Smart factory warehouse management method and system based on big data

Abstract

The invention discloses a smart factory warehouse management method and system based on big data, and the method comprises the steps: determining the dynamic position distribution of cargos and calculating the taking frequency fluctuation of the cargos, so as to quantify the demand change trend of the cargos; according to the quantized value of the demand change trend of the goods, the goods are divided into high-frequency goods and low-frequency goods, so that the area range of optimized storage of the high-frequency goods is determined; and determining a layout scheme of a storage position and a conflict-free optimal goods taking path sequence through an optimized storage area range of the high-frequency goods, thereby obtaining an optimized resource allocation scheme. The method can improve the efficiency and flexibility of the warehousing system.

Description

Technical Field

[0001] The present application relates to the technical field of smart factory warehouse management, and in particular to a smart factory warehouse management method and system based on big data. Background Art

[0002] Smart factory warehouse management, a key area for improving supply chain efficiency and corporate competitiveness, is gaining increasing attention. Its core focus is on visualizing and optimizing the scheduling of goods throughout their entire lifecycle through data-driven approaches, significantly reducing operating costs and improving responsiveness. However, traditional warehouse management methods are increasingly limited in the face of increasingly complex production demands. These methods often rely on static storage plans and manual experience, making them difficult to adapt to dynamic market demands and failing to fully leverage real-time data to optimize goods layout and retrieval efficiency. This results in warehouse systems with both limited efficiency and flexibility, particularly in balancing rapid response times for high-frequency goods with the appropriate storage of low-frequency goods. Summary of the Invention

[0003] This application provides a smart factory warehousing management method and system based on big data to improve the efficiency and flexibility of the warehousing system.

[0004] First, in order to solve the above technical problems, this application provides a smart factory warehouse management method based on big data, including: Each piece of cargo is assigned an identification code through RFID technology, and the cargo is bound to a collection device equipped with a sensor to obtain the initial location data of the cargo at the warehouse entrance and record it in the database, thereby obtaining a preliminary location map; Based on the preliminary location mapping, the movement trajectory of the goods from the warehouse to the storage point is analyzed by a positioning algorithm combined with multi-point sensor data to calculate the path node density, thereby determining the current dynamic location distribution of the goods; Based on the dynamic location distribution, historical pickup data within a classified time window is integrated using time series processing technology to calculate the pickup frequency fluctuation, thereby obtaining a quantitative value of the demand change trend of the goods; determining whether the quantified value of the demand change trend exceeds a frequency threshold, and if the quantified value of the demand change trend exceeds the frequency threshold, classifying the goods into high-frequency and low-frequency categories by combining a clustering algorithm with frequency fluctuations and cargo volume parameters, thereby determining an optimized storage area for high-frequency goods; According to the optimized storage area of ​​the high-frequency goods, the coding-related data is obtained through the goods identification and integrated into the dynamic storage to obtain the adjustment requirements of the storage location; According to the adjustment requirements of the storage locations, the storage locations are replanned by dividing the granularity by area using a simulated annealing algorithm and combining the cargo volume parameters to obtain an adjusted layout plan; Based on the adjusted layout plan, the A-star algorithm is used to combine the path node density and real-time speed collection to generate the pickup path, and the path intersection probability and conflict range are detected at the same time to obtain the conflict-free optimal pickup path sequence; Instructing the handling equipment to perform the pickup operation according to the optimal pickup path sequence, and obtaining real-time speed data and the location coordinates of dynamic obstacles from the operation log to determine the accuracy of the path intersection probability detection and update the conflict detection range; The path length change is analyzed according to the updated conflict detection range, and the storage layout is adjusted by using frequency fluctuations and dynamic obstacle coordinates to obtain an optimized resource allocation solution.

[0005] In a second aspect, the present application provides a storage medium storing computer program data, which, when executed, can implement any of the above-mentioned smart factory warehouse management methods based on big data.

[0006] In a third aspect, this application provides a smart factory warehouse management system based on big data, including: A preliminary location mapping module is used to assign an identification code to each piece of goods using RFID technology, and to obtain the initial location data of the goods at the warehouse entrance by binding the goods to a collection device equipped with a sensor and recording it in a database, thereby obtaining a preliminary location map; a dynamic location distribution determination module, configured to analyze the movement trajectory of the goods from the warehouse entry to the storage point using a positioning algorithm combined with multi-point sensor data based on the preliminary location mapping to calculate the path node density, thereby determining the current dynamic location distribution of the goods; a module for obtaining a quantitative value of a demand change trend, for fusing historical pickup data within a classified time window using time series processing technology based on the dynamic location distribution to calculate pickup frequency fluctuations, thereby obtaining a quantitative value of the demand change trend of the goods; A module for determining the optimal storage area for high-frequency goods is configured to determine whether the quantified value of the demand change trend exceeds a frequency threshold, and when the quantified value of the demand change trend exceeds the frequency threshold, classify the goods into high-frequency and low-frequency categories by combining a clustering algorithm with frequency fluctuations and cargo volume parameters, thereby determining the optimal storage area for high-frequency goods. A storage location adjustment demand acquisition module is used to obtain coded associated data through cargo identification according to the optimized storage area of ​​the high-frequency cargo and integrate it into dynamic storage to obtain storage location adjustment requirements; An adjusted layout plan acquisition module is used to re-plan the storage locations by dividing the granularity by area using a simulated annealing algorithm and combining the cargo volume parameters according to the adjustment requirements of the storage locations, so as to obtain an adjusted layout plan; A conflict-free optimal pickup path sequence acquisition module is used to generate pickup paths based on the adjusted layout plan using the A-star algorithm combined with path node density and real-time speed collection, while simultaneously detecting path intersection probability and conflict range to obtain a conflict-free optimal pickup path sequence; a conflict detection range update module, configured to guide the handling equipment to perform a pickup operation according to the optimal pickup path sequence, and obtain real-time speed data and the position coordinates of dynamic obstacles from the operation log to determine the accuracy of the path intersection probability detection and update the conflict detection range; The optimized resource allocation scheme acquisition module is used to analyze the path length change according to the updated conflict detection range and adjust the storage layout by using frequency fluctuations and dynamic obstacle coordinates to obtain the optimized resource allocation scheme.

