Automatic warehouse management method and system based on artificial intelligence embedded host

Abstract

The invention discloses an automatic warehouse management method and system based on an artificial intelligence embedded host, and relates to the technical field of warehouse management, and the method comprises the steps: obtaining a storage warehouse corresponding to a target type of goods as a target warehouse, obtaining the environment data of the target warehouse and other remaining warehouses, and screening the other remaining warehouses, thereby achieving the automatic warehouse management. A storable warehouse set is obtained; for each storable warehouse in the storable warehouse set, obtaining the vacant space of the corresponding warehouse, the distance to the target warehouse, and the connection state of the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse; according to the method, the target type of goods are stored in the storable centralized warehouse according to the priority storage indexes from large to small, so that the target goods can be reasonably stored in other warehouses, it is ensured that the warehouses have enough storage capacity to meet the requirements in the peak period of the target goods, and goods loss caused by improper storage is avoided.

Description

Technical Field

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

[0002] Warehouse management based on artificial intelligence embedded host refers to the use of central embedded devices equipped with artificial intelligence technology to monitor and automatically manage the logistics, inventory, environmental monitoring, etc. of the warehouse, thereby improving the efficiency and accuracy of warehouse management; A large warehouse management park usually includes multiple warehouses. In order to classify and manage goods more accurately, the staff will determine which type of goods each warehouse is suitable for storing based on the storage environment of each warehouse, and use each warehouse as a dedicated storage warehouse for the corresponding goods. At the same time, the central embedded device is connected to the management system of each warehouse, and the management system of each warehouse is controlled by the central embedded device to monitor and automatically manage each warehouse. This can reduce losses and simplify the inventory management process, allowing staff to locate and dispatch goods faster and more conveniently, thereby improving overall operational efficiency. For certain goods, in order to ensure the supply of goods during the upcoming peak period, we will choose to produce and store them in advance to ensure that we can supply the demand during the peak period; but due to the excessive quantity of goods, the storage space of the warehouse corresponding to this kind of goods may be full and can no longer be stored; and if the excess goods are returned, the goods stored in the warehouse may not be able to meet the demand during the peak period, and if they are blindly stored in other warehouses, it may cause losses due to improper storage. Summary of the invention

[0003] The purpose of the present invention is to solve the problem and propose an automated warehouse management method and system based on an artificial intelligence embedded host.

[0004] In the first aspect of the implementation of the present invention, an automated warehouse management method based on an artificial intelligence embedded host is first proposed, the method comprising: Obtain the storage warehouse corresponding to the target type of goods as the target warehouse, obtain the environmental data of the target warehouse and the remaining other warehouses, and filter the remaining other warehouses according to the environmental data of the target warehouse and the remaining other warehouses to obtain a set of storable warehouses; For each storable warehouse in the storable warehouse set, obtain the corresponding warehouse vacant space, the distance to the target warehouse, and the connection status between the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse; The target category goods are stored in the centralized warehouse of the storable warehouse in the order of priority storage index from large to small.

[0005] Optionally, the remaining warehouses are screened according to the environment data of the target warehouse and the remaining warehouses, and the storable warehouse set includes: Each of the remaining warehouses is recorded as a first warehouse, and the environmental data of the target warehouse and the environmental data of the first warehouse within a preset time period are obtained, and the environmental data of the target warehouse and the environmental data of the first warehouse at each moment are preprocessed; Construct a distance matrix, in which each element is the distance between the environmental data point of the target warehouse and the environmental data point of the first warehouse; Using a dynamic programming algorithm to calculate the shortest path in the distance matrix to find the best match between the environmental data sequence of the target warehouse and the environmental data sequence of the first warehouse; According to the calculated shortest path, align the environment data sequence of the target warehouse with the environment data sequence of the first warehouse; Calculate the similarity between the aligned environment data sequence of the target warehouse and the environment data sequence of the first warehouse; and use the calculated similarity as the similarity value of the first warehouse at the corresponding time; The availability status of the corresponding first warehouse is determined according to the similarity value of each first warehouse at each moment in a preset time period, and the storable warehouse set is screened out according to the availability status of the remaining other warehouses.

