warehouse omission probability.

6. The intelligent warehouse monitoring method according to claim 1 is characterized in that: The obtaining of the storage monitoring result according to the comparison of the actual probability of the storage object being left behind with the average probability of the storage object being grabbed includes: When the actual probability of the stored object being left behind is greater than or equal to the average probability of the stored object being grabbed, adjusting the system parameters; When the actual probability of the stored object being left behind is less than the average probability of the stored object being grabbed, the storage monitoring result is obtained.

7. A smart warehouse monitoring device, characterized in that: include: An information receiving module is used to obtain the total grabbing space size of the storage system and the actual storage structure data of the total grabbing space; An information matching module, used for obtaining the grasping strength according to the total grasping space size and the actual storage structure data of the total grasping space; A traversal processing module, used for traversing random sub-warehouses in the crawling warehouse according to the crawling strength, and obtaining a traversal crawling result; A first numerical calculation module, used for calculating the average probability of the storage object being grasped according to the traversal grasping result; A second numerical calculation module is used to obtain the probability of leaving the sub-storage object according to the average probability of the storage object being grabbed; A data collection module, configured to obtain an estimated total grasping quantity according to the probability of the sub-storage objects being left behind, and compare the estimated total grasping quantity with a preset target grasping quantity to obtain the actual probability of the storage objects being left behind; A comparison and analysis module, used to compare the actual probability of the stored object being left behind with the average probability of the stored object being grabbed, to obtain a storage monitoring result; Wherein, the grasping strength is obtained according to the total grasping space size and the actual storage structure data of the total grasping space, including: obtaining the physical items to be detected in the total grasping space through the total grasping space size and the actual storage structure data of the total grasping space; estimating the size and shape of the physical items to be detected to obtain the volume parameters of the physical items to be detected, and judging the number of the items to be detected in the current storage according to the volume parameters of the items to be detected to obtain the grasping strength; wherein, the grasping strength is expressed in terms of the number or the percentage of the total space occupied; Among them, the probability of sub-storage objects being left behind is obtained according to the average probability of the storage objects being grasped, including: calculating the probability that each storage object in the warehouse will remain in the warehouse after being randomly grasped under the set grasping intensity; and obtaining the probability of each storage object remaining in the warehouse under the condition of the maximum grasping intensity by comparison, thereby obtaining the probability of sub-storage objects being left behind.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the intelligent warehouse monitoring method as described in any one of claims 1 to 6.

Images