[0007] Compared with the existing technology, the present application has at least the following beneficial effects: by determining the dynamic location distribution of goods and calculating the fluctuations in the frequency of goods retrieval, the demand change trend of goods can be quantified; further, through the quantified value of the demand change trend of goods, the goods are divided into high-frequency and low-frequency categories to determine the area range for optimized storage of high-frequency goods; further, through the area range for optimized storage of high-frequency goods, the layout plan of the storage location and the conflict-free optimal retrieval path sequence are determined, thereby obtaining an optimized resource allocation plan, thereby improving the efficiency and flexibility of the warehousing system. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a flowchart of a smart factory warehouse management method based on big data provided by the first embodiment of the present application; Figure 2 This is a structural diagram of the smart factory warehouse management system based on big data provided in the second embodiment of this application. DETAILED DESCRIPTION

[0009] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0010] Reference Figure 1 The first embodiment of the present application provides a smart factory warehouse management method based on big data, comprising the following steps: S101: Using RFID technology to assign an identification code to each piece of goods, and by binding the goods to a collection device equipped with a sensor, the initial location data of the goods is obtained at the warehouse entrance and recorded in a database, thereby obtaining a preliminary location map; S102: Based on the preliminary location mapping, the movement trajectory of the goods from the warehouse to the storage point is analyzed by combining the positioning algorithm with the multi-point sensor data to calculate the path node density, thereby determining the current dynamic location distribution of the goods; S103: Based on the dynamic location distribution, the historical pickup data within the classification time window is integrated using time series processing technology to calculate the pickup frequency fluctuation, thereby obtaining a quantitative value of the demand change trend of the goods; S104: Determine whether the quantified value of the demand change trend exceeds the access frequency threshold. If the quantified value of the demand change trend exceeds the access frequency threshold, use a clustering algorithm to combine access frequency fluctuations and cargo volume parameters to classify the cargo into high-frequency and low-frequency categories, thereby determining an optimized storage area for high-frequency cargo. S105: Based on the optimized storage area of ​​high-frequency goods, the coded associated data is obtained through the goods identification and integrated into the dynamic storage to obtain the storage location adjustment requirements; S106: Based on the storage location adjustment requirements, the storage locations are replanned by dividing the granularity by region using a simulated annealing algorithm and combining the cargo volume parameters to obtain an adjusted layout plan; S107: Based on the adjusted layout plan, a pickup route is generated by combining the node density and real-time speed data with the A-star algorithm. The path intersection probability and conflict range are also detected to obtain a conflict-free optimal pickup route sequence. S108: Instructing the handling equipment to perform the picking operation according to the optimal picking path sequence, and obtaining real-time speed data and the location coordinates of dynamic obstacles from the operation log to determine the accuracy of the path intersection probability detection and update the conflict detection range; S109: Analyze the change in path length according to the updated conflict detection range, and adjust the storage layout by using frequency fluctuations and dynamic obstacle coordinates to obtain an optimized resource allocation solution.

[0011] In step S101, each piece of cargo is assigned an identification code through RFID technology, and the cargo is bound to a collection device equipped with a sensor to obtain the initial location data of the cargo at the warehouse entrance and record it in the database, thereby obtaining a preliminary location map.

[0012] Using sensors and RFID technology, cargo identification is generated and bound to a collection device. Initial location data is obtained from the warehouse entrance and entered into a database to generate a preliminary location map. The binding relationship between location information and the collection device is used to determine whether the cargo identification matches the initial location. If so, the location map is updated based on the database records. After obtaining the updated location map, position information deviations are detected using precision constraints. If the deviation exceeds a preset threshold, the collection device data is clustered using the K-means algorithm to identify anomalous locations. Based on these anomalous locations, the corresponding cargo identification is extracted from the database records. RFID technology is used to verify the matching between the cargo identification and location information, generating corrected location data. Using this corrected location data, sensor technology is used to obtain real-time location information, and its consistency with the database records is determined. If not, the database records are updated and a new location map is generated.

[0013] Specifically, generating cargo identification through sensors and RFID technology and binding it to collection devices is the basis for achieving cargo tracking in modern warehouse management.

[0014] For example, in a large logistics warehouse, each item is uniquely identified by an RFID tag upon entry, such as "Item A-001." This unique identifier is then linked to a sensor-equipped data collection device. This device can be a reader / writer fixed to a shelf or a mobile handheld terminal. Initial location data is obtained at the warehouse entrance—for example, item A-001 is recorded at "Shelf 1, Area A, Position 01"—and entered into a database, creating a preliminary location mapping. This step ensures a preliminary association between the item and its location, laying the foundation for subsequent tracking.

[0015] In a possible implementation, the binding relationship between the location information and the collection device is used to determine whether the cargo identification is consistent with the initial location.

[0016] Specifically, if the data collection device for item A-001 continuously reports the location as "Shelf 1, Area A, Position 01," which is consistent with the database record, the location mapping is updated in the database to maintain real-time data. This consistency verification effectively reduces location errors caused by human error and improves inventory management accuracy. After obtaining the updated location mapping, position information deviations are detected using precision constraints.

[0017] For example, if you set a preset threshold, such as a position deviation of no more than 50 cm, and the location information of item A-001 is displayed as "Shelf 1, Area A, Position 02," and the deviation exceeds the threshold, it indicates a possible anomaly.

[0018] Preferably, a K-means algorithm is used to perform cluster analysis on data from collection devices. For example, location data from multiple collection devices within a warehouse is divided into three categories. One category is concentrated around "Shelf 1, Area A, Position 02," indicating an anomalous location. This clustering method quickly locates problem areas through data grouping, improving anomaly detection efficiency. Based on the anomalous location, the corresponding item identifier (for example, item A-001) is extracted from the database, and RFID technology is used to verify its match with the location information.

[0019] For example, if an RFID scan shows that item A-001 is actually located at "Shelf 1, Area A, Position 02" instead of the initially recorded "Position 01," the corrected location data is based on the most recent scan result. This verification method leverages RFID's high precision to ensure the reliability of location data and avoid confusion caused by position drift. This corrected location data, combined with sensor technology, provides real-time location information.

[0020] For example, the sensor updates the location of item A-001 every 5 minutes. If it displays "Shelf 1, Area A, Position 02," it is consistent with the corrected data and no further action is required. If it displays "Shelf 1, Area B, Position 01," it indicates that the item has been moved, requiring the database to be updated and a new location map to be generated.

[0021] It is understandable that this real-time update mechanism can promptly reflect the actual dynamics of goods, making it easier for managers to quickly respond to inventory changes.

[0022] It should be noted that the above process realizes closed-loop management from cargo identification generation to location mapping update through the collaborative work of sensors and RFID.

[0023] In one embodiment, assuming a warehouse processes 1,000 pieces of goods per day, deviation detection and anomaly localization can reduce the location error rate from 5% to 1%, significantly improving warehousing efficiency.

[0024] For example, managers can quickly identify unusual goods through system reports and adjust the layout, reducing the time spent searching for goods. This technology not only optimizes operational processes but also provides data support for large-scale warehousing, enhancing overall management capabilities.

[0025] In step S102, based on the preliminary location mapping, the movement trajectory of the goods from the warehouse to the storage point is analyzed by the positioning algorithm combined with multi-point sensor data to calculate the path node density, thereby determining the current dynamic location distribution of the goods. After that, the following steps are also included: S1021: Verify the matching status between the location distribution of the goods and the storage points through multi-point analysis; Specifically, fusing sensor data through positioning algorithms and analyzing the movement trajectory of goods from entering the warehouse to the storage point can be understood as a method based on multi-source data integration.

[0026] For example, in a large storage center, after the goods enter from the entrance, the sensor will continuously record its location information. For example, the infrared sensor captures the coordinate points where the goods pass, combines the identification data read by RFID, and generates a complete moving path through the positioning algorithm.

[0027] For example, the path of cargo B-002 from the entrance to Shelf 2, Area B, Position 03 might include four nodes: Entrance, Aisle 1, Transfer Area, and Shelf 2, with a path length of approximately 20 meters. Node density data is extracted from the node distribution along the path, and statistical tools are used to calculate density variation patterns to reveal concentrated areas of cargo movement.