[0006] Optionally, judging the availability status of the corresponding first warehouse according to the similarity value of each first warehouse at each moment in a preset time period, and filtering out the storable warehouse set according to the availability status of the remaining other warehouses includes: Sequencing the similarity values ​​of each first warehouse at each moment within a preset time period based on time to obtain a similarity value time series corresponding to the first warehouse; Calculate the similarity value mean and similarity value standard deviation of the similarity value time series of the first warehouse, and compare the similarity value mean with the preset similarity value mean minimum threshold, and compare the similarity value standard deviation with the preset similarity value standard deviation maximum threshold; When the similarity value mean is greater than the preset similarity value mean minimum threshold and the similarity value standard deviation is less than the preset similarity value standard deviation maximum threshold, the availability status of the corresponding first warehouse is recorded as available and recorded as the second warehouse; if not, the availability status of the corresponding first warehouse is recorded as unavailable; All the second warehouses among the remaining warehouses are collected as a storable warehouse set.

[0007] Optionally, obtaining the vacant space of the corresponding warehouse, the distance to the target warehouse, and the connection status between the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse includes: For each available warehouse, obtain the space volume of the warehouse that can be used to store the target type of goods , and obtain the average storage time interval of the warehouse , the time interval since the last storage of goods , the average space volume occupied by goods each time they are stored and the time until the peak period of the target type of goods arrives , get the vacancy coefficient, the calculation formula is: , where is the vacancy coefficient; Get the shortest drivable distance from each storage warehouse to the target warehouse and the shortest drivable distance to the transport warehouse management park transport exit , and the transport distance coefficient is obtained. The calculation formula is: , where is the transport distance coefficient, and are preset proportional coefficients of the shortest drivable distance to the target warehouse and the shortest drivable distance to the transport exit of the transport warehouse management park, respectively, and and All are greater than 0; The priority storage index of each storable warehouse is determined according to the vacancy coefficient, transportation distance coefficient, connection status of the corresponding management system and central embedded equipment, and the average of similarity values.

[0008] Optionally, determining the priority storage index of each storable warehouse according to the vacancy coefficient, the transportation distance coefficient, the connection status of the corresponding management system and the central embedded device, and the similarity value average includes: For each storable warehouse, the network connection signal value between the warehouse management system and the central embedded device is obtained at multiple times continuously to obtain a network connection signal value sequence; Calculate the standard deviation of the network connection signal value sequence, and use the standard deviation of the network connection signal value sequence as the network signal connection fluctuation value; Compare each value in the network connection signal value sequence with a preset minimum network connection signal value threshold, and record a value less than the preset minimum network connection signal value threshold as a disconnection signal value; The total number of disconnection signal values ​​in the network connection signal value sequence is divided by the number of all values ​​in the network connection signal value sequence to obtain a network signal disconnection value; The network signal connection fluctuation value and the network signal disconnection value are normalized, and the connection abnormality coefficient between the management system and the central embedded device is obtained according to the normalized network signal connection fluctuation value and the network signal disconnection value; The priority storage index of each storable warehouse is determined according to the vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value average.

[0009] Optionally, determining the priority storage index of each storable warehouse according to the vacancy coefficient, the transportation distance coefficient, the connection anomaly coefficient, and the similarity value mean includes: The vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean are normalized, and the priority storage index of each storable warehouse is obtained according to the normalized vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean. The calculation formula is: , In the formula, To store the index first, , , , They are the vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean after normalization. are the preset proportional coefficients of the normalized vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean, respectively, and Both are greater than 0.