[0028] Specifically, suppose 500 pieces of cargo pass through Channel 1 in a single day, representing a high node density, while only 100 pieces pass through the transit area, representing a lower density. Using statistical tools such as mean analysis, we can see that the density in Channel 1 varies steadily, while the density in the transit area fluctuates significantly, which helps infer the current dynamic location of the cargo.

[0029] For example, if cargo B-002 remains in the transit area, this may indicate that its movement is not yet complete. After obtaining the dynamic location, multi-point analysis is performed to verify the matching status between the location distribution and the storage points to determine if there are any deviations.

[0030] S1022: Determine whether there is a deviation between the location distribution and the storage points; if there is a deviation, cluster the sensor data using the K-means algorithm to obtain an abnormal node set; In one possible implementation, the system compares the real-time location of item B-002, in the "transfer area," with its target storage location, Shelf 2, Area B, Location 03. Any discrepancies indicate that the item did not arrive as expected.

[0031] Preferably, multi-point analysis can utilize data from multiple sensors, such as readers at the entrance and on the shelves, to comprehensively determine the degree of location matching. If deviations exist, the sensor data is clustered using the K-means algorithm to obtain a set of abnormal nodes.

[0032] For example, suppose data from 100 sensors in a warehouse is categorized into three groups. One group shows that goods have strayed to "Shelf 1, Area C," more than 5 meters from their intended storage location. This data constitutes an abnormal node cluster. This clustering method can quickly pinpoint the problem area.

[0033] S1023: Extract corresponding moving trajectory segments from the trajectory analysis based on the abnormal node set to determine the time range of the abnormality occurrence; According to the set of abnormal nodes, the corresponding moving trajectory segments are extracted from the trajectory analysis to determine the time range of the abnormality.

[0034] For example, if the trajectory of cargo B-002 shows that it enters the transfer area from channel 1 at 10:00 am, but after 10:30 it abnormally appears in the location "Shelf 1 - Area C", then the abnormal time range is 10:00 to 10:30.

[0035] It should be noted that this time range extraction can help trace the cause of the problem, such as manual handling errors.

[0036] S1024: Correcting the dynamic position using the sensor data within the time range of the anomaly occurrence in combination with the positioning algorithm to obtain an adjusted location distribution of the cargo; The dynamic position is corrected by combining the sensor data within the time range with the positioning algorithm to obtain the adjusted position distribution.

[0037] In one example, the system analyzed sensor data from 10:00 AM to 10:30 AM and discovered that item B-002 had been mistakenly placed in "Shelf 1, Section C." The algorithm then adjusted its location to the actual scanning point, "Shelf 2, Section B, Position 03." This correction ensures data accuracy.

[0038] S1025: Based on the adjusted location distribution, the current dynamic location distribution of the goods is updated by comparing the storage point data.

[0039] Obtain the adjusted location distribution, compare it with the storage point data, and update the current dynamic location record of the goods.

[0040] For example, the cargo B-002 originally recorded in the database as "transit area" is now updated to "Shelf No. 2 - Area B - Position 03".

[0041] It is understandable that this real-time update mechanism can reflect the status of goods in a timely manner and facilitate subsequent management.

[0042] In step S103, based on the dynamic location distribution, the historical pickup data within the classified time window is integrated using time series processing technology to calculate the pickup frequency fluctuation, thereby obtaining a quantitative value of the demand trend of the goods, including the following steps: S1031: Extracting the storage location information of the goods based on the dynamic location distribution to create a location index table; Specifically, the process of extracting cargo storage location information and establishing a location index table based on dynamic location distribution data can be understood as a systematic data organization method.

[0043] For example, in a large storage center, the cargo storage location information may include specific coordinates such as "Shelf No. 2 - Area B - Position 03". By analyzing the dynamic location distribution data, the system will summarize the current locations of all cargoes to form an index table containing location numbers and cargo identifications.

[0044] For example, item B-002 corresponds to "Shelf 2, Area B, Position 03," and item C-005 corresponds to "Shelf 3, Area A, Position 01." This index table makes it easy to quickly find the location of items.

[0045] S1032: Using a sliding time window method, obtain the pickup records within a specified time range from the historical database, and calculate the pickup frequency value corresponding to each location in the location index table using a frequency analysis algorithm; Using the sliding time window method to obtain the pickup records within a specified time range from the historical database is a dynamic analysis method.

[0046] Specifically, assuming a 24-hour time window, the system extracts all pickup records from the database for the past day, such as item B-002 picked up at 10:00 AM and item C-005 picked up at 2:00 PM. Using a sliding window, the time range can be gradually shifted forward, continuously updating the data. This approach captures the temporal characteristics of pickup behavior. Using a frequency analysis algorithm, the frequency of pickups corresponding to each location index is calculated to quantify the activity level of each location.

[0047] S1033: Determine whether the access frequency value exceeds a preset threshold. If the access frequency value exceeds the preset threshold, mark the location as a high-frequency access area. In one possible implementation, the system calculates the frequency of access to Shelf 2, Section B, Position 03, five times within 24 hours, and Shelf 3, Section A, Position 01, twice. If the preset threshold is four times, then Shelf 2, Section B, Position 03 exceeds the threshold and is marked as a frequently accessed area.

[0048] It should be noted that this type of marking can highlight areas with frequent operations, facilitating optimized management.

[0049] S1034: Based on the distribution of high-frequency access areas, use cluster analysis to divide the storage areas of goods; Based on the distribution of high-frequency access areas, the cluster analysis method is used to divide the cargo storage area, which can realize spatial zoning management.

[0050] Preferably, assuming there are 10 high-frequency access locations in the warehouse, cluster analysis may divide them into three areas: area A near the entrance, area B in the middle aisle, and area C in the deep shelves.

[0051] For example, Area A includes "Rack 2 - Area B" because it is frequently used and located in a concentrated area. This division helps to rationally plan the storage layout.

[0052] S1035: Using time series processing technology, perform a volatility analysis on the access frequency of each storage area, and use a regression model to quantify the demand change trend based on the results of the volatility analysis to obtain a quantitative value of the demand change trend of the goods.

[0053] By using time series processing technology to conduct a fluctuation analysis of the access frequency in each area, the regularity of the access pattern can be revealed.

[0054] In one embodiment, the system analyzed the usage frequency of area A over the past seven days and found that usage on Mondays and Fridays fluctuated significantly, with 8 and 10 visits, respectively, while on Wednesdays, there were only 3 visits. This volatility analysis can reflect the temporal characteristics of demand changes. Based on the volatility analysis results, a regression model is used to quantify demand trends and generate trend forecasts, which is a forward-looking analytical tool.

[0055] For example, based on seven days of data from region A, the regression model predicts that the frequency of withdrawals may increase to 12 times over the next three days. This forecast can provide a basis for inventory adjustments.

[0056] It is understandable that accurate trend forecasting helps to prepare resources in advance and improve efficiency.

[0057] In step S104, it is determined whether the quantified value of the demand change trend exceeds the access frequency threshold. If the quantified value of the demand change trend exceeds the access frequency threshold, a clustering algorithm is used to combine the access frequency fluctuation and the cargo volume parameter to classify the cargo into high-frequency and low-frequency categories, thereby determining the optimal storage area for high-frequency cargo. The steps include: S1041: Obtaining a quantitative value of the demand change trend and usage frequency data from historical usage records, and determining whether the quantitative value exceeds a preset usage frequency threshold to obtain an over-threshold flag; Specifically, obtaining quantitative values ​​of demand changes and usage frequency data through historical usage records can be understood as a data-based dynamic evaluation method.

[0058] Specifically, the system extracts the past 30 days' worth of pickup records from the warehouse database. For example, if item A-001 is picked up three times per day and item B-002 is picked up eight times per day, these records are quantified. A preset frequency threshold of five times is set for pickup frequency. Item B-002 exceeds this threshold and is marked as exceeding the threshold, while item A-001 does not. This clear logic allows for rapid screening of active items.

[0059] S1042: Extract frequency fluctuation data based on the over-threshold markers, integrate the volume parameters of the goods, and use a clustering algorithm to divide high-frequency goods into low-frequency goods to determine the classification results; For example, frequency fluctuation data is extracted based on the over-threshold markers and fused with cargo volume parameters, and a clustering algorithm is used to divide high-frequency and low-frequency cargoes.

[0060] In one possible implementation, cargo B-002 is retrieved between 6 and 10 times a day and has a volume of 0.5 cubic meters. Cargo C-003 is retrieved between 1 and 3 times and has a volume of 1.2 cubic meters. The clustering algorithm combines frequency and volume to classify B-002 as a high-frequency cargo and C-003 as a low-frequency cargo. This classification not only considers access activity but also differences in space occupancy.

[0061] S1043: For high-frequency goods in the classification results, calculate the fluctuation amplitude through frequency fluctuation analysis to obtain the priority ranking of high-frequency goods; Frequency fluctuation analysis of high-frequency goods is carried out and the fluctuation amplitude is calculated to determine the priority ranking.

[0062] For example, over the past seven days, B-002 was accessed 8, 10, 6, 9, 7, 8, and 10 times, showing significant fluctuations, indicating unstable but generally high demand. Another high-frequency item, D-004, was accessed 7, 8, 7, 7, 8, 7, and 8 times, showing less fluctuation and stability. In the priority ranking, B-002 takes first place due to its high frequency and significant fluctuations, followed by D-004. This ranking method highlights the urgency of demand and facilitates prioritization.

[0063] S1044: Calculate the area division granularity by combining the priority sorting with the volume parameters of the goods to determine the area range for optimized storage of high-frequency goods.

[0064] Preferably, the area division granularity is calculated in combination with the priority sorting and cargo volume data to determine the optimized storage range.

[0065] In one embodiment, B-002 is smaller but has a higher priority, suitable for Area X near the entrance, occupying 0.5 square meters. D-004, with a volume of 0.8 cubic meters and a slightly lower priority, is assigned to Area Y near the aisle, occupying 1 square meter. The granularity of area division is adjusted based on the characteristics of the goods. For example, Area X at the entrance is limited to a total occupancy of 2 square meters to ensure that frequently used goods are stored centrally. This approach improves access efficiency.

[0066] It should be noted that the clustering of fused volume parameters can avoid the imbalance of spatial distribution caused by relying solely on frequency.

[0067] For example, if we only consider frequency, the large C-003 may occupy the space of high-frequency, small-volume goods, affecting operational smoothness. After adding the volume dimension, the classification is more reasonable.

[0068] It is understandable that fluctuation analysis provides a basis for prioritization and makes resource allocation more accurate.

[0069] In one possible implementation, after high-frequency goods are concentrated in area X, the pickup time is shortened from 5 minutes to 3 minutes, significantly improving efficiency.

[0070] Specifically, the storage range can be optimized and adjusted according to the warehouse layout.

[0071] For example, Area X is located near the forklift access, making it suitable for quick handling; Area Y is located near the packaging area, facilitating the connection to subsequent processes. This zoning logic fully utilizes spatial characteristics and enhances operational continuity.

[0072] For example, if a warehouse handles 500 pieces of goods per day, after centralized optimization of high-frequency goods, the overall process time can be reduced by 10%, which is a significant effect.

[0073] In step S105, based on the optimized storage area of ​​high-frequency goods, the coded associated data is obtained through the goods identification and integrated into the dynamic storage to obtain the adjustment requirements of the storage location; Obtain code-related data from cargo identification, integrate it with dynamic storage information, and determine the initial layout plan. Use code-related data to analyze dynamic storage change trends and determine storage location adjustment requirements.

[0074] Specifically, the coding-related data is obtained through cargo identification, and the dynamic storage information is integrated to determine the initial layout plan.

[0075] It is understandable that cargo identifications such as A-001 and B-002 usually correspond to unique codes, and the code-related data includes information such as cargo type and warehousing time.

[0076] For example, the code for A-001 indicates a small part that has been stored three times in the past 30 days, while B-002, a fast-moving consumer product, has been stored ten times. After integrating dynamic storage information, the initial layout plan temporarily stores A-001 at the back and B-002 near the entrance and exit, reflecting their different activity levels. Using code-related data, we analyze dynamic storage trends and identify storage location adjustments.

[0077] In step S106, based on the storage location adjustment requirements, the storage locations are replanned by using a simulated annealing algorithm based on the regional granularity and in combination with the cargo volume parameters to obtain an adjusted layout plan, which includes the following steps: S1061: extracting the area division granularity based on the storage location adjustment requirement and combining the layout information; Specifically, the system tracked an increase in the frequency of B-002's arrivals from 5 to 10 times per week, indicating increased demand and a need for relocation to a more convenient location. Meanwhile, A-001's performance remained stable, and no relocation was currently required. This trend analysis relies on historical data to highlight the dynamic nature of cargo. Based on the adjustment requirements and combined with layout information, regional division data was extracted to determine whether the division granularity met storage requirements.

[0078] For example, the warehouse is divided into entry zone X and back-end zone Y, with an initial granularity of 5 square meters per zone. B-002 requires 2 square meters to enter entry zone X, but if the number of high-frequency goods increases, 5 square meters may not be enough.

[0079] S1062: Determine whether the region division granularity meets the storage requirement. If the region division granularity does not meet the storage requirement, adjust the region division granularity using a simulated annealing algorithm to obtain an optimized division result. It should be noted that if it is not satisfied, the partitioning granularity is adjusted through the simulated annealing algorithm.

[0080] In one possible implementation, the algorithm simulates multiple partitions and concludes that the entrance area X is expanded to 8 square meters to ensure that the capacity matches the demand.

[0081] S1063: Based on the optimized division results, obtain the volume parameters of the goods to determine a preliminary layout plan for the storage locations; Based on the optimized division results, obtain cargo volume data and determine the preliminary allocation plan for storage locations.

[0082] For example, B-002 has a volume of 0.5 cubic meters and is assigned to the front of Zone X; C-003 has a volume of 1.2 cubic meters and is assigned to Zone Y despite its low frequency and large volume. This allocation takes into account both space utilization efficiency and the environment.