[0010] In a second aspect of the present invention, an automated warehouse management system based on an artificial intelligence embedded host is proposed, the system comprising: Screening module: obtain the storage warehouse corresponding to the target type of goods as the target warehouse, obtain the environmental data of the target warehouse and other remaining warehouses, and screen the remaining warehouses according to the environmental data of the target warehouse and other remaining warehouses to obtain a set of storable warehouses; Priority storage module: for each storable warehouse in the storable warehouse set, obtain the corresponding warehouse vacant space, the distance to the target warehouse, the connection status of the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse; Storage management module: Store the target category of goods in the order of priority storage index from large to small in the centralized storage warehouse of storable warehouses.

[0011] Beneficial effects of the present invention: The present invention proposes an automated warehouse management method and system based on an artificial intelligence embedded host. The method obtains the storage warehouse corresponding to the target type of goods as the target warehouse, obtains the environmental data of the target warehouse and other remaining warehouses, and screens the other remaining warehouses to obtain a set of storable warehouses; for each storable warehouse in the storable warehouse set, the corresponding warehouse vacant space, the distance to the target warehouse, and the connection status of the corresponding management system and the central embedded device are obtained to determine the priority storage index of each storable warehouse; the target type of goods are stored in the storable warehouse set in the order of the priority storage index from large to small. In this way, the target goods can be reasonably stored in other warehouses to ensure that during the peak period of the target goods, the warehouse has sufficient storage capacity to meet the demand, avoid the loss of goods due to improper storage, maximize the reasonable allocation of resources, improve storage efficiency, and reduce potential operational risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The present invention will be further described below in conjunction with the accompanying drawings.

[0013] Figure 1 A flowchart of an automated warehouse management method based on an artificial intelligence embedded host; Figure 2 This is a framework diagram of an automated warehouse management system based on an artificial intelligence embedded host. DETAILED DESCRIPTION

[0014] 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.

[0015] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0016] The embodiment of the present invention provides an automated warehouse management method based on an artificial intelligence embedded host. Figure 1 , Figure 1 A flowchart of an automated warehouse management method based on an artificial intelligence embedded host provided by an embodiment of the present invention. The method comprises the following steps: Obtain the storage warehouse corresponding to the target type of goods as the target warehouse, obtain the environmental data of the target warehouse and the remaining other warehouses, and filter the remaining other warehouses according to the environmental data of the target warehouse and the remaining other warehouses to obtain a set of storable warehouses; For each storable warehouse in the storable warehouse set, obtain the corresponding warehouse vacant space, the distance to the target warehouse, and the connection status between the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse; The target category goods are stored in the centralized warehouse of the storable warehouse in the order of priority storage index from large to small.

[0017] Based on the automated warehouse management method based on artificial intelligence embedded host provided by the embodiment of the present invention, through the above method, the target goods can be reasonably stored in other warehouses to ensure that during the peak period of the target goods, the warehouse has sufficient storage capacity to meet the demand, avoid the loss of goods due to improper storage, maximize the reasonable allocation of resources, improve warehousing efficiency, and reduce potential operational risks.

[0018] In one embodiment, the remaining warehouses are screened according to the environment data of the target warehouse and the remaining warehouses, and the storable warehouse set obtained includes: Each of the remaining warehouses is recorded as a first warehouse, and the environmental data of the target warehouse and the environmental data of the first warehouse within a preset time period are obtained, and the environmental data of the target warehouse and the environmental data of the first warehouse at each moment are preprocessed; Construct a distance matrix, in which each element is the distance between the environmental data point of the target warehouse and the environmental data point of the first warehouse; Using a dynamic programming algorithm to calculate the shortest path in the distance matrix to find the best match between the environmental data sequence of the target warehouse and the environmental data sequence of the first warehouse; According to the calculated shortest path, align the environment data sequence of the target warehouse with the environment data sequence of the first warehouse; Calculate the similarity between the aligned environment data sequence of the target warehouse and the environment data sequence of the first warehouse; and use the calculated similarity as the similarity value of the first warehouse at the corresponding time; The availability status of the corresponding first warehouse is determined according to the similarity value of each first warehouse at each moment in a preset time period, and the storable warehouse set is screened out according to the availability status of the remaining other warehouses.