[0083] S1064: The position parameters are integrated through the preliminary layout plan, and the storage position is recalculated using a simulated annealing algorithm to obtain an adjusted layout plan.

[0084] The position parameters are integrated through the preliminary allocation scheme, and the storage positions are recalculated using the simulated annealing algorithm to obtain the adjusted position layout.

[0085] Optimally, the positioning parameters include the distance from the aisle, adjusting B-002 to 1 meter from the entrance, and moving C-003 to the wall in area Y. The algorithm optimizes the spatial distribution of goods through multiple iterations, improving handling convenience.

[0086] In step S106, based on the storage location adjustment requirements, the storage locations are replanned by using a simulated annealing algorithm based on the regional granularity and in combination with the cargo volume parameters to obtain an adjusted layout plan. The following steps are then included: S1065: Analyze the matching degree of the coded association data according to the adjusted layout scheme; S1066: Determine whether the matching degree is lower than a preset threshold. If the matching degree is lower than the preset threshold, readjust the layout information by dynamically storing data to determine a final optimized layout solution.

[0087] The matching degree of the coded associated data is analyzed according to the adjusted position layout. If the matching degree is lower than a preset threshold, the layout information is readjusted by dynamically storing the data.

[0088] For example, the preset matching degree is 80%, and the B-002 code shows that it needs to be close to the forklift lane, but the current layout is remote and the matching degree is only 60%.

[0089] In one embodiment, based on the latest incoming inventory data, the system moves B-002 to the forklift lane, increasing the matching degree to 85%, and determines the final layout. The system then obtains the cargo identification and storage location data from the final optimized layout plan and generates a complete, adjusted layout plan.

[0090] Specifically, the plan lists A-001 at position 3 in area Y, B-002 at position 1 in area X, and so on. This plan ensures that cargo locations are highly aligned with dynamic demand, facilitating rapid response to operational needs.

[0091] In step S107, based on the adjusted layout plan, the A-star algorithm is used to combine the path node density and real-time speed collection to generate the pickup path. At the same time, the path intersection probability and conflict range are detected to obtain the conflict-free optimal pickup path sequence, which includes the following steps: S1071: Obtain path node distribution data based on the adjusted layout plan and integrate node density information to determine a preliminary pickup route sequence; Specifically, the path node distribution data is obtained through the adjusted layout plan, and the node density information is integrated to determine the preliminary pickup route sequence.

[0092] It can be understood that the path node distribution data reflects the connection relationship between the cargo location and the channel in the warehouse.

[0093] For example, the adjusted layout shows that cargo B-002 is located at position 1 in area X, near the entrance, and cargo A-001 is located at position 3 in area Y, near the rear. Path nodes might be entrances, forklift turning points, or storage locations, while node density indicates the number of nodes per unit area.

[0094] For example, the node density in Area X is higher due to its proximity to the entrance, while the density in Area Y is lower. The initial pickup route sequence might be from the entrance to Area X, then to Area Y, then to Area Y.

[0095] S1072: Analyze the traffic efficiency between path nodes using real-time speed data to obtain dynamic adjustment requirements for the route sequence; Real-time speed data is used to analyze the traffic efficiency between path nodes and obtain the dynamic adjustment requirements of the route sequence.

[0096] Specifically, the real-time speed data comes from the actual operation records of the forklift or handling equipment.

[0097] For example, the speed from the entrance to Zone X (position 1) is 2 m / s because the distance is short and unobstructed. However, the speed from Zone X to Zone Y drops to 1 m / s because the path is longer and may have corners. Dynamic adjustment needs to be made based on this judgment, shortening the low-speed section or optimizing the turning point.

[0098] In one possible implementation, the system detects that the traffic efficiency from area X to area Y is low and recommends adjusting the route to bypass the congested corner.

[0099] S1073: Detecting intersection probabilities in the route sequence based on dynamic adjustment requirements; S1074: Determine whether there is a conflict point by combining the intersection probability and the conflict range information. If a conflict point exists, regenerate the pickup route by adjusting the node density to obtain an updated route sequence. Detect the intersection probability in the route sequence and combine it with the conflict range information to determine whether there is a conflict point.

[0100] It should be noted that the intersection probability refers to the possibility that multiple pickup routes overlap at a certain node.

[0101] For example, if two workers simultaneously retrieve B-002 and C-003, their paths intersect at the forklift lane, with a 70% probability of intersection. The conflict range information includes the width of the intersection, such as a 1.5-meter width, which prevents forklifts from moving in parallel.

[0102] In one embodiment, if such a conflict point is detected, the system marks it as an area that needs to be optimized. If a conflict point exists, the pickup route is regenerated by adjusting the node density to obtain an updated route sequence.

[0103] Preferably, adjusting the node density can reduce the number of nodes at the intersection.

[0104] For example, some nodes in Area X were merged to reduce density, allowing the route to avoid intersections with fork lanes. The updated route now goes directly from the entrance to Area X, Station 1, and then along the side passage to Area Y, Station 3. This adjustment reduces conflicts and improves traffic flow.

[0105] S1075: For the updated route sequence, obtain the real-time speed change trend of the path nodes to determine a preliminary plan for optimizing the path; For the updated route sequence, the real-time speed change trend of the path nodes is obtained to determine the preliminary plan for optimizing the path.

[0106] Specifically, the speed change trend can reflect the effect of node adjustment.

[0107] For example, the side channel speed is stabilized at 1.8 m / s, which is better than the 1 m / s of the original corner section. Therefore, the preliminary plan retains the side channel design to ensure improved efficiency.

[0108] S1076: Use the A-star algorithm to integrate the node density and speed data in the preliminary plan of the optimized path to calculate the conflict-free optimal pickup path sequence.

[0109] The A-star algorithm is used to fuse the node density and speed data in the preliminary plan to calculate the conflict-free optimized path sequence.

[0110] In one embodiment, the A-star algorithm uses node density as a weight and speed as a cost, and calculates a path from the entrance to position 1 in area X in only 3 seconds, and to position 3 in area Y in a total of 10 seconds.

[0111] For example, the optimized route sequence is entrance-side channel-X zone position 1-Y zone position 3, with no intersections to ensure smooth transportation. This approach significantly improves pickup response speed and optimizes resource utilization.

[0112] In step S108, the handling equipment is guided to perform the pickup operation according to the optimal pickup path sequence, and real-time speed data and the location coordinates of dynamic obstacles are obtained from the operation log to determine the accuracy of the path intersection probability detection and update the conflict detection range. The steps include: S1081: driving the transport equipment to perform the picking task according to the optimal picking path sequence, and obtaining real-time speed data and location coordinates of dynamic obstacles from the operation log; Specifically, the optimal pickup path sequence is used to drive the handling equipment to perform the pickup task. The operation log provides real-time speed data and the location coordinates of dynamic obstacles, which lays the foundation for understanding the task execution status.

[0113] Understandably, the operation log records the actual operation of handling equipment in the warehouse. For example, a forklift departs from the entrance and travels along the side aisle to pick up item B-002 from location 1 in area X. Real-time speed data indicates that it maintains a speed of 1.8 m / s in the side aisle, while the coordinates of a dynamic obstacle indicate a temporarily stacked item near location 2 in area Y at coordinates (5, 12). These data reflect operational characteristics in a dynamic environment.

[0114] S1082: Analyze the intersection probability of dynamic obstacles with the pickup path based on their location coordinates to determine potential conflict areas in the path sequence, and use real-time speed data to compare the efficiency of handling equipment in the conflict areas. It is particularly important to analyze the intersection probability of dynamic obstacles with the pickup path based on their location coordinates and determine the potential conflict area.

[0115] Specifically, the forklift path is entrance-side channel-position 1 of area X-position 3 of area Y, and the obstacle is located at (5,12), close to the intersection of the channel in area Y.

[0116] For example, if the obstacle occupies a width of 1 meter and the channel width is only 2 meters, the forklift may be blocked when passing through, and the intersection probability can reach 60%.

[0117] In one possible implementation, the system calculates the intersection of the obstacle and the path based on coordinates and marks the area around position 2 in zone Y as a conflict zone. This analysis helps identify risk points in advance. Using real-time speed data to compare the efficiency of handling equipment in the conflict zone can further determine the accuracy of intersection probability detection.

[0118] For example, the speed of the forklift in the side channel is 1.8 m / s, and drops to 0.5 m / s when approaching position 2 in area Y, indicating that the obstacle significantly affects passage.

[0119] Preferably, if the preset threshold is that the crossing probability detection accuracy must reach 80%, but the actual detection probability calculated based on speed change is only 60%, it means that the detection is not accurate enough.

[0120] S1083: Determine whether the detection accuracy of the intersection probability meets a preset threshold. If the detection accuracy is lower than the preset threshold, adjust the conflict range according to the position coordinates of the dynamic obstacle to update the conflict detection range.

[0121] It should be noted that the correlation between the speed drop and the obstacle location directly affects the reliability of the judgment. If the detection accuracy is lower than the threshold, the conflict range is adjusted based on the location coordinates of the dynamic obstacle to provide an updated detection basis.

[0122] In one embodiment, the system expands the conflict range from the single point at position 2 in zone Y to the surrounding 1-meter area, and the coordinate range is adjusted to (4-6, 11-13).

[0123] For example, the forklift's premature deceleration to 1 m / s at (5,11) indicates that the obstacle's impact range exceeded expectations. This dynamic adjustment makes the collision zone more realistic, optimizing the detection basis. This approach improves the adaptability of path planning, ensuring that handling equipment avoids risky areas and enhancing task execution stability.

[0124] For example, the adjusted detection basis can also support the collaborative operation of multiple devices.

[0125] For example, if two forklifts are picking up goods from location 1 in area X and location 3 in area Y, respectively, the system can use the updated conflict range to schedule one truck to go directly along a side aisle while the other takes a detour along an alternate route, thus avoiding intersection congestion. This flexibility significantly enhances the efficiency of equipment scheduling within the warehouse.

[0126] In step S109 , the path length change is analyzed according to the updated conflict detection range, and the storage layout is adjusted by using the frequency fluctuation and the dynamic obstacle coordinates to obtain an optimized resource allocation solution.

[0127] Path length changes are analyzed within the conflict detection range to determine the weight exceedance status. If the weight exceedance status exceeds a preset threshold, the obstacle coordinate data of the dynamic obstacle is obtained to determine the coordinate distribution characteristics. Based on the coordinate distribution characteristics, the access frequency fluctuations are extracted to determine the frequency fluctuation range. The frequency fluctuation range is used to adjust the storage layout structure and obtain the adjusted layout parameters. The resource allocation logic is updated using the adjusted layout parameters to obtain a preliminary allocation plan. The preliminary allocation plan is compared with the obstacle coordinate distribution to determine the optimization level. If the optimization level is below the preset threshold, the final allocation plan is iteratively adjusted using the frequency fluctuation range and obstacle coordinates.

[0128] Specifically, the path length variation is analyzed through the conflict detection range.

[0129] It is understandable that the core of this analysis lies in identifying the actual extension of the path due to dynamic obstacles.

[0130] For example, a transport device originally planned to have a 20-meter path from the warehouse entrance to Area X, Location 1, but was forced to detour to 25 meters due to a temporary pile of goods near Area Y, Location 2. This increase in path length directly reflects the weighted excess state.

[0131] For example, if the preset threshold is that the path extension does not exceed 10%, that is, 22 meters, and the actual extension exceeds 25 meters, then the weight exceeds the state. This method intuitively reflects the impact of obstacles on the path.

[0132] In a possible implementation, after the weight exceeds the threshold, the system obtains coordinate data of the dynamic obstacle.

[0133] For example, an obstacle is located at position 2 in area Y with coordinates 5, 12, and another obstacle is located at position 3 in area Y with coordinates 6, 14. The coordinate distribution characteristics show that the obstacles are concentrated near the channel in area Y and are arranged linearly.

[0134] It should be noted that this distribution pattern suggests that the obstruction may be caused by the regular placement of temporary piles of goods. Based on this, the fluctuation of the extraction frequency is particularly important.

[0135] For example, the frequency of cargo retrieval at position 1 in area X was originally stable at 5 times per day, but due to a detour, it dropped to 3 times. The frequency at position 3 in area Y fluctuated from 4 times to 2 times due to obstacles, and the frequency fluctuation range was thus determined to be 2-5 times.

[0136] Specifically, the frequency fluctuation range can be used to adjust the storage layout structure.

[0137] In one embodiment, based on a fluctuation range of 2-5, the system moves high-frequency goods from location 2 in area Y to a spare location in area X, reducing channel pressure in area Y. The adjusted layout parameters result in a 20% reduction in storage density in area Y and a 15% increase in the utilization of the spare location in area X.

[0138] Preferably, by updating the resource allocation logic through these parameters, the preliminary allocation plan may deploy two handling devices to area X and the backup channel respectively to avoid congestion in area Y.

[0139] For example, one device is responsible for picking up goods at position 1 in area X, while another device takes a backup route directly to position 3 in area Y. For the preliminary allocation plan, it is necessary to compare the obstacle coordinate distribution to determine the degree of optimization.

[0140] For example, obstacle coordinates 5, 12 and 6, 14 show that there is still potential conflict in the Y zone channel. If the equipment detour time is only reduced by 10% after the solution is executed, which is lower than the preset optimization threshold of 30%, the optimization is insufficient.

[0141] In one possible implementation, the system iteratively adjusts the frequency fluctuation range 2-5 times with the obstacle coordinates.

[0142] For example, analysis revealed that the frequency drop was primarily due to an obstruction at position 2 in area Y. This led to the distribution of its cargo to a backup position at coordinates 4 and 11. The resulting distribution plan was adjusted to one machine taking cargo from area X along a side channel, while another detoured along the backup route to position 3 in area Y. This reduced detour time to 5%, approaching the optimal state.

[0143] Exemplarily, this iterative adjustment can also support multi-device collaboration.

[0144] For example, when two handling devices pick up goods separately, the updated plan ensures that the paths do not intersect, and the equipment waiting time is reduced from 5 minutes to 2 minutes.