[0019] It should be noted that the environmental data may include the temperature, humidity, light intensity, air quality, air pressure, ventilation conditions inside the warehouse, and other physical factors that may affect the storage conditions of the goods. These data are collected in real time by corresponding sensors in the warehouse and are used to evaluate the environmental similarity between the two warehouses. The selection of specific environmental data can be determined by professional personnel based on actual conditions and is not limited here. It should be noted that the preset time period is set by professionals. For example, the past half month or one month can be selected as the preset time period to obtain environmental data at each moment. It can also be other times. The specific situation can be determined by professionals according to the actual situation, and no specific limitations or elaboration will be made.

[0020] It should be noted that the similarity between the environmental data sequence of the target warehouse and the environmental data sequence of the first warehouse can be calculated by cumulative distance or similarity measurement to measure the similarity between real-time data and historical data, or other methods, which are not limited or elaborated in detail.

[0021] In one implementation method, the environmental data sequence is aligned through the shortest path, which can handle the misalignment problem in the time series. Even if the environmental data changes of the two warehouses are offset or not completely synchronized in time, dynamic programming can find the best match and more accurately capture the complex changes of environmental data over time, especially in the presence of local differences or asynchronous fluctuations, thereby improving the accuracy of similarity calculation.

[0022] In one embodiment, the availability status of the corresponding first warehouse is determined according to the similarity value of each first warehouse at each moment in a preset time period, and the storage warehouse set is screened out according to the availability status of the remaining other warehouses, including: Sequencing the similarity values ​​of each first warehouse at each moment within a preset time period based on time to obtain a similarity value time series corresponding to the first warehouse; Calculate the similarity value mean and similarity value standard deviation of the similarity value time series of the first warehouse, and compare the similarity value mean with the preset similarity value mean minimum threshold, and compare the similarity value standard deviation with the preset similarity value standard deviation maximum threshold; When the similarity value mean is greater than the preset similarity value mean minimum threshold and the similarity value standard deviation is less than the preset similarity value standard deviation maximum threshold, the availability status of the corresponding first warehouse is recorded as available and recorded as the second warehouse; if not, the availability status of the corresponding first warehouse is recorded as unavailable; All the second warehouses among the remaining warehouses are collected as a storable warehouse set.

[0023] It should be noted that the preset similarity value mean minimum threshold and the preset similarity value standard deviation maximum threshold are set by professionals according to actual conditions, and are not specifically limited or elaborated; It should be noted that by comparing the similarity mean with the preset similarity mean minimum threshold, it is possible to effectively evaluate whether the overall warehouse environment matches the target warehouse. The similarity mean reflects the average similarity between the two warehouses within a preset time period. If the mean is greater than the preset minimum threshold, it means that the environmental conditions of the first warehouse are very close to those of the target warehouse as a whole, and meet the storage requirements of the target type of goods. This comparison ensures that the target goods can obtain a suitable storage environment in the warehouse to avoid affecting the quality of the goods due to inconsistent conditions. At the same time, the similarity standard deviation is compared with the preset similarity standard deviation maximum threshold. The standard deviation reflects the degree of fluctuation of the similarity value within a preset time period. If the standard deviation is less than the preset maximum threshold, it means that the environmental changes in the warehouse are small and relatively stable, and most of the time The similarity values ​​are closer to the similarity average value, indicating that the consistency of the similarity values ​​at different times within the preset time period is high; at the same time, only when the similarity mean is greater than the preset similarity mean minimum threshold and the similarity standard deviation is less than the preset similarity standard deviation maximum threshold, it means that the corresponding first warehouse's available status is the standby status. If not, that is, the similarity mean is not greater than the preset similarity mean minimum threshold and the similarity standard deviation is not less than the preset similarity standard deviation maximum threshold, the similarity mean is greater than the preset similarity mean minimum threshold but the similarity standard deviation is not less than the preset similarity standard deviation maximum threshold, the similarity mean is not greater than the preset similarity mean minimum threshold but the similarity standard deviation is less than the preset similarity standard deviation maximum threshold, it cannot indicate that the first warehouse's available status is the available status, and the corresponding warehouse does not meet the storage requirements of the target type of goods.

[0024] In one implementation, by considering both the mean and standard deviation of similarity values, not only is the average similarity between the overall warehouse environment and the target warehouse (i.e., whether the environmental conditions meet the storage requirements of the target goods) ensured, but also the stability of the environmental conditions (i.e., the magnitude of environmental changes) is evaluated. This dual standard ensures that only warehouses whose environmental conditions are sufficiently similar to those of the target warehouse and whose environmental fluctuations are small are considered available warehouses. This method can effectively filter out warehouses suitable for stable storage of target goods, avoiding adverse effects on the quality of goods due to incompatible or excessively fluctuating environmental conditions.

[0025] In one embodiment, obtaining the corresponding warehouse vacant space, the distance to the target warehouse, and the connection status between the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse includes: For each available warehouse, obtain the space volume of the warehouse that can be used to store the target type of goods , and obtain the average storage time interval of the warehouse , the time interval since the last storage of goods , the average space volume occupied by goods each time they are stored and the time until the peak period of the target type of goods arrives , get the vacancy coefficient, the calculation formula is: , where is the vacancy coefficient; Get the shortest drivable distance from each storage warehouse to the target warehouse and the shortest drivable distance to the transport warehouse management park transport exit , and the transport distance coefficient is obtained. The calculation formula is: , where is the transport distance coefficient, and are preset proportional coefficients of the shortest drivable distance to the target warehouse and the shortest drivable distance to the transport exit of the transport warehouse management park, respectively, and and All are greater than 0; The priority storage index of each storable warehouse is determined according to the vacancy coefficient, transportation distance coefficient, connection status of the corresponding management system and central embedded equipment, and the average of similarity values.

[0026] It should be noted that the space volume available for storing the target type of goods can be obtained through the management system of the corresponding storable warehouse, and the remaining storable space volume of the corresponding storable warehouse can be directly obtained; the average storage time interval of the warehouse, the time interval from the last storage of goods, and the average space volume occupied by the goods each time they are stored can be obtained based on the historical records saved by the management system of the corresponding storable warehouse; the time to the peak period of the target type of goods can be directly obtained through the work plan of the staff; It should be noted that the shortest drivable distance from the storage warehouse to the target warehouse and the shortest drivable distance from the transportation warehouse management park's transportation exit can be obtained directly through the park's topographic map or other methods, which are not specifically limited or elaborated.

[0027] It should be noted that and It is set by professionals according to the actual situation. Generally, and The sum of is 1, for example and They can be 0.4, 0.6, or other numbers respectively, and are not specifically limited.

[0028] It should be noted that the larger the vacancy coefficient, the greater the priority storage of the corresponding storable warehouse. The reason is that a larger vacancy coefficient means that the warehouse has more available storage space, and its historical storage frequency and current load are lower, which indicates that the warehouse has sufficient capacity to carry more target goods in the short term without causing excessive pressure on the warehouse management system. At the same time, a larger vacancy coefficient reflects that the warehouse remains in a good state of availability when approaching the peak period of goods. Therefore, it is suitable as an option for priority storage of target goods, which can effectively reduce storage pressure during peak periods.

[0029] It should be noted that the smaller the transportation distance coefficient is, the greater the storage priority of the corresponding storable warehouse is. The reason is that the smaller the transportation distance coefficient is, the shorter the distance between the warehouse and the target warehouse and the park's transportation exit is, which can significantly shorten the transportation time and improve the efficiency of cargo circulation. In addition, a shorter transportation distance also helps to reduce transportation costs and potential risks in transportation, and the transportation rate of target goods is faster during peak periods, so it is more appropriate to give priority to these warehouses for cargo storage.