[0145] It's understandable that the combination of frequency fluctuation and coordinate distribution not only optimizes a single path but also improves overall scheduling efficiency. This approach provides a reliable basis for resource allocation in dynamic environments.

[0146] Reference Figure 2 The second embodiment of the present application provides a smart factory warehouse management system based on big data, including: A preliminary location mapping module is used to assign an identification code to each piece of goods using RFID technology, and to obtain the initial location data of the goods at the warehouse entrance by binding the goods to a collection device equipped with a sensor and recording it in a database, thereby obtaining a preliminary location map; a dynamic location distribution determination module, configured to analyze the movement trajectory of the goods from the warehouse entry to the storage point using a positioning algorithm combined with multi-point sensor data based on the preliminary location mapping to calculate the path node density, thereby determining the current dynamic location distribution of the goods; a module for obtaining a quantitative value of a demand change trend, for fusing historical pickup data within a classified time window using time series processing technology based on the dynamic location distribution to calculate pickup frequency fluctuations, thereby obtaining a quantitative value of the demand change trend of the goods; A module for determining the optimal storage area for high-frequency goods is configured to determine whether the quantified value of the demand change trend exceeds a frequency threshold, and when the quantified value of the demand change trend exceeds the frequency threshold, classify the goods into high-frequency and low-frequency categories by combining a clustering algorithm with frequency fluctuations and cargo volume parameters, thereby determining the optimal storage area for high-frequency goods. A storage location adjustment demand acquisition module is used to obtain coded associated data through cargo identification according to the optimized storage area of ​​the high-frequency cargo and integrate it into dynamic storage to obtain storage location adjustment requirements; An adjusted layout plan acquisition module is used to re-plan the storage locations by dividing the granularity by area using a simulated annealing algorithm and combining the cargo volume parameters according to the adjustment requirements of the storage locations, so as to obtain an adjusted layout plan; A conflict-free optimal pickup path sequence acquisition module is used to generate pickup paths based on the adjusted layout plan using the A-star algorithm combined with path node density and real-time speed data, while also detecting path intersection probability and conflict range to obtain a conflict-free optimal pickup path sequence; a conflict detection range update module, configured to guide the handling equipment to perform the pickup operation according to the optimal pickup path sequence, and obtain real-time speed data and the location coordinates of dynamic obstacles from the operation log to determine the accuracy of the path intersection probability detection and update the conflict detection range; The optimized resource allocation scheme acquisition module is used to analyze the path length change according to the updated conflict detection range and adjust the storage layout by using frequency fluctuations and dynamic obstacle coordinates to obtain the optimized resource allocation scheme.

[0147] It should be noted that the smart factory warehouse management system based on big data provided in an embodiment of the present invention is used to execute all the process steps of the smart factory warehouse management method based on big data in the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0148] The present application also 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 program for smart factory warehouse management based on big data. When the processor executes the computer program, the steps in the above-mentioned embodiments of the smart factory warehouse management method based on big data 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 preliminary position mapping module.

[0149] 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, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0150] The electronic device may be a computing device such as a desktop computer, notebook, PDA, or smart tablet. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the aforementioned components are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0151] 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), 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. The processor is the control center of the electronic device and connects various parts of the entire electronic device using various interfaces and lines.

[0152] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0153] If the module / unit integrated into the electronic device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0154] It should be noted that the device embodiments described above are merely illustrative, 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 across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the 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 can understand and implement the present invention without inventive effort.

[0155] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this application by those skilled in the art should be included within the scope of protection of this application.

Claims

1. A smart factory warehouse management method based on big data, characterized in that: include: Each piece of cargo is assigned an identification code through RFID technology, and the cargo is bound to a collection device equipped with a sensor to obtain the initial location data of the cargo at the warehouse entrance and record it in the database, thereby obtaining a preliminary location map; Based on the preliminary location mapping, the movement trajectory of the goods from the warehouse to the storage point is analyzed by a positioning algorithm combined with multi-point sensor data to calculate the path node density, thereby determining the current dynamic location distribution of the goods; Based on the dynamic location distribution, historical pickup data within a classified time window is integrated using time series processing technology to calculate the pickup frequency fluctuation, thereby obtaining a quantitative value of the demand change trend of the goods; determining whether the quantified value of the demand change trend exceeds a frequency threshold, and if the quantified value of the demand change trend exceeds the frequency threshold, classifying the goods into high-frequency and low-frequency categories by combining a clustering algorithm with frequency fluctuations and cargo volume parameters, thereby determining an optimized storage area for high-frequency goods; According to the optimized storage area of ​​the high-frequency goods, the coding-related data is obtained through the goods identification and integrated into the dynamic storage to obtain the adjustment requirements of the storage location; According to the adjustment requirements of the storage locations, the storage locations are replanned by dividing the granularity by area using a simulated annealing algorithm and combining the cargo volume parameters to obtain an adjusted layout plan; Based on the adjusted layout plan, the A-star algorithm is used to combine the path node density and real-time speed collection to generate the pickup path, and the path intersection probability and conflict range are detected at the same time to obtain the conflict-free optimal pickup path sequence; Instructing the handling equipment to perform the pickup operation according to the optimal pickup path sequence, and obtaining real-time speed data and the location coordinates of dynamic obstacles from the operation log to determine the accuracy of the path intersection probability detection and update the conflict detection range; The path length change is analyzed according to the updated conflict detection range, and the storage layout is adjusted by using frequency fluctuations and dynamic obstacle coordinates to obtain an optimized resource allocation solution.

2. The smart factory warehouse management method based on big data according to claim 1 is characterized in that: The method further includes: analyzing the movement trajectory of the goods from the warehouse to the storage point by combining a positioning algorithm with multi-point sensor data based on the preliminary location mapping to calculate the path node density, thereby determining the current dynamic location distribution of the goods; and then: Verify the matching status between the location distribution of the goods and the storage points through multi-point analysis; Determine whether there is a deviation between the position distribution and the storage point; if the deviation exists, cluster the sensor data using a K-means algorithm to obtain an abnormal node set; According to the abnormal node set, the corresponding movement trajectory segment is extracted from the trajectory analysis to determine the time range of the abnormality; Correcting the dynamic position using the sensor data of the time range in which the anomaly occurred in combination with the positioning algorithm to obtain the adjusted position distribution of the cargo; According to the adjusted location distribution, the current dynamic location distribution of the goods is updated by comparing the storage point data.

3. The smart factory warehouse management method based on big data according to claim 1 is characterized in that: The method of fusing historical pickup data within a classified time window using time series processing technology based on the dynamic location distribution to calculate the pickup frequency fluctuation, thereby obtaining a quantitative value of the demand change trend of the goods, includes: Extracting storage location information of the goods according to the dynamic location distribution to establish a location index table; Using a sliding time window method, the pickup records within a specified time range are obtained from the historical database, and the frequency of pickup corresponding to each location in the location index table is calculated using a frequency analysis algorithm; Determining whether the access frequency value exceeds a preset threshold, and if the access frequency value exceeds the preset threshold, marking the location as a high-frequency access area; Based on the distribution of the high-frequency access areas, a cluster analysis method is used to divide the storage areas of the goods; By using time series processing technology, a fluctuation analysis is performed on the access frequency of each storage area, and based on the results of the fluctuation analysis, a regression model is used to quantify the demand change trend to obtain a quantitative value of the demand change trend of the goods.

4. The smart factory warehouse management method based on big data according to claim 1 is characterized in that: The determining whether the quantified value of the demand change trend exceeds the access frequency threshold, and when the quantified value of the demand change trend exceeds the access frequency threshold, using a clustering algorithm in combination with access frequency fluctuations and cargo volume parameters to classify the cargo into high-frequency and low-frequency categories, thereby determining an optimized storage area for high-frequency cargo, includes: Obtaining a quantitative value and usage frequency data of the demand change trend through historical usage records, and determining whether the quantitative value exceeds a preset usage frequency threshold to obtain an over-threshold mark; Extracting frequency fluctuation data based on the above-threshold markers, fusing the volume parameters of the cargo, and using a clustering algorithm to divide high-frequency cargo into low-frequency cargo to determine a classification result; For the high-frequency goods in the classification results, calculate the fluctuation amplitude through frequency fluctuation analysis to obtain the priority ranking of the high-frequency goods; The area division granularity is calculated by combining the priority sorting with the volume parameters of the goods to determine the area range for optimized storage of the high-frequency goods.

5. The smart factory warehouse management method based on big data according to claim 1 is characterized in that: According to the adjustment requirements of the storage locations, the storage locations are replanned by dividing the granularity by area using a simulated annealing algorithm and combining the cargo volume parameters to obtain an adjusted layout plan, including: According to the adjustment requirements of the storage location, combining layout information to extract the area division granularity; Determining whether the region division granularity meets the storage requirement; if the region division granularity does not meet the storage requirement, adjusting the region division granularity by a simulated annealing algorithm to obtain an optimized division result; Obtaining volume parameters of the cargo based on the optimized division results to determine a preliminary layout plan for storage locations; The position parameters are integrated with the preliminary layout plan, and the storage positions are recalculated using a simulated annealing algorithm to obtain the adjusted layout plan.

6. The smart factory warehouse management method based on big data according to claim 1 is characterized in that: According to the adjustment requirements of the storage locations, the storage locations are replanned by dividing the granularity by area using a simulated annealing algorithm and combining the cargo volume parameters to obtain an adjusted layout plan, which then includes: Analyze the matching degree of the coded association data according to the adjusted layout scheme; It is determined whether the matching degree is lower than a preset threshold. If the matching degree is lower than the preset threshold, the layout information is readjusted by dynamically storing data to determine a final optimized layout solution.

7. The smart factory warehouse management method based on big data according to claim 1 is characterized in that: According to the adjusted layout plan, the pickup path is generated by combining the path node density and real-time speed collection through the A-star algorithm, and the path intersection probability and conflict range are detected to obtain the conflict-free optimal pickup path sequence, including: Obtaining path node distribution data according to the adjusted layout plan and integrating node density information to determine a preliminary pickup route sequence; Using real-time speed data to analyze the traffic efficiency between path nodes to obtain dynamic adjustment requirements for the route sequence; detecting intersection probabilities in the route sequence according to the dynamic adjustment requirements; Combining the intersection probability and the conflict range information, determining whether a conflict point exists; if the conflict point exists, regenerating the pickup route by adjusting the node density to obtain an updated route sequence; For the updated route sequence, obtaining the real-time speed change trend of the path nodes to determine a preliminary plan for optimizing the path; The A-star algorithm is used to integrate the node density and speed data in the preliminary plan of the optimized path to calculate the conflict-free optimal pickup path sequence.

8. The smart factory warehouse management method based on big data according to claim 1 is characterized in that: The method of guiding the handling equipment to perform the picking operation according to the optimal picking path sequence and obtaining real-time speed data and the position coordinates of dynamic obstacles from the operation log to determine the accuracy of the path intersection probability detection and update the conflict detection range includes: Driving the handling equipment to perform the picking task according to the optimal picking path sequence, and obtaining real-time speed data and position coordinates of dynamic obstacles from the operation log; Analyzing the intersection probability of the dynamic obstacle with the pickup path based on the location coordinates of the dynamic obstacle to determine potential conflict areas in the path sequence, and using the real-time speed data to compare the efficiency of the handling equipment in the conflict area; It is determined whether the detection accuracy of the intersection probability meets a preset threshold; if the detection accuracy is lower than the preset threshold, the conflict range is adjusted according to the position coordinates of the dynamic obstacle to update the conflict detection range.

9. A storage medium, characterized in that: The storage medium stores computer program data, which, when executed, can implement the big data-based smart factory warehouse management method as described in any one of claims 1 to 8.

10. A smart factory warehouse management system based on big data, characterized by: include: A preliminary location mapping module is used to assign an identification code to each piece of goods using RFID technology, and to obtain the initial location data of the goods at the warehouse entrance by binding the goods to a collection device equipped with a sensor and recording it in a database, thereby obtaining a preliminary location map; a dynamic location distribution determination module, configured to analyze the movement trajectory of the goods from the warehouse entry to the storage point using a positioning algorithm combined with multi-point sensor data based on the preliminary location mapping to calculate the path node density, thereby determining the current dynamic location distribution of the goods; a module for obtaining a quantitative value of a demand change trend, for fusing historical pickup data within a classified time window using time series processing technology based on the dynamic location distribution to calculate pickup frequency fluctuations, thereby obtaining a quantitative value of the demand change trend of the goods; A module for determining the optimal storage area for high-frequency goods is configured to determine whether the quantified value of the demand change trend exceeds a frequency threshold, and when the quantified value of the demand change trend exceeds the frequency threshold, classify the goods into high-frequency and low-frequency categories by combining a clustering algorithm with frequency fluctuations and cargo volume parameters, thereby determining the optimal storage area for high-frequency goods. A storage location adjustment demand acquisition module is used to obtain coded associated data through cargo identification according to the optimized storage area of ​​the high-frequency cargo and integrate it into dynamic storage to obtain storage location adjustment requirements; An adjusted layout plan acquisition module is used to re-plan the storage locations by dividing the granularity by area using a simulated annealing algorithm and combining the cargo volume parameters according to the adjustment requirements of the storage locations, so as to obtain an adjusted layout plan; A conflict-free optimal pickup path sequence acquisition module is used to generate pickup paths based on the adjusted layout plan using the A-star algorithm combined with path node density and real-time speed collection, while simultaneously detecting path intersection probability and conflict range to obtain a conflict-free optimal pickup path sequence; a conflict detection range update module, configured to guide the handling equipment to perform a pickup operation according to the optimal pickup path sequence, and obtain real-time speed data and the position coordinates of dynamic obstacles from the operation log to determine the accuracy of the path intersection probability detection and update the conflict detection range; The optimized resource allocation scheme acquisition module is used to analyze the path length change according to the updated conflict detection range and adjust the storage layout by using frequency fluctuations and dynamic obstacle coordinates to obtain the optimized resource allocation scheme.

Images