[0030] In one embodiment, determining the priority storage index of each storable warehouse according to the vacancy coefficient, the transportation distance coefficient, the connection status of the corresponding management system and the central embedded device, and the similarity value average includes: For each storable warehouse, the network connection signal value between the warehouse management system and the central embedded device is obtained at multiple times continuously to obtain a network connection signal value sequence; Calculate the standard deviation of the network connection signal value sequence, and use the standard deviation of the network connection signal value sequence as the network signal connection fluctuation value; Compare each value in the network connection signal value sequence with a preset minimum network connection signal value threshold, and record a value less than the preset minimum network connection signal value threshold as a disconnection signal value; The total number of disconnection signal values ​​in the network connection signal value sequence is divided by the number of all values ​​in the network connection signal value sequence to obtain a network signal disconnection value; The network signal connection fluctuation value and the network signal disconnection value are normalized, and the connection abnormality coefficient between the management system and the central embedded device is obtained according to the normalized network signal connection fluctuation value and the network signal disconnection value; The priority storage index of each storable warehouse is determined according to the vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value average.

[0031] It should be noted that the preset minimum network connection signal value threshold is set by professionals based on actual conditions, and is not limited or elaborated on in detail; in addition, the network connection signal value between the warehouse management system and the central embedded device can be a WIFI connection signal value, and the network connection signal value between the warehouse management system and the central embedded device can be directly extracted through the recording system of the central embedded device, or it can be other methods, which are not limited or elaborated on in detail.

[0032] It should be noted that the calculation formula for the connection anomaly coefficient between the management system and the central embedded device can be obtained according to the normalized network signal connection fluctuation value and the network signal disconnection value: , where is the connection anomaly coefficient, and are the normalized network signal connection fluctuation value and network signal disconnection value, and are respectively the preset proportional coefficients of the normalized network signal connection fluctuation value and the network signal disconnection value, and and All are greater than 0; It should be noted that and It is set by professionals according to the actual situation. Generally, and The sum of is 1, for example and They can be 0.5, 0.5, or other numbers respectively, and are not specifically limited.

[0033] It should be noted that, when the network signal connection fluctuation value is smaller and the network signal disconnection value is smaller, it means that the connection abnormality coefficient between the management system and the central embedded device is smaller, which means that the corresponding storable warehouse has a greater priority storage degree. The reason is that when the connection abnormality coefficient is smaller, it means that the network connection between the management system and the central embedded device is more stable and the risk of disconnection is lower. This means that in the management and monitoring process of the warehouse, the data transmission is more reliable, and the central embedded device controls the management system of each warehouse to monitor and automatically manage each warehouse more conveniently, and it is not easy to have delays or operation interruptions caused by network instability or disconnection. Therefore, the smaller the connection abnormality coefficient, the higher the reliability of the corresponding storable warehouse in terms of technical infrastructure, and it is suitable as a priority storage warehouse for target goods, which is conducive to ensuring the continuity and efficiency of the target goods management and transportation process.

[0034] In one embodiment, determining the priority storage index of each storable warehouse according to the vacancy coefficient, the transportation distance coefficient, the connection anomaly coefficient, and the similarity value average includes: The vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean are normalized, and the priority storage index of each storable warehouse is obtained according to the normalized vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean. The calculation formula is: , In the formula, To store the index first, , , , They are the vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean after normalization. are the preset proportional coefficients of the normalized vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean, respectively, and Both are greater than 0.

[0035] It should be noted that It is set by professionals according to the actual situation. Generally, The sum of is 1, for example They can be 0.25, 0.25, 0.25, 0.25, or other numbers, without limitation.

[0036] It should be noted that the storable warehouses are sorted in descending order according to the priority storage index, and the target goods are stored in the warehouses with higher priority storage indexes in turn. In this way, the utilization rate of the warehouse can be effectively optimized to ensure that the warehouse has sufficient storage capacity to meet the demand during the peak period of goods, avoiding the loss of goods due to improper storage space or unreasonable allocation. This method helps to maximize the rational allocation of resources, improve warehousing efficiency, and reduce potential operational risks.

[0037] Based on the same inventive concept, the embodiment of the present invention also provides an automated warehouse management system based on an artificial intelligence embedded host. Figure 2 , Figure 2 A schematic diagram of the structure of an automated warehouse management system based on an artificial intelligence embedded host provided by an embodiment of the present invention, the system includes: Screening module: obtain the storage warehouse corresponding to the target type of goods as the target warehouse, obtain the environmental data of the target warehouse and other remaining warehouses, and screen the remaining warehouses according to the environmental data of the target warehouse and other remaining warehouses to obtain a set of storable warehouses; Priority storage module: for each storable warehouse in the storable warehouse set, obtain the corresponding warehouse vacant space, the distance to the target warehouse, the connection status of the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse; Storage management module: Store the target category of goods in the order of priority storage index from large to small in the centralized storage warehouse of storable warehouses.

[0038] Based on the automated warehouse management system based on artificial intelligence embedded host provided by the embodiment of the present invention, the target goods can be reasonably stored in other warehouses through the above method, ensuring that during the peak period of the target goods, the warehouse has sufficient storage capacity to meet the demand, avoiding the loss of goods due to improper storage, maximizing the reasonable allocation of resources, improving warehousing efficiency, and reducing potential operational risks.

[0039] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An automated warehouse management method based on an artificial intelligence embedded host, characterized in that: The following steps are involved: Obtain the storage warehouse corresponding to the target type of goods as the target warehouse, obtain the environmental data of the target warehouse and the remaining other warehouses, and filter the remaining other warehouses according to the environmental data of the target warehouse and the remaining other warehouses to obtain a set of storable warehouses; For each storable warehouse in the storable warehouse set, obtain the corresponding warehouse vacant space, the distance to the target warehouse, and the connection status between the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse; The target category goods are stored in the centralized warehouse of the storable warehouse in the order of priority storage index from large to small.

2. The automated warehouse management method based on artificial intelligence embedded host according to claim 1 is characterized in that: The remaining warehouses are screened according to the environment data of the target warehouse and the remaining warehouses, and the set of warehouses that can be stored includes: Each of the remaining warehouses is recorded as a first warehouse, and the environmental data of the target warehouse and the environmental data of the first warehouse within a preset time period are obtained, and the environmental data of the target warehouse and the environmental data of the first warehouse at each moment are preprocessed; Construct a distance matrix, in which each element is the distance between the environmental data point of the target warehouse and the environmental data point of the first warehouse; Using a dynamic programming algorithm to calculate the shortest path in the distance matrix to find the best match between the environmental data sequence of the target warehouse and the environmental data sequence of the first warehouse; According to the calculated shortest path, align the environment data sequence of the target warehouse with the environment data sequence of the first warehouse; Calculate the similarity between the aligned environment data sequence of the target warehouse and the environment data sequence of the first warehouse; and use the calculated similarity as the similarity value of the first warehouse at the corresponding time; The availability status of the corresponding first warehouse is determined according to the similarity value of each first warehouse at each moment in a preset time period, and the storable warehouse set is screened out according to the availability status of the remaining other warehouses.

3. The automated warehouse management method based on artificial intelligence embedded host according to claim 2 is characterized in that: The availability status of the corresponding first warehouse is determined according to the similarity value of each first warehouse at each moment in the preset time period, and the storage warehouse set is screened out according to the availability status of the remaining other warehouses, including: Sequencing the similarity values ​​of each first warehouse at each moment within a preset time period based on time to obtain a similarity value time series corresponding to the first warehouse; Calculate the similarity value mean and similarity value standard deviation of the similarity value time series of the first warehouse, and compare the similarity value mean with the preset similarity value mean minimum threshold, and compare the similarity value standard deviation with the preset similarity value standard deviation maximum threshold; When the similarity value mean is greater than the preset similarity value mean minimum threshold and the similarity value standard deviation is less than the preset similarity value standard deviation maximum threshold, the availability status of the corresponding first warehouse is recorded as available and recorded as the second warehouse; if not, the availability status of the corresponding first warehouse is recorded as unavailable; All the second warehouses among the remaining warehouses are collected as a storable warehouse set.

4. The automated warehouse management method based on artificial intelligence embedded host according to claim 1 is characterized in that: Obtaining the corresponding warehouse vacant space, the distance to the target warehouse, and the connection status between the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse includes: For each available warehouse, obtain the space volume of the warehouse that can be used to store the target type of goods , and obtain the average storage time interval of the warehouse , the time interval since the last storage of goods , the average space volume occupied by goods each time they are stored and the time until the peak period of the target type of goods arrives , get the vacancy coefficient, the calculation formula is: , where is the vacancy coefficient; Get the shortest drivable distance from each storage warehouse to the target warehouse and the shortest drivable distance to the transport warehouse management park transport exit , and the transport distance coefficient is obtained. The calculation formula is: , where is the transport distance coefficient, and are preset proportional coefficients of the shortest drivable distance to the target warehouse and the shortest drivable distance to the transport exit of the transport warehouse management park, respectively, and and All are greater than 0; The priority storage index of each storable warehouse is determined according to the vacancy coefficient, transportation distance coefficient, connection status of the corresponding management system and central embedded equipment, and the average of similarity values.

5. The automated warehouse management method based on artificial intelligence embedded host according to claim 4 is characterized in that: The priority storage index of each storable warehouse is determined based on the vacancy coefficient, transportation distance coefficient, connection status of the corresponding management system and central embedded equipment, and the average of similarity values, including: For each storable warehouse, the network connection signal value between the warehouse management system and the central embedded device is obtained at multiple times continuously to obtain a network connection signal value sequence; Calculate the standard deviation of the network connection signal value sequence, and use the standard deviation of the network connection signal value sequence as the network signal connection fluctuation value; Compare each value in the network connection signal value sequence with a preset minimum network connection signal value threshold, and record a value less than the preset minimum network connection signal value threshold as a disconnection signal value; The total number of disconnection signal values ​​in the network connection signal value sequence is divided by the number of all values ​​in the network connection signal value sequence to obtain a network signal disconnection value; The network signal connection fluctuation value and the network signal disconnection value are normalized, and the connection abnormality coefficient between the management system and the central embedded device is obtained according to the normalized network signal connection fluctuation value and the network signal disconnection value; The priority storage index of each storable warehouse is determined according to the vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value average.

6. The automated warehouse management method based on artificial intelligence embedded host according to claim 5 is characterized in that: The priority storage index of each storable warehouse is determined based on the vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value average, including: The vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean are normalized, and the priority storage index of each storable warehouse is obtained according to the normalized vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean. The calculation formula is: ， In the formula, To store the index first, , , , They are the vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean after normalization. are the preset proportional coefficients of the normalized vacancy coefficient, transportation distance coefficient, connection anomaly coefficient and similarity value mean, respectively, and Both are greater than 0.

7. An automated warehouse management system based on artificial intelligence embedded host, characterized in that: The system comprises: Screening module: obtain the storage warehouse corresponding to the target type of goods as the target warehouse, obtain the environmental data of the target warehouse and other remaining warehouses, and screen the remaining warehouses according to the environmental data of the target warehouse and other remaining warehouses to obtain a set of storable warehouses; Priority storage module: for each storable warehouse in the storable warehouse set, obtain the corresponding warehouse vacant space, the distance to the target warehouse, the connection status of the corresponding management system and the central embedded device to determine the priority storage index of each storable warehouse; Storage management module: Store the target category of goods in the order of priority storage index from large to small in the centralized storage warehouse of storable warehouses.

